• 1. Boosting the accuracy of risk predictions.

Amgen
In the U.S., half of all women over the age of 50 will have an osteoporosis-related bone break in her lifetime. Yet less than half of all patients with osteoporosis are
ever diagnosed, and just 25 percent ever receive treatment. Leveraging historical data already on file, Amgen is attempting to address this gap with two calls to
action: 1) reduce the risk prediction window from 10 to two years; 2) drive increased awareness of near-term fracture risk to support appropriate osteoporosis
diagnosis for patients.
• Amgen built a sequential neural network, capable of learning order dependence in sequence prediction problems. These approaches, inspired from state-of-the-art
natural language processing algorithms, have shown relevance to healthcare applications in recent research. The models learned “fingerprints” of patients in a
latent vector space to estimate sequences more commonly associated with fracture patients and used a tree-based model to predict risk. Together, the neural
network and sequence prediction have shown promising early results in predicting imminent fractures from the historical data set.
• 2. Making patient care more intuitive.
It’s no secret that healthcare in the U.S. is in need of change. This $3.5 trillion industry has not yet been disrupted. Imagine a world where data analytics could
be used to change patient care or predict serious illnesses before a patient ends up hospitalized.
• Take cardiovascular disease as an example. While a patient’s chances of surviving heart failure are somewhat better today than they were a decade ago, we still live
in an era where someone in the U.S. suffers a heart attack every 40 seconds. And once an event strikes, the stakes are high.
• To help address this, Amgen has both internally developed as well as partnered with a handful of niche startups in the medical research and data science space
since 2015 to hone a series of machine-learning algorithms and devices with the potential to predict risk of certain serious illnesses before they strike. For example,
Amgen is exploring ways that novel home monitoring technology could be used as part of clinical trials with Emerald Innovations, a spin out from Prof. Dina Katabi’s
lab at MIT.
• 3. Using data to determine the most effective treatment for individual patients.
Multiple myeloma (MM) is a rare, complex blood cancer with no known cure, and represents just two percent of all cancers. Many patients receiving the
diagnosis have never heard of this incurable disease but have to learn quickly to map out treatment options with an oncologist or hematologist.
• Amgen is now striving to arm clinicians with insights into the patient response of different therapies, thereby improving patient outcomes throughout the
treatment journey. Amgen has partnered with GNS Healthcare, which specializes in analyzing both clinical trial and real-world data to model patient response to
treatment using artificial intelligence and Bayesian modeling, to play out different “what if” scenarios.
• 4. Supporting compliance via real-time answers.
Internally, Amgen is using AI to drive activities across the company with an eye for improving how it operates and fulfills its mission to serve patients.
Specifically, it’s using technology to support one of its core tenets: do the right thing. In an industry where patients are involved, there is no room for error.
• Amgen recognized that by pushing the boundaries of advanced text recognition, artificial intelligence could be used to provide real-time answers to questions
related to compliance and regulations. Collaborating with Avata Intelligence, a leader in AI for enterprise-level solutions, Amgen created ASK, an application that
uses AI and natural language processing to provide fast answers with accuracy, consistency, and confidence.
 Bayer
• Cyclica: Cyclica was included in Bayer's Grants4Apps program, and in November 2018 announced that
Bayer was using its technology for off-target effect investigation, pharmacokinetic property prediction,
and multi-targeted drug design.
• Genpact: Genpact worked with Bayer to apply AI to pharmacovigilance. Genpact's technology
automatically extracts adverse event data from source documents.
• Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY): Bayer is a member of the
MELLODDY project, which will train machine learning models on datasets from multiple partners while
ensuring the privacy of each partner using federated learning.
• Machine Learning for Pharmaceutical Discovery and Synthesis Consortium (MLDPS): Bayer is a member
of MLDPS, which is a collaboration with MIT to develop software for automating small molecule
discovery and synthesis.
• Schrödinger: In January 2020, Schrödinger and Bayer announced a five-year alliance to create a new
solution for Bayer to enumerate, screen, and score synthetically feasible, virtual compounds. The
software will combine Schrödinger’s physics-based modeling and machine learning technology with
Bayer’s proprietary in silico models.
• Sensyne Health: Bayer and Sensyne are collaborating to develop treatments for cardiovascular disease.
Sensyne has a unique partnership with the NHS to leverage its electronic patient record data while
protecting patient privacy. The partners also established the "LifeHub" project, focused on AI-enabled
radiology and imaging.
• A new collaboration between Bayer and UK-based Exscientia is set to accelerate the discovery of small
molecule drugs, focused on cardiovascular disease and oncology.
• The companies have announced that they will use artificial intelligence (AI) to further the development
of drug candidates for three of Bayer’s projects in the areas of cardiovascular disease (CVD) and
oncology.
 Eli Lilly
• Atomwise: Atomwise Inc. today announced a multi-year agreement with Eli
Lilly and Company to apply Atomwise’s patented artificial intelligence (AI)
technology in support of Lilly’s preclinical drug discovery efforts. The
companies will collaborate on up to ten drug targets selected by Lilly, with
the goal of accelerating the time it takes to identify and develop potential
new medicines.
• Lilly is a recognized leader in virtual library design, with a massive number
• of molecules enabled by automated synthesis in their robotic laboratory.
• Identifying which of these molecules might be a potentially new
therapeutic for specific diseases is a scientific and analytical challenge, and
that is well suited for Atomwise’s AI technology.
 GSK
• ATOM: GSK was the first pharmaceutical company to participate in the Accelerating Therapeutics
for Opportunities in Medicine (ATOM) Consortium, which aims to leverage artificial intelligence to
go from drug target to patient-ready therapy in less than a year. (An ambitious goal.) GSK gave
ATOM chemical and in vitro biological data for more than 2 million compounds it has screened.
• Alliance for Artificial Intelligence in Healthcare (AAIH): GSK is a founding member of the AAIH.
• Cloud Pharmaceuticals: Cloud Pharmaceuticals is partnering with GSK to use AI for the design of
novel small-molecule drugs.
• Exscientia: GSK's partnership with Excscientia is to discover novel and selective small molecules
for up to 10 disease-related targets across undisclosed therapeutic areas. In early April 2019,
Exscientia announced that its partnership with GSK had produced its first tangible result: a "highly
potent" lead molecule targeting a novel pathway for chronic obstructive pulmonary disease.
• Google: While I didn't see any formal partnership announcement, GSK researchers have worked
with Google researchers on applying AI to drug discovery, including to develop a machine learning
algorithm to identify protein crystals.
• Insilico Medicine: Insilico is partnering with GSK to identify novel biological targets and pathways.
• Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY): GSK is a member of the
MELLODDY project, which will train machine learning models on datasets from multiple partners
while ensuring the privacy of each partner using federated learning.
• University of Nottingham: GSK has a collaboration with researchers at the Universities of
Strathclyde and Nottingham, announced in July 2019, that focuses on applying AI to synthetic
chemistry.
 AbbVie
• AiCure: AbbVie used AiCure's AI-based patient monitoring platform to improve
adherence in an phase 2 schizophrenia trial. ("AiCure announces new study results
demonstrating 90% adherence from Phase 2 Abbvie study," 9/26/2016.)

• Atomwise: AbbVie is listed on the Atomwise partner page. It uses deep convolutional
neural network AtomNet to empower structure based drug design. Atomwise was
founded in 2015 and since then established a number of confidential collaborations
with high profile organization, such as pharma giants Merck, and Abbvie, as well as
Stanford University, Duke University School of Medicine and so on.
 Merck Group
• Merck and Wayra UK are working together (part of Spanish telecoms
business Telefonica) under the banner of the ‘Velocity Health’ programme.
The Velocity Health programmes focused on prevention in healthcare with
an emphasis on diabetes prevention and cancer prevention.
• FDA grants breakthrough device designation to artificial intelligence
software for Chronic Thromboembolic Pulmonary Hypertension pattern
recognition from MSD and Bayer. The software processes image findings of
cardiovascular, lung perfusion and pulmonary vessel analyses in
combination with the patient’s history of pulmonary embolism.
• Merck (MSD) and Accenture in collaboration with Amazon Web Services
(AWS), launched a cloud-based informatics research platform to improve
productivity, efficiency and innovation in the early stages of drug
development.
• Merck Sharp & Dohme (MSD) Corp., a subsidiary of Merck & Co., Inc has
developed an Artificial Intelligence (AI) chat bot. The MSD Salute chat bot is
designed to aid physicians in providing product information and pathology.
 Sanofi
• Sanofi Genzyme, the specialty care global business unit of Sanofi joined with Recursion Pharmaceuticals to
deploy its drug repurposing platform to identify new uses for Sanofi’s clinical stage molecules across dozens
of genetic diseases.
• Sanofi joined with Exscientia (AI driven company) to identify and validate combinations of drug targets for
metabolic disorders like diabetes. In August 2019, Exscientia announced that Sanofi exercised its option for a
bispecific small molecule targeting inflammation and the progression of fibrosis.
• Sanofi joined with BERG to use BERG's proprietary Interrogative Biology® platform to assess potential
biomarkers of seasonal influenza vaccination outcomes in an unbiased and data-driven manner.
• Sanofi also connected with Researchably, a young startup incubated at UC Berkeley, for conducting a pilot
with Sanofi in China, using AI to sift through thousands of research studies and surface the most relevant
ones to pharma stakeholders.
• In June 2019, Sanofi joined with Google to establish a new virtual Innovation Lab. Through this partnership,
they will leverage deep analytics across data sets to better understand key diseases and extract related
patient insights. They were also planned to apply artificial intelligence (AI) across diverse datasets to better
forecast sales and supply chain efforts.
• An illustrative example is a recent R&D partnership between Sanofi and an emerging AI-driven
biotechnology company Recursion Pharmaceuticals in 2016 with the purpose to identify new uses for
Sanofi’s clinical stage molecules across dozens of genetic diseases. The Recursion’s approach is a “target-
agnostic” one, and is based on cellular phenotyping via image analysis using computer vision. Thousands of
morphological measures are thus extracted at the level of individual cells and large catalogs of molecules are
screened for the ability to “fix” phenotypic defects associated with each disease. Under the agreement,
Sanofi will provide Recursion with a number of small molecules, and Recursion will screen them across its
rapidly expanding library of genetic disease models and use machine learning technology to derive
promising new indications.
 Gilead Sciences
• Glympse Bio: In October 2019, Gilead and Glympse Bio announced a
strategic collaboration in nonalcoholic steatohepatitis (NASH) that will
leverage Glympse's AI-powered synthetic biomarkers to determine
clinical trial participants’ stage of disease at initial screening, and their
response to treatment.
• Insitro:Gilead's first publicly announced use of AI in drug discovery
was in April 2019. This month, Gilead announced a strategic
collaboration with stealthy startup Insitro. The collaboration will focus
on nonalcoholic steatohepatitis (NASH). Gilead will use Insitro's
platform to create disease models for NASH and find targets that
affect the disease's progression and regression.
 Johnson & Johnson
• Johnson & Johnson announced results of a new real-world study, which found newly
diagnosed patients with nonvalvular atrial fibrillation (NVAF) taking XARELTO®
(rivaroxaban) experienced significantly fewer strokes, significantly fewer severe strokes
and fewer stroke-related deaths compared to those taking warfarin using artificial
intelligence. The study also found that XARELTO® significantly reduced overall strokes
(across all severities) by 18 percent compared to warfarin and reduced the risk of
experiencing the most severe strokes.
• Janssen has developed Neutrogena Skin360™ app which uses artificial intelligence (AI),
to track your skin's progress over time to give you deep information about your skin's
actual needs and health. It lead to personalize skincare.
• Johnson & Johnson Vision introduced Andy, a virtual assistant chatbot powered by
artificial intelligence (AI). It helps U.S. consumers throughout their ACUVUE® Brand
Contact Lens journey – from those considering contact lenses for the first time to long-
term wearers. The chatbot also provides intuitive coaching to help new wearers develop
healthy contact lens habits.
 Novartis
• Novartis was able to decode cancer pathology images through AI. Novartis joined with Tech startup PathAI
and created a system through which they are able to diagnose cancer.
• In June 2017, Novartis joined with IBM Watson for breast cancer clinical trial in which IBM was contributed
its data analytics and machine learning chops to better understand the expected outcomes of various breast
cancer treatments.
• In January 2018, Novartis partnered with McKinsey’s QuantumBlack to analyze 500 clinical trials operations
with machine learning around the world in realtime.
• In May 2018, MIT announced that Novartis became a member of its Machine Learning for Pharmaceutical
Discovery and Synthesis Consortium. In the same month, Intel collaborates with Novartis on the use of deep
neural networks to accelerate high content screening, a key element of early drug discovery.
• Novartis also collaborate with the University of Oxford’s Big Data Institute (BDI) to identify early predictors of
patient responses to treatments for inflammatory diseases, such as multiple sclerosis (MS) and psoriasis.
They also worked to identify patterns in data, often across multiple data sources and types (imaging,
genomics, clinical and biological), which cannot be detected by humans alone.
• In June 2019, the MELLODDY (Machine Learning Ledger Orchestration for Drug Discovery) consortium
created by 17 partners across Europe and Novartis was one of its members. Through this platform
companies will develop more accurate models to predict which compounds could be promising in the later
stages of drug discovery and development.
• On September 2019, Novartis and Microsoft announced a multiyear alliance which will leverage data &
Artificial Intelligence (AI) to transform how medicines are discovered, developed and commercialized.
Novartis is also establishing an AI Innovation Lab to empower associates to use AI across their business. Joint
research activities will include co-working environments on Novartis Campus (Switzerland), at Novartis
Global Service Center in Dublin, and at Microsoft Research Lab (UK) – starting with tackling personalized
therapies for macular degeneration; cell & gene therapy; and drug design.
 Roche
• Roche has developed a machine learning diagnostic techniques for
diabetic macular edema, a complication of diabetes that causes a
thickening of the retina and lead to blindness. Roche can utilise its
vast clinical trial database to develop AI algorithms to predict the
presence of disease, risk of disease progression, and response to
treatment; all of which could be supplied to ophthalmologists to
deliver higher quality personalised healthcare.
• In February 2018, Roche acquired Flatiron Health, an oncology-
focused electronic health records company. Flatiron's massive
amount of oncology data provides Roche with a tremendous asset for
machine learning.
 Pfizer
• Pfizer promoted a drug discovery partnership with IBM Watson. In December 2016, Pfizer and
IBM announced a partnership to accelerate drug discovery in immuno-oncology.
• In May 2018, Pfizer had fastened AI collaboration. Massachusetts Institute of Technology
announced Pfizer as a member of its Machine Learning for Pharmaceutical Discovery and
Synthesis Consortium. Pfizer also announced a partnership with Chinese tech startup XtalPi for
molecular stability of an organic compound and advanced their work in drug designing. As
reported by the wall street journal, Pfizer built analytics platform to identify patients with rare
diseases that might previously have gone undiagnosed.
• In September 2018, Pfizer announced to evaluate Atomwise’s platform to identify potential drug
candidates for up to three target proteins selected by Pfizer.
• CytoReason, a leader in machine learning for drug discovery and development, announced that it
had entered into a collaboration agreement with Pfizer Inc. that will leverage CytoReason’s cell-
centered models of the immune system. CytoReason’s proprietary platform helps rebuild lost
cellular information from gene expression data and associates genes to specific cells. This
information is then integrated with additional omics and literature data to create a cell-based
model of the trial-specific immune response.
• In April 2019, Pfizer joined with Concerto HealthAI to use AI and real world data in oncology. The
collaboration will conduct novel synthetic control arm and prospective Real World Data outcomes
study designs for therapeutics that are both pre- and post-approval.
• In September 2019, Pharmaceutical giant Pfizer announced plans to launch a one-year pilot
program with robotics company Catalia Health, maker of Mabu, a home robot that coaches
patients on health and prescription drugs. The main idea behind this collaboration is to
understand patients clinical journeys using artificial intelligence.
 Novo Nordisk
• Novo Nordisk has signed a deal with UK biotech e-Therapeutics to use its
AI-based drug discovery technology to find new therapies for type 2
diabetes.
• e-Therapeutics will work with Novo for a year and use its technology to
identify novel intervention strategies, biological pathways and compounds
that could form the basis of new therapies.
• e-Therapeutics uses a suite of powerful computational tools to augment
and interrogate the vast amount of biological information currently
available in both public and private databases.
• Using techniques such as machine learning, artificial intelligence (AI) and
state of the art data analysis, e-Therapeutics creates and analyses network
models of disease to identify likely proteins that could be disrupted to treat
diseases.
• The company said this approach more realistically reflects the true
complexity of disease with its multiple and often interconnected cellular
pathways.
 Celgene
• Artificial Intelligence (AI)-driven drug discovery company Exscientia has entered a
three-year AI drug discovery partnership with biopharma company Celgene,
including an initial $25 million upfront payment and eligibility to receive
substantial milestones based on the clinical, regulatory and commercial success
of the program.
• In addition, Exscientia is due to receive tiered royalties on net sales on any
product resulting from the collaboration.
• The collaboration will use AI to accelerate the discovery of small molecule
therapeutic drug candidates for three therapeutic programmes for Celgene in the
areas of oncology and autoimmunity.
• Exscientia will apply its full-stack AI drug discovery capabilities to the execution of
the entire project – from gene to the drug candidate.
• Applying AI to improve the speed of delivery of new treatments for patients is a
key goal of this collaboration.
 Takeda pharma
• Recursion announced progress in its collaboration with Takeda
Pharmaceutical on identifying novel preclinical candidates for rare
diseases. In 18 months, the partnership had led to the evaluation of
Takeda preclinical and clinical compounds in more than 60 unique
indications, with new therapeutic candidates identified in more than half-
a-dozen diseases. As a result, Takeda exercised its option for drug
candidates in two rare diseases and the two companies have extended the
partnership.
 Astra Zeneca
• Using AI to liberate our IMED scientists In discovery, we are also applying AI to make existing processes more efficient, and to turn data into
knowledge. We are using AI to reliably predict the results of routine assays, such as human plasmaprotein binding (hPPB) tests, to liberate our
scientists and give them more time to focus their passion for science on problems that will give AstraZeneca an even greater competitive edge. The
hPPB assay, developed in Drug Safety and Metabolism, is used to help us understand how a potential drug molecule is distributed within a patient.
We are working with world-leading partners to use the latest advances in AI to predict the results with a high degree of confidence. We are
currently assessing the utility of AI for safety screens, protein production, image analysis and the design of clustered regularly interspaced short
palindromic repeats (CRISPR) gene editing. In the months and years ahead, we expect to use AI to transform any area in the discovery process
where we collect data and turn that data into knowledge. In 2017, a testament to the success of machine derived efficiency was the development
of a virtual screening tool FastVS. The new “Google-like” webbased tool, developed in collaboration with OpenEye Scientific Software, reduces the
time to search and score entries in numerous large molecular databases, from hours to seconds, optimising the process of drug discovery.
• BenevolentAI: The partnership will focus on new drugs for chronic kidney disease and idiopathic pulmonary fibrosis.
• Berg: Berg is collaborating with AstraZeneca to identify and evaluate novel targets and therapeutics to treat neurological disorders such as
Parkinson's disease.
• DeepMatter: In December 2019, articles reported that DeepMatter would provide its AI-driven compound synthesis platform to AstraZeneca.
• Gatehouse Bio: In December 2019, Gatehouse Bio announced a partnership with AstraZeneca to explore the identification of new targets for
respiratory and cardiovascular diseases using its AI-powered platform. Gatehouse uses AI to identify novel small RNA (sRNA) signatures and
molecular pathways correlated with and potentially driving disease. Gatehouse had joined AstraZeneca's Boston Bio Hub Incubator in 2018.
• Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY): AstraZeneca is a member of the MELLODDY project, which will train
machine learning models on datasets from multiple partners while ensuring the privacy of each partner using federated learning.
• ProteinQure: In June 2019, I received a tip (see comments) that AstraZeneca, via subsidiary MedImmune, had established a multi-year collaboration
with ProteinQure. The exact nature of this partnership isn't clear.
• Schrödinger: AstraZeneca is collaborating with Schrödinger to deploy its drug design platform, which combines physics-based modeling and
machine learning, to identify new therapeutic candidates and improve the likelihood that synthesized compounds will have desired properties.
 Bristol-Myers Squibb(BMS)
• Bristol-Myers Squibb and Concerto HealthAI have announced plans to apply artificial intelligence
(AI) and real-world data to a diverse range of cancers in a multi-year strategic agreement.
• The collaboration will cover a diverse range of cancers, integrate multiple data sources, and apply
AI and machine learning to accelerate clinical trials, enable robust protocol design and generate
insights for precision treatment and improved patient outcomes.
• The partnership will give the American pharma giant access to Concerto’s eurekaHealth AI
insights platform, in order to accelerate insights through novel health economic outcomes and
clinical development synthetic control arm studies.
• The platform will give Bristol-Myers Squibb access to over a decade of real-world patient data
from geographically diverse community oncology practices.
• Concerto HealthAI: Concerto specializes in using AI to analyze real-world oncology data in order
to generate insights and real-world evidence. Its partnership with BMS covers a range of data
sources, cancers, and activities, including clinical trials, protocol design, and precision oncology
treatments.
• PathAI: In November 2019, PathAI announced investment from BMS and the Merck Global Health
Innovation Fund (Merck GHIF) in its AI-powered pathology platform.
• Sirenas: BMS partnered with Sirenas to apply the biotech company's technology to challenging
therapeutic targets. Sirenas uses data mining and machine learning to find therapeutic
applications of chemicals from global microbiome samples.
 Astellas
• Biovista: will explore new indications for a number of undisclosed Astellas compounds using its
Clinical Outcome Search Space (COSS) technology.

• Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY): MELLODDY aims to
train machine learning models across multi-partner datasets while ensuring privacy preservation
of both the data and the models by developing a platform using federated learning. The
MELLODDY platform uses Amazon Web Services technologies in order to execute Machine
Learning algorithms from academic partners on a large scale. The data never leaves the owner’s
infrastructure and only non-sensitive models are exchanged. A central dispatcher allows each
partner to share a common model to be consolidated collectively. To provide full traceability of
the operations, the platform is based on a private blockchain. This means that a ledger will be
distributed across all contributing pharma partners in such a way that there is no central
authority. The platform guarantees by design that partners keep control and visibility over their
own private data. Since there is no central authority, any communication between the dispatcher
and a ledger needs to be approved by all partners before one can proceed. Like a bank statement,
the ledger holds a log of all activities and can be requested after a federated run. The MELLODDY
platform is designed to prevent the leaking of proprietary information from one data set to
another or through one model to another while at the same time boosting the predictive
performance and applicability domain of the models by leveraging all available data.

• NuMedii: NuMedii will identify new indications for a number of undisclosed Astellas compounds
using its "Big Data intelligence" technology.
 Boehringer Ingelheim
• In order to support the identification of IPF at an earlier stage, Boehringer Ingelheim is
developing an artificial intelligence-based “Auscultation Aid” which works as follows: a
stethoscope with a digital interface is linked via a mobile phone to a cloud-based large
sound database. Using artificial intelligence, a patient’s lung sound recordings are then
compared with reference data from the sound database. This database was created from
recorded and confirmed diagnoses of lung diseases, collected in large clinical studies. The
auscultation aid immediately sends the physician a result in the form of a “probability
score” for a certain lung disease. If this score is higher than a pre-specified threshold
value, the tool will provide suggestions to the examining physician for additional
diagnostic steps, examinations and procedures.

• Boehringer Ingelheim tapped the drug discovery company Healx to help identify new
indications for molecules within its pipeline and to leverage its artificial intelligence
platforms to explore their potential against rare neurological conditions.

• Healx’s AI-based Healnet program draws from an array of data sources focused on rare
diseases and pharmacology—including targets, symptoms, sequencing results and
scientific literature—to help predict how well a treatment will match groups of patients.
The goal is to help the German drugmaker prioritize its indications for further research.
 Janssen
• Janssen Research & Development has collaborated with software solutions provider nference to leverage artificial intelligence (AI) and data sciences for the discovery and clinical
development of drugs.
• Under the project, Janssen R&D will use nference’s AI platform to support discovery and early development applications, including the identification and selection of new targets
and disease subsets to facilitate competitive therapeutic programmes.
• nference and Janssen will work together to improve the effectiveness and efficiencies of these processes. For example, patients will be stratified to detect individuals that would
most likely respond to each drug candidate. Another application would see sites and investigators required to advance clinical trials across certain hospitals.
• The partners will pursue additional related activities such as R&D compliance, regulatory affairs and medical safety.
• nference has developed a data science kernel to support the alliance. This will be used to synthesise certain Janssen R&D databases by leveraging real-time insights from the
nference AI platform across public biomedical knowledge bases.

• These activities will see the synthesis of unstructured, semi-structured and structured data sets, which will learn as the companies feed further insights into the platform.
• The aim of the project is to link biological information to disease condition and therapeutic mechanisms.
• Janssen Pharmaceutica has initiated a collaboration agreement to use Iktos’ artificial intelligence (AI) technology to accelerate small molecule drug discovery.
• Under the collaboration, Janssen will implement Iktos’ virtual design technology to several of its projects.
• The companies will partner to develop applications using Iktos’s knowledge in deep generative models and Janssen’s expertise in AI-enabled prediction of small molecule
activities.
• Iktos leverages deep generative models to develop new technology for in silico drug design, which has the potential to enable vast improvements in discovery workflows.
• BenevolentAI: One of the more unique AI drug development partnerships I've seen is that between Janssen and BenevolentAI. In November 2016, they announced that
BenevolentAI would license the right to develop, manufacture, and commercialize clinical stage drug candidates from Janssen after using artificial intelligence to identify
untapped potential in Janssen's portfolio. BenevolentAI launched a phase 2b trial for a drug from the partnership to treat sleepiness in people with Parkinson's disease.
• Celsius Therapeutics: Apart from collaborations to develop new drugs, Janssen is also applying AI to clinical trials. In July 2019, Celsius Therapeutics announced a partnership with
Janssen to use its single-cell genomics and machine learning platform to find predictive biomarkers of response in Janssen’s VEGA study of golimumab (Simponi) and guselkumab
(Tremfya) in patients with ulcerative colitis.
• Machine Learning Ledger Orchestration for Drug Discovery (MELLODDY): Janssen is a member of the MELLODDY project, which will train machine learning models on datasets
from multiple partners while ensuring the privacy of each partner using federated learning.
• WinterLight Labs: In January 2018, Johnson Johnson Innovation announced a partnership between Janssen and WinterLight Labs to try predicting dementia and
neurodegenerative diseases from voice samples obtained through Janssen clinical trials.
• Amplion
• Uses AI to: Synthesize biomedical knowledge and biomarker expertise to
guide biomarker strategic planning. Allows researchers to: Ensure an
effective mix of biomarkers, establish differentiation, recruit the right
patients, and identify the best companion diagnostic opportunities.
• BioSymetrics
• Uses AI to: Process raw phenotypic, imaging, drug, and genomic data
sets. Allows researchers to: Integrate rapid analytics and machine learning
capabilities into existing business processes to improve care, enhance
discoveries, gain insight into business, and enable fast data-driven
decisions.
• Biorelate
• Uses AI to: Create curated databases from the analysis of published
scientific literature. Allows researchers to: Extract structured biological
knowledge to power drug discovery applications.
• Causaly
• Uses AI to: Read scientific articles and extract causal
associations. Allows researchers to: Search for cause and effect
relationships and gather evidence on how biomedical entities
interact.
• Data2Discovery
• Uses AI to: Find hidden connections and new insights in diverse,
linked datasets. Allows researchers to: Understand and treat disease
by connecting data in new ways.
• Data4Cure
• Uses AI to: Infer and organize knowledge from thousands of genomic,
phenotypic, and clinical datasets. Allows researchers to: Identify new
targets and biomarkers, repurpose drugs, and identify disease
pathways amenable to combination therapy.
• Elucidata Corporation
• Uses AI to: Analyze complex biological datasets. Allows researchers to:
Standardize and streamline analysis of -omics data from multiple sources.
• Evid Science
• Uses AI to: Build a database of therapy evidence. Allows researchers to: Quickly
answer any comparative cost and outcome question.
• Genialis
• Uses AI to: Analyze multi-omics next-generation sequencing data for
contextual, systems-level insights. Allows researchers to: Reveal previously
unseen patterns across large, heterogeneous datasets to predict targets and
biomarkers.
• HelixAI
• Uses AI to: Respond to verbal questions and requests in a lab setting. Allows
researchers to: Increase efficiency, improve lab safety, keep current on relevant
new research, and manage inventory.
• Innoplexus
• Uses AI to: Generate insights from billions of disparate data points from thousands of data
sources. Allows researchers to: Improve decision-making by seeing information in context
from biomedical data sources including publications, clinical trials, congresses, and theses.
• Intellegens
• Uses AI to: Learn underlying correlations in fragmented datasets with incomplete
information. Allows researchers to: Estimate missing knowledge of how candidate drugs act
on proteins, to aid design of new drug cocktails that activate proteins to cure disease.
• InveniAI
• Uses AI to: Monitor millions of data points for signs of breakthrough events. Allows
researchers to: Detect early signals of innovation.
• Iris.ai
• Uses AI to: Establish and find the similarity of document "fingerprints" based on a
combination of keyword extraction, word embeddings, neural topic modeling, and other
natural language understanding techniques. Allows researchers to: Build reading lists faster,
with more precision and interdisciplinary inspiration.
• Kyndi
• Uses AI to: Analyze large amounts of data fast and provide explainable, auditable
results. Allows researchers to: Understand and extract meaning from internal data sets,
especially unstructured ones.
• LabTwin
• Uses AI to: Understand voice-based commands and transcribe voice-based notes. Allows
researchers to: Take notes and organize lab documentation faster and with less effort.
• LabVoice
• Uses AI to: Power voice-based interactions. Allows researchers to: Use their voice to query
lab equipment and software for information, as well as update records, take notes, and
trigger actions.
• Linguamatics
• Uses AI to: Extract and analyze text. Allows researchers to: Answer a range of life science
questions with natural language queries.
• Meta
• Uses AI to: Analyze and organize biomedical research. Allows researchers to: Receive a
personalized feed of the most relevant and important research as it's published.
• Mozi
• Uses AI to: Find patterns in biomedical data and infer hypotheses for investigation. Allows
researchers to: Upload datasets and have them analyzed in the context of global biomedical
knowledge, leading to new diagnostic and treatment strategies, particularly for personalized
medicine.
• Owkin
• Uses AI to: Build intelligence from distributed datasets, including through privacy-safe transfer and federated learning. Allows researchers to:
Overcome the problem of data-sharing in healthcare to automate diagnostics, predict treatment outcomes, and optimize clinical trials.
• PatSnap
• Uses AI to: Analyze over 114 million chemical structures, clinical trial information, regulatory details, toxicity data, and over 121 million patents and
other sources. Allows researchers to: Validate chemical development projects.
• Percayai
• Uses AI to: Organize and prioritize data in a contextual manner, enabling interactive 3D diagrams illustrating biological information. Allows
researchers to: Rapidly generate testable hypotheses from complex, omic, and multi-omic data sets.
• Plex Research
• Uses AI to: Allow for intuitive searches on the world's biomedical research data. Allows researchers to: Find relevant results for drug discovery-
related queries such as compounds for a specified target.
• Quertle
• Uses AI to: Retrieve and visualize relevant results from multiple biomedical data sources. Allows researchers to: Gain a deeper understanding of a
topic and avoid missing key information.
• Researchably
• Uses AI to: Search and organize information in research papers, clinical trial listings, and patents. Allows researchers to: Save time searching for
information while receiving more relevant and personalized results
• Sparrho
• Uses AI to: Curate, in combination with human expertise, millions of scientific papers from thousands of publications. Allows researchers to: Stay up-
to-date with new scientific publications and patents.
• ThoughtSpot
• Uses AI to: Enable natural language search on billions of rows of data from any source. Allows researchers to: Speed analysis of clinical trial results
and historical genomics data.
• Wisecube AI
• Uses AI to: Analyze internal and external datasets. Allows researchers to: Rank molecules for purchasing, repurpose drugs, and optimize clinical
studies.
• nference
• Uses AI to: Extract knowledge in real-time from commercial, scientific, and regulatory literature. Allows researchers to: Identify competitive white
space, eliminate blind spots in research, and discover disease similarities by phenotype for clinical trial design.
• Aiforia
• Uses AI to: Analyze images uploaded to their cloud environment. Allows researchers to: Detect any visible feature or pattern at scale, including in
tissues and cells to understand pathophysiology.
• Cambridge Cancer Genomics
• Uses AI to: Predict cancer progression from tumor DNA in blood samples. Allows researchers to: Determine treatment response and relapse earlier,
and use Bayesian adaptive clinical trial design to increase the success of late stage trials.
• CytoReason
• Uses AI to: Organize and standardize immune-related gene, protein, cell, and microbiome data into a single, machine-readable, cell-level view of the
immune-system. Allows researchers to: Gain novel insights related to mechanisms of disease, clinical markers, and drug discovery and validation.
• Empiric Logic
• Uses AI to: Analyze genomics and other biomedical data to identify probable causes of rare and common diseases. Allows researchers to: Gain new
insights into drug discovery and support the process of drug repositioning.
• Euretos
• Uses AI to: Analyze 200 omics databases, connecting published literature, experimental data, and clinical data. Allows researchers to: Get insight
into how molecular mechanisms influence cell and tissue functions, and how these in turn influence phenotypes and disease pathology.
• FDNA
• Uses AI to: Link phenotypic traits to genetic mutations. Allows researchers to: Discover new clinical signs, symptoms, and genes for biomarkers, and
access data to develop, test, and market precision medicines.
• OccamzRazor
• Uses AI to: Transform all available data about Parkinson's disease into machine-readable graphs. Allows researchers to: Have a complete map of
Parkinson's disease—the "Human Parkinsome"—and use it to better understand how the disease works, identify biomarkers, develop new targets,
and evaluate treatments.
• Phenomic AI
• Uses AI to: Analyze cell and tissue phenotypes in microscopy data. Allows researchers to: Rapidly and accurately profile single cells in microscopy
images.
• Precisionlife
• Uses AI to: Find combinations of genomic, phenotypic, and clinical features that define disease risk, prognosis, and therapy response in a complex
disease population. Allows researchers to: Find novel drug targets in existing datasets, identify drug repurposing opportunities, and improve
biomarker-driven patient stratification strategies.
• ReviveMed
• Uses AI to: Analyze metabolomic data along with other large-scale molecular information such as data from genes, proteins, drugs, and
diseases. Allows researchers to: Find disease pathways, novel drug targets, new therapeutic effects for existing drugs, molecular mechanisms for
pharmacological effects, and new biomarkers.
• Sensyne Health
• Uses AI to: Analyze ethically sourced, clinically curated, anonymised patient data from NHS Foundation Trusts. Allows researchers to: Discern
potential new physiological pathways and identify subgroups of patients most likely to respond well to treatments.
• Structura Biotechnology
• Uses AI to: Enable high-throughput structure discovery of proteins and molecular complexes from cryo-EM data. Allows researchers to: Discover
and understand the detailed three-dimensional structure of important protein molecules, complexes, and drug targets.
• Ariana Pharma
• Uses AI to: Explore complex datasets in order to reveal hidden relationships and to derive new hypotheses. Allows researchers to: Improve
identification and validation of biomarker signatures, identify the best patient responder sub-groups and populations at risk of adverse events, and
improve clinical trial success rates.
• Biodesix
• Uses AI to: Uncover clinically relevant blood-based biomarker patterns and relationships. Allows researchers to: Enable
personalized approaches to therapy selection and a better understanding of complex diseases like cancer. Founded:
2005. Headquarters: Broomfield, Colorado, United States.
• Biotrillion
• Uses AI to: Analyze data from nontraditional sensors such as smartphones, wearables, internet of things devices, and virtual
assistants to measure disease development and response to drugs. Allows researchers to: Leverage data from nontraditional
sensors for digitally enabled clinical trials. Founded: 2017. Headquarters: San Francisco, California, United States.
• Biotx.ai
• Uses AI to: Reliably find complex patterns in high-dimensionality biomedical data. Allows researchers to: Predict disease
status, stratify patients, and provide decision support in drug development and precision medicine. Founded:
2017. Headquarters: Berlin, Berlin, Germany.
• Evoke Neuroscience
• Uses AI to: Identify unique neural signatures of Alzheimer’s disease in electroencephalography data. Allows researchers to:
Monitor response to Alzheimer's disease treatments, including in clinical trials. Founded: 2009. Headquarters: New York, New
York, United States.
• Glympse Bio
• Uses AI to: Predict the stage and progression of disease by analyzing data from synthetic biomarker-based liquid
biopsies. Allows researchers to: Validate drug-target engagement and determine responders and non-responders in clinical
trials. Founded: 2015. Headquarters: Cambridge, Massachusetts, United States.
• HistoIndex
• Uses AI to: Analyze and quantify nonalcoholic steatohepatitis (NASH) features for treatment efficacy. Allows researchers to:
Improve the efficiency and effectiveness of NASH clinical trials. Founded: 2010. Headquarters: Singapore, Central Region,
Singapore.
• Paige
• Uses AI to: Analyze pathology slides with models that incorporate diagnoses by the world's foremost cancer experts. Allows researchers to: Accelerate cancer biomarker
discovery and get new disease insights from decades of pathology data. Founded: 2018. Headquarters: New York, New York, United States.
• Syntekabio
• Uses AI to: Analyze genomic data related to cancer and other diseases. Allows researchers to: Discover biomarkers associated with drug responses. Founded:
2009. Headquarters: Sunnyvale, California, United States.
• Generate data and models
• TARA Biosystems
• Uses AI to: Generate models from data on mature cardiac tissue engineered from induced-pluripotent stem cells. Allows researchers to: Predict the physiological effects of
different drugs for heart conditions. Founded: 2014. Headquarters: New York, New York, United States.
• Repurpose existing drugs
• Acurastem
• Uses AI to: Analyze data from sources including patient stem cells. Allows researchers to: Discover drugs for neurodenerative diseases, including ALS. Founded:
2016. Headquarters: Monrovia, California, United States.
• BioXcel Therapeutics
• Uses AI to: Find applications for existing approved drugs or clinically validated candidates. Allows researchers to: Develop a pipeline of product candidates in immuno-
oncology, neuroscience, and rare diseases. Founded: 2017. Headquarters: Branford, Connecticut, United States.
• Biovista
• Uses AI to: Analyze data to find non-obvious, mechanism-of-action based associations between compounds, molecular targets, and diseases. Allows researchers to:
Reposition late preclinical stage drugs in multiple sclerosis, mitochondrial diseases, oncology, epilepsy and chronic fatigue syndrome / myalgic encephalopathy. Founded:
2005. Headquarters: Charlottesville, Virginia, United States.
• Healx
• Uses AI to: Match existing drugs with rare diseases. Allows researchers to: Repurpose existing drugs to accelerate treatment of rare diseases. Founded:
2014. Headquarters: Cambridge, Cambridgeshire, United Kingdom.
• Lantern Pharma
• Uses AI to: Analyze genetic signals and molecular markers for patient response to drugs. Allows researchers to: Find clinical uses for validated cancer treatments whose
development has been discontinued. Founded: 2013. Headquarters: Dallas, Texas, United States.
• Pharnext
• Uses AI to: Screen and reposition known drugs in unrelated indications at new, lower doses. Allows researchers to: Identify synergistic combinations of repositioned
drugs for diseases with high unmet medical needs. Founded: 2007. Headquarters: Issy-les-moulineaux, Ile-de-France, France.
• Qrativ
• Uses AI to: Synthesize knowledge from multiple biomedical sources (using nference technology). Allows researchers to: Discover potential rare disease indications and
subsets of patients who may respond favorably to an existing drug. Founded: 2017. Headquarters: Cambridge, Massachusetts, United States.
• Recursion Pharmaceuticals
• Uses AI to: Conduct experimental biology at scale by testing thousands of compounds on hundreds of cellular disease models in parallel. Allows researchers to: Rapidly
identify new indications for many known drugs and shelved assets. Founded: 2013. Headquarters: Salt Lake City, Utah, United States.
• Generate novel drug candidates
• A2A Pharmaceuticals
• Uses AI to: Iterate small molecules to find candidates with optimal properties for a target. Allows researchers to: Design novel treatments for diseases including cancer,
bacterial infection, and muscular dystrophy. Founded: 2016. Headquarters: New York, New York, United States.
• AI Therapeutics
• Uses AI to: Analyze data from next-gen sequencing, genome editing, chemical genomics, and combinational drug screening to find the most appropriate patients to treat
with novel therapeutics. Allows researchers to: Develop precision therapeutics for cancer and rare diseases. Founded: 2013. Headquarters: Guilford, Connecticut, United
States.
• Alphanosos
• Uses AI to: Predict synergistic plant mixes. Allows researchers to: Develop plant-based compounds that counteract bacterial infection and restore microbiota
equilibrium. Founded: 2014. Headquarters: Goulier, Midi-Pyrenees, France.
• Antiverse
• Uses AI to: Predict antibody-antigen binding. Allows researchers to: Generate antibody drug candidates in one day. Founded: 2017. Headquarters: Cardiff, Cardiff, United
Kingdom.
• Arbor Biotechnologies
• Uses AI to: Curate and mine gene variants. Allows researchers to: Accelerate discovery of proteins for improving human health. Founded: 2016. Headquarters:
Cambridge, Massachusetts, United States.
• Ares Genetics
• Uses AI to: Identify, prioritize, and validate genetic markers of antibiotic resistance. Allows researchers to: Accelerate development of novel antibiotics and combination
therapies based on rational drug design and companion diagnostics. Founded: 2017. Headquarters: Vienna, Wien, Austria.
• Arzeda
• Uses AI to: Find correlations and patterns that can be used for protein design. Allows researchers to: Design proteins "never before seen in
nature." Founded: 2008. Headquarters: Seattle, Washington, United States.
• Atomwise
• Uses AI to: Predict drug candidates by leveraging a convolutional neural network trained on a huge amount of organic chemistry data. Allows
researchers to: Generate novel drug candidates faster (with a number of candidates already in development with partners). Founded:
2012. Headquarters: San Francisco, California, United States.
• Auransa
• Uses AI to: Generate insights from molecular data for a deep understanding of disease biology and patient subtypes. Allows researchers to: Discover
compounds designed to most effectively address significant unmet medical needs for clinically meaningful disease subtypes. Founded:
2014. Headquarters: Palo Alto, California, United States.
• BenevolentAI
• Uses AI to: Ingest scientific research data sets, then form and qualify hypotheses and generate novel insights. Allows researchers to: Identify novel
drug candidates (via life science-focused subsidiary BenevolentBio). Founded: 2013. Headquarters: London, England, United Kingdom.
• Berg
• Uses AI to: Analyze data from patient samples in both healthy and diseased states to generate novel biomarkers and therapeutic targets. Allows
researchers to: Generate therapeutic targets from biological data in an unbiased way, and implement personalized medicine at scale. Founded:
2006. Headquarters: Framingham, Massachusetts, United States.
• BioAge Labs
• Uses AI to: Analyze omics data related to aging. Allows researchers to: Develop biomarkers and drugs that impact human aging. Founded:
2015. Headquarters: Richmond, California, United States.
• BlackThorn Therapeutics
• Uses AI to: Generate novel insights into neurobehavioral health from prorietary data sources including brain imaging and functional assessment
tools. Allows researchers to: Develop new drugs targeting receptors in dysregulated brain circuits. Founded: 2015. Headquarters: San Francisco,
California, United States.
• CaroCure
• Uses AI to: Predict toxicity to weed out toxic compounds and increase the efficacy of computational drug discovery. Allows researchers to: Discover new drugs for oncology,
immuno-oncology, cardiology, and infectious disease. Founded: 2017. Headquarters: Hyderabad, Andhra Pradesh, India.
• Cellarity
• Uses AI to: Uncover and exploit unappreciated molecular and cellular behaviors by analyzing digital representations of biology and drug actions. Allows researchers to:
Develop medicines by iteratively testing and curating new approaches to manipulate molecular and cellular behaviors. Founded: 2019. Headquarters: Cambridge,
Massachusetts, United States.
• Celsius Therapeutics
• Uses AI to: Analyze data from single-cell RNA sequencing. Allows researchers to: Understand genes in specific cells that trigger disease, then develop precision treatments
for those diseases along with companion biomarker-based diagnostic tools. Founded: 2018. Headquarters: Cambridge, Massachusetts, United States.
• ChemPass
• Uses AI to: Generate molecular structures based on user-defined criteria. Allows researchers to: Design novel small organic molecules and scaffolds. Founded:
2016. Headquarters: Budapest, Budapest, Hungary.
• Cloud Pharmaceuticals
• Uses AI to: Search a virtual chemical space, predict binding affinity and allow filtering for drug-like properties, safety, and synthesizability. Allows researchers to: Speed drug
development with a higher success rate and better targeting of hard-to-drug indications. Founded: 2014. Headquarters: Durham, North Carolina, United States.
• Clover Therapeutics
• Uses AI to: Analyze clinical and genomic data from consenting participants who are members of insurer Clover Health. Allows researchers to: Discover strategies or
interventions that can form the basis of new therapies for pharma partners. Founded: 2016. Headquarters: Jersey City, New Jersey, United States.
• Collaborations Pharma
• Uses AI to: Filter and score compounds prior to testing. Allows researchers to: Develop innovative therapeutics for multiple rare and infectious diseases. Founded:
2015. Headquarters: Raleigh, North Carolina, United States.
• Cotinga Pharmaceuticals
• Uses AI to: Predict biological activity from molecular structures. Allows researchers to: Intervene in pathways that cancer cells use to escape cell death. Founded:
1999. Headquarters: London, England, United Kingdom.
• Datavant
• Uses AI to: Integrate clinical trial data with real-world evidence and public datasets to eliminate silos of health information. Allows researchers to: Reduce the cost of drug
development, and improve the time-to-market and likelihood of success for new drugs. Founded: 2017. Headquarters: San Francisco, California, United States.
• Deep Genomics
• Uses AI to: Search 69 billion molecules with the goal of generating a library of 1,000 compounds to manipulate cell biology. Allows researchers to: Unlock new classes of antisense oligonucleotide therapies. Founded: 2014. Headquarters: Toronto,
Ontario, Canada.
• Dyno Therapeutics
• Uses AI to: Predict the function of sequences for adeno-associated virus capsids, which are used as vectors for gene therapy. Allows researchers to: Improve and expand the use of gene therapy by programming capsids with improved functions like
precision delivery and immune system evasion. Founded: 2018. Headquarters: Cambridge, Massachusetts, United States.
• Engine Biosciences
• Uses AI to: Uncover gene interactions and biological networks underlying diseases, and test therapies that target them. Allows researchers to: Make analyses and predictions for precision medicine applications. Founded: 2014. Headquarters: San
Francisco, California, United States.
• Envisagenics
• Uses AI to: Analyze RNA data from patients to identify new biomarkers and drug targets. Allows researchers to: Accelerate discovery of RNA therapeutics. Founded: 2014. Headquarters: New York, New York, United States.
• Erasca
• Uses AI to: Elucidate novel tumor biology and innovative strategies that shut down key cancer pathways. Allows researchers to: Focus on the most promising strategies to tackle essential oncogenes, accelerating development of oncology drug
candidates. Founded: 2018. Headquarters: San Diego, California, United States.
• Evaxion Biotech
• Uses AI to: Identify suitable targets for vaccines and antibodies in complex immunological data. Allows researchers to: Program the immune system to fight off diseases from cancers to hard-to-treat infections. Founded: 2008. Headquarters:
Copenhagen, Hovedstaden, Denmark.
• Exscientia
• Uses AI to: Learn best-practices from drug discovery data and experienced drug hunters. Allows researchers to: Generate drug candidates in roughly one-quarter the time of traditional approaches. Founded: 2012. Headquarters: Oxford,
Oxfordshire, United Kingdom.
• GTN
• Uses AI to: Simulate, filter, and search for molecules with "Generative Tensorial Networks." Allows researchers to: Discover molecules otherwise hidden from view. Founded: 2017. Headquarters: London, England, United Kingdom.
• Gatehouse Bio
• Uses AI to: Illuminate molecular pathways of disease through deep analysis of small RNA. Allows researchers to: Identify therapeutic targets and develop companion diagnostics. Founded: 2016. Headquarters: Waltham, Massachusetts, United
States.
• Genesis Therapeutics
• Uses AI to: Accurately predict ADMET properties. Allows researchers to: Use neural networks and biophysical simulation to generate and optimize molecules. Founded: 2019. Headquarters: South San Francisco, California, United States.
• Globavir
• Uses AI to: Generate novel insights and predictions from biological data, chemical data, and curated databases of approved drugs. Allows researchers to: Leverage existing data to develop therapies (currently focused on infectious disease
diagnostics and treatments). Founded: 2011. Headquarters: Los Altos, California, United States.
• Gritstone Oncology
• Uses AI to: Predict immune targets for cancer immunotherapy using a model trained on extensive human tumor data. Allows researchers to: Develop new approaches to drive potent, tumor-specific
immune responses that provide therapeutic benefit to a large number of cancer patients. Founded: 2015. Headquarters: Emeryville, California, United States.
• Iktos
• Uses AI to: Design novel compounds that optimize for specific objectives. Allows researchers to: Improve the success rate of in silico to in vitro translation. Founded: 2016. Headquarters: Paris, Ile-de-
France, France.
• Insilico Medicine
• Uses AI to: Predict pharmacological properties of drugs and supplements, and identify novel biomarkers. Allows researchers to: Generate novel therapeutic candidates, with a focus on aging and age-
related diseases. Founded: 2014. Headquarters: Rockville, Maryland, United States.
• Insitro
• Uses AI to: Generate models from large, high-quality datasets. Allows researchers to: Address key problems in the drug discovery and development process. (Not clear on their positioning at this point,
but recent partnerships suggest they aim to generate drug candidates.) Founded: 2018. Headquarters: South San Francisco, California, United States.
• LabGenius
• Uses AI to: Provide the brains for EVA, a smart robotic platform that can design, conduct, and learn from its own experiments. Allows researchers to: Develop next-generation protein therapeutics,
including by optimizing multiple drug properties simultaneously. Founded: 2012. Headquarters: London, England, United Kingdom.
• Lodo Therapeutics
• Uses AI to: Find undiscovered molecules encoded in environmental microbial DNA. Allows researchers to: Address undruggable targets with structurally diverse molecules that have drug-like
properties. Founded: 2016. Headquarters: New York, New York, United States.
• Menten Biotechnology Labs
• Uses AI to: Optimize activity, specificity, and stability of peptides, proteins, and enzymes. Allows researchers to: Create novel peptide therapeutics, proteins for drug delivery, and enzymes. Founded:
2018. Headquarters: Toronto, Ontario, Canada.
• Micar Innovation
• Uses AI to: Shorten discovery and screening, lead optimization, and ADMET studies. Allows researchers to: Create "build-to-buy" partnerships, forming startups around new drug discovery programs that
pharmaceutical companies can then acquire if successful. Founded: 2016. Headquarters: Sofia, Grad Sofiya, Bulgaria.
• Mind the Byte
• Uses AI to: Analyze data in a SaaS-based bioinformatics platform for computational drug discovery. Allows researchers to: Leverage big data and machine learning for every stage of the drug discovery
process, from target-identification to post-marketing activities, with no need for their own hardware infrastructure. Founded: 2011. Headquarters: Barcelona, Catalonia, Spain.
• Nanna Therapeutics
• Uses AI to: Analyze data from its "Totally Integrated Medicines Engine" platform, which also leverages microfluidics and nanofabrication. Allows researchers to: Create drugs to treat age-related diseases
and improve longevity, with a strong focus on mitochondria. Founded: 2012. Headquarters: Cambridge, Cambridgeshire, United Kingdom.
• Neon Therapeutics
• Uses AI to: Identify, predict, and select the most therapeutically relevant neoantigen (newly formed antigen not previously recognized by the immune system) targets associated with a patient’s
tumor. Allows researchers to: Develop novel neoantigen-based therapeutics for cancer. Founded: 2015. Headquarters: Cambridge, Massachusetts, United States.
• NuMedii
• Uses AI to: Discover connections between drugs and diseases at a systems level by analyzing hundreds of millions of raw human, biological, pharmacological, and clinical data points. Allows researchers to:
Find drug candidates and biomarkers predictive of efficacy for diseases. Founded: 2008. Headquarters: Menlo Park, California, United States.
• Nuritas
• Uses AI to: Predict the therapeutic potential of food-derived bioactive peptides. Allows researchers to: Cost-effectively develop highly targeted treatments for specific diseases from natural food
sources. Founded: 2014. Headquarters: Dublin, Dublin, Ireland.
• Pharos iBT
• Uses AI to: Predict properties of compounds and enable low-cost and efficient drug development. Allows researchers to: Develop new drugs for orphan and rare diseases. Founded: 2016. Headquarters:
Anyang, Kyonggi-do, South Korea.
• ProteinQure
• Uses AI to: Design protein drugs through reinforcement learning. Allows researchers to: Target a wider array of binding sites, target diseases with high specificity, and create compounds that are easier to
synthesize and test. Founded: 2017. Headquarters: Toronto, Ontario, Canada.
• Quantitative Medicine
• Uses AI to: Analyze many drug discovery factors simultaneously, such as effects, side effects, and toxicity. Allows researchers to: Solve complex drug discovery optimization problems. Founded:
2012. Headquarters: Vero Beach, Florida, United States.
• Qulab
• Uses AI to: Perform de novo molecular design and molecular simulation. Allows researchers to: Automate design of small molecule drugs. Founded: 2017. Headquarters: Los Angeles, California, United
States.
• Relay Therapeutics
• Uses AI to: Understand protein motion—how protein shape influences health and disease. Allows researchers to: Design compounds that can target and stabilize proteins in a normal shape. Founded:
2016. Headquarters: Cambridge, Massachusetts, United States.
• Resonant Therapeutics
• Uses AI to: Assess and prioritize a library of drug candidates derived from analyzing tumor microenvironments. Allows researchers to: Simultaneously discover novel targets and functional antibodies for
cancer. Founded: 2014. Headquarters: Santa Barbara, California, United States.
• SEngine Precision Medicine
• Uses AI to: Find novel small molecules that can bind and inhibit targets that are specific to cancer cells. Allows researchers to: Develop targeted therapies for the three most common cancer-causing genes:
MYC, TP53, and KRAS. Founded: 2015. Headquarters: Seattle, Washington, United States.
• Sirenas
• Uses AI to: Analyze metabolomic and bioassay datasets to uncover insights into human health and disease, as well as potential new chemical scaffolds. Allows researchers to: Find new therapeutic targets
and biomarkers for diseases and aging, as well as novel compounds that can provide the foundation for new drugs. Founded: 2011. Headquarters: San Diego, California, United States.
• Spring Discovery
• Uses AI to: Accelerate experimentation for discovering therapies for aging and related diseases. Allows researchers to: Uncover new therapies for diseases of aging by targeting the biological processes
of aging itself. Founded: 2017. Headquarters: Palo Alto, California, United States.
• Standigm
• Uses AI to: Analyze biomedical data to predict how drug compounds would interact with people in the real world. Allows researchers to: Generate novel compounds satisfying desired properties and
discover hidden indications and pathways. Founded: 2015. Headquarters: Seoul, Seoul-t'ukpyolsi, South Korea.
• Systems Oncology
• Uses AI to: Aggregate and mine disparate biomedical datasets to reveal novel vulnerabilities in cancer. Allows researchers to: Exploit novel cancer vulnerabilities with innovative treatments. Founded:
2016. Headquarters: Scottsdale, Arizona, United States.
• TwoXAR
• Uses AI to: Screen compound libraries for efficacy against a disease, identify new drug candidates from a public library, and identify biologic targets. Allows researchers to: Speed and reduce costs for
drug discovery. Founded: 2014. Headquarters: Mountain View, California, United States.
• Unnatural Products
• Uses AI to: Analyze data on prospective macrocycle therapies (which combine benefits of large biomolecules, such as high selectivity, with small molecules, such as ease of administration). Allows
researchers to: Develop drugs for currently undruggable targets. Founded: 2017. Headquarters: Santa Cruz, California, United States.
• Verge Genomics
• Uses AI to: Map hundreds of genes that cause a disease, then find drugs that target all at once. Allows researchers to: Find cures for complex diseases—especialy brain diseases—that involve a network
of genes. Founded: 2015. Headquarters: San Francisco, California, United States.
• Vyasa
• Uses AI to: Analyze concepts in unstructured documents and perform advanced chemistry analysis. Allows researchers to: Mine data in electronic laboratory notebooks, find unexpected relationships
between mechanisms of action and disease, and generate novel compounds optimized for specific variables. Founded: 2016. Headquarters: Newburyport, Massachusetts, United States.
• X-37
• Uses AI to: Perform structure-based drug design and discovery (using AtomNet from Atomwise). Allows researchers to: Develop drugs for hard-to-target proteins with high therapeutic value. Founded:
2019. Headquarters: San Francisco, California, United States.
• Xbiome
• Uses AI to: Analyze the gut microbiome. Allows researchers to: Modulate the microbiome to develop novel drugs. Founded: 2017. Headquarters: Shenzhen, Guangdong, China.
• e-Therapeutics
• Uses AI to: Analyze complex networks of molecular interactions in cells. Allows researchers to: Acquire or in-license drug candidates. Founded: 2003. Headquarters: Hanborough, Oxfordshire, United
Kingdom.
• uBiome
• Uses AI to: Analyze data from the world's largest database of microbiomes in the world. Allows researchers to: Develop new treatments inspired by novel insights into human-microbe
relationships. Founded: 2012. Headquarters: San Francisco, California, United States.
• Accutar
• Uses AI to: Learn physical and chemical nature of biological systems from protein crystal structure data. Allows researchers to: Predict drug pocket side chain conformation, drug docking, and chemical
compound characteristics. Founded: 2015. Headquarters: Shanghai, Shanghai, China.
• Acellera
• Uses AI to: Predict protein-ligand binding. Allows researchers to: Select better drug candidates, exclude toxic or reactive molecules, and improve ADMET profiles. Founded: 2006. Headquarters: London,
England, United Kingdom.
• InVivo AI
• Uses AI to: Integrate structural, target, and pathway-based descriptors to generate toxicological profiles of small molecule drugs in silico. Allows researchers to: Reduce the time and cost of preclinical
decision-making while increasing the likelihood of success for compounds selected for clinical trials. Founded: 2018. Headquarters: Montréal, Quebec, Canada.
• Interprotein
• Uses AI to: Predict the impact of ligands on protein-protein interactions. Allows researchers to: Increase the success rate of small molecule drugs targeting protein-protein interactions. Founded:
2001. Headquarters: Osaka, Osaka, Japan.
• NetraMark
• Uses AI to: Understand how patient subpopulations respond to treatments. Allows researchers to: Match drugs to patients, with the potential to extract information from failing or failed clinical trials and
revive the prospects for at-risk drugs. Founded: 2015. Headquarters: Toronto, Ontario, Canada.
• Reverie Labs
• Uses AI to: Predict potency and pharmacokinetic properties of small molecules, and conceive new molecules to optimize for them. Allows researchers to: Accelerate preclinical drug development by
generating and improving leads. Founded: 2017. Headquarters: Boston, Massachusetts, United States.
• Synsight
• Uses AI to: Analyze data from molecular modeling and high-content screening. Allows researchers to: Solve complex systems like protein-protein interactions and undersand modes of action in biological
sytems. Founded: 2013. Headquarters: Évry, Ile-de-France, France.
• Turbine
• Uses AI to: Simulate experiments. Allows researchers to: Gain insights into how a drug works from the preclinical phase through phases I, II, and III. Founded: 2015. Headquarters: Budapest, Budapest,
Hungary.
• VERISIM Life
• Uses AI to: Predict pharmacology of potential new drug candidates through pharmacokinetic and pharmacodynamic modeling and simulation. Allows researchers to: Narrow the number of drug
candidates that offer anticipated effects for specified diseases. Founded: 2017. Headquarters: San Francisco, California, United States.
• XtalPi
• Uses AI to: Predict the crystalized form a drug will take. Allows researchers to: Understand the potential safety, stability, and efficacy of drug candidates. Founded: 2014. Headquarters: Cambridge,
Massachusetts, United States.
• Cyclica
• Uses AI to: Consider the polypharmacology, pharmacokinetics, and structural pharmacogenomics of molecules. Allows researchers to: Explain mechanisms of action, and de novo design or optimize multi-targeted drug-like molecules with preferred
pharmacokinetic properties while minimizing off-target interactions. Founded: 2013. Headquarters: Toronto, Ontario, Canada.
• DeepMatter
• Uses AI to: Analyze data on successful and unsuccessful chemical reactions. Allows researchers to: Discover new molecules more efficiently, with better reproducibility. Founded: 2015. Headquarters: Glasgow, Glasgow City, United Kingdom.
• Fetch Biosciences
• Uses AI to: Understand structure-to-function relationships underpinning existing biomolecules. Allows researchers to: Engineer novel biomolecules with optimized functions. Founded: 2019. Headquarters: Toronto, Ontario, Canada.
• MAbSilico
• Uses AI to: Predict antibody binding, similarity, and cross-reactivity. Allows researchers to: Characterize, find substitutes for, and identify potential off-target effects of a specified antibody. Founded: 2017. Headquarters: Nouzilly, Centre, France.
• Molecule.one
• Uses AI to: Predict whether a particular chemical reaction will work. Allows researchers to: Input a chemical structure and receive reactions and synthesis pathways for it. Founded: 2016. Headquarters: Warsaw, Mazowieckie, Poland.
• Molomics
• Uses AI to: Design structurally new small molecules for validated biological targets. Allows researchers to: Collaborate with each other (using what they call "Human Collective Intelligence") and AI to jointly develop safer and more effective
therapeutics. Founded: 2015. Headquarters: Barcelona, Catalonia, Spain.
• Numerate
• Uses AI to: Analyze public and private data, with a claim to work with less data, noisier data, and more biased data than alternative approaches. Allows researchers to: Predict how a potential drug will behave in the lab and the body, with a focus on
neurodegeneration, cardiovascular disease, and oncology. Founded: 2007. Headquarters: San Bruno, California, United States.
• Pending.ai
• Uses AI to: Learn chemistry from a database of more than 130 million compounds, 20 million reactions, and 146,000 proteins. Allows researchers to: Generate novel molecules with neural networks, do structure-based drug design, plan chemical
synthesis, and conduct high-throughput chemistry. Founded: 2018. Headquarters: Wollongong, New South Wales, Australia.
• Pepticom
• Uses AI to: Design peptides based on a target's solved crystal structure. Allows researchers to: Speed development of peptide drugs, which have high selectivity and low toxicity. Founded: 2011. Headquarters: Jerusalem, Yerushalayim, Israel.
• Peptone
• Uses AI to: Predict protein features and characteristics. Allows researchers to: Reduce complexity in protein design, detect production and characterisation issues, and discover novel protein features. Founded: 2018. Headquarters: London, England,
United Kingdom.
• Remedium
• Uses AI to: Identify minimum functional units of protein drug candidates by building specific predictive models from customized data sets. Allows researchers to: Reduce dependence on mass screenings, both virtual and chemical, through rapid
selection of small molecule agonists, antagonists, or functional mimics of protein drug candidates. Founded: 2017. Headquarters: Montréal, Quebec, Canada.
• Schrödinger
• Uses AI to: Ideate, optimize, and analyze drug candidates. Allows researchers to: Evaluate chemical compounds in silico ahead of synthesis and assay. Founded: 1990. Headquarters: New York, New York, United States.
• BenchSci
• Uses AI to: Decode open- and closed-access data on reagents such as antibodies and present published figures with actionable insights. Allows
researchers to: Reduce time, money, and uncertainty in planning experiments. Founded: 2015. Headquarters: Toronto, Ontario, Canada.
• Desktop Genetics
• Uses AI to: Determine biological variables influencing CRISPR guide design. Allows researchers to: Improve activity and reduce experimental bias in
the selection of guides for CRISPR libraries. Founded: 2012. Headquarters: London, England, United Kingdom.
• Run preclinical experiments
• Arctoris
• Uses AI to: Generate novel insights from high-quality cancer research data gathered by a robotic system. Allows researchers to: Configure experiments
remotely and have them executed in a fully automated cloud laboratory. Founded: 2016. Headquarters: Oxford, Oxfordshire, United Kingdom.
• Berkeley Lights
• Uses AI to: Automate selection, manipulation, and analysis of cells. Allows researchers to: Expedite development of cell lines and automate
manufacturing of cellular therapeutics. Founded: 2011. Headquarters: Emeryville, California, United States.
• Emerald Cloud Lab
• Uses AI to: Conduct experiments in an automated lab exactly as specified. Allows researchers to: Run experiments in a central lab from anywhere in
the world. Founded: 2010. Headquarters: South San Francisco, California, United States.
• Strateos
• Uses AI to: Automate sample analysis with a robotic cloud laboratory. Allows researchers to: Generate needed data quickly and reliably with an
outsourced, on-demand, automated lab. Founded: 2012. Headquarters: Menlo Park, California, United States.
• Synthace
• Uses AI to: Build models to understand complex biological systems within Antha, its language and software platform for biology experiments. Allows
researchers to: Optimize, reproduce, automate, and scale experiment workflows. Founded: 2011. Headquarters: London, England, United Kingdom.
•
• BullFrog AI
• Uses AI to: Predict which patients will respond to therapies in development. Allows researchers to: Advance therapies that fail phase 3 studies. Founded:
2017. Headquarters: Boyds, Maryland, United States.
• GNS Healthcare
• Uses AI to: Transform diverse streams of biomedical and healthcare data into computer models representative of individual patients. Allows researchers to: Deliver
personalized medicine at scale, by revealing optimal health interventions for individual patients. Founded: 2000. Headquarters: Cambridge, Massachusetts, United States.
• Intelligencia
• Uses AI to: Estimate the risk of clinical trials, and interpret the multitude of factors that contribute to that risk. Allows researchers to: De-risk drug development at the clinical
trial stage. Founded: 2017. Headquarters: New York, New York, United States.
• Keen Eye Technologies
• Uses AI to: Empower pathologists to access new insights in biomedical data. Allows researchers to: Increase diagnostics sensitivity and find predictive signatures of drug
response. Founded: 2015. Headquarters: Paris, Ile-de-France, France.
• Nucleai
• Uses AI to: Analyze features in pathology images more efficiently and find hidden patterns within. Allows researchers to: Match patients to the right drugs based on novel
pathology-based insights into which drugs might be most effective for their disease. Founded: 2017. Headquarters: Tel Aviv, Tel Aviv, Israel.
• PathAI
• Uses AI to: Improve pathology analysis. Allows researchers to: Identify patients that would benefit from novel therapies. Founded: 2016. Headquarters: Boston,
Massachusetts, United States.
• Perceiv Research
• Uses AI to: Identify subpopulations of interest from heterogeneous data for complex diseases. Allows researchers to: Improve treatment success with appropriate subject
selection for clinical trials. Founded: 2018. Headquarters: Montréal, Quebec, Canada.
• Reveal Biosciences
• Uses AI to: Automate histopathology. Allows researchers to: Stratify patients for clinical trials. Founded: 2012. Headquarters: San Diego, California, United States.
• Trials.ai
• Uses AI to: Optimize clinical trial study design. Allows researchers to: Make it easier for patients to enroll and engage in clinical trials, eliminate unnecessary clinical
operations burdens, and gain real-time insight into study health. Founded: 2016. Headquarters: San Diego, California, United States.
• Antidote.me
• Uses AI to: Make sense of unorganized and unstructured data about clinical trials. Allows researchers to: Enrol more patients in appropriate
trials. Founded: 2010. Headquarters: London, England, United Kingdom.
• Clinithink
• Uses AI to: Transform unstructured clinical notes into rich structured data. Allows researchers to: Increase the speed of screening eligible subjects
for clinical trials against trial-specific inclusion and exclusion criteria. Founded: 2009. Headquarters: London, England, United Kingdom.
• Deep 6 AI
• Uses AI to: Analyze medical records to find patients for clinical trials. Allows researchers to: Accelerate patient recruitment to complete clinical trials
faster. Founded: 2015. Headquarters: Pasadena, California, United States.
• Deep Lens
• Uses AI to: Classify digital pathology images. Allows researchers to: Identify and triage patients for clinical trials at the time of diagnosis. Founded:
2017. Headquarters: Columbus, Ohio, United States.
• Inato
• Uses AI to: Screen clinical trial sites and investigators at scale. Allows researchers to: Select appropriate sites to improve patient recruitment rates
and accelerate clinical trials. Founded: 2016. Headquarters: Paris, Ile-de-France, France.
• Massive Bio
• Uses AI to: Match cancer patients with active clinical trials. Allows researchers to: Facilitate oncology clinical trial enrollment. Founded:
2014. Headquarters: New York, New York, United States.
• Mendel.ai
• Uses AI to: Automate matching cancer patients to clinical trials through personal medical history and genetic analysis. Allows researchers to:
Expedite clinical trial enrollment for cancer treatments. Founded: 2016. Headquarters: San Jose, California, United States.
• Notable
• Uses AI to: Automate evaluating the impact of drug combinations on cancer cells. Allows researchers to: Prioritize drugs for patients with cancer,
including to ensure they're enrolled in the most appropriate clinical trials. Founded: 2014. Headquarters: Foster City, California, United States.
• Tempus
• Uses AI to: Analyze clinical and molecular data at scale. Allows researchers to: Identify clinical trial matches for patients that fit their molecular and
phenotypic profile. Founded: 2015. Headquarters: Chicago, Illinois, United States.
• AiCure
• Uses AI to: Visually confirm medication ingestion via smartphone. Allows researchers to: Improve medication adherence in clinical trials. Founded: 2009. Headquarters: New
York, New York, United States.
• Athelas
• Uses AI to: Analyze cancer biomarkers in 60 seconds from a drop of blood using an at-home device slightly bigger than an Amazon Echo. Allows researchers to: Optimize
oncology drug development with a biomarker monitoring platform and millions of patient datapoints. Founded: 2016. Headquarters: Mountain View, California, United
States.
• Brite Health
• Uses AI to: Analyze structured and unstructured clinical trial participant data. Allows researchers to: Reduce clinical trial dropout rates through personalized
communication. Founded: 2015. Headquarters: Palo Alto, California, United States.
• Imagia
• Uses AI to: Analyze radiological images to produce clinically actionable information. Allows researchers to: Predict a patient's disease progression and treatment response,
for clinical trial stratification and companion diagnostics. Founded: 2015. Headquarters: Montréal, Quebec, Canada.
• Medable
• Uses AI to: Model and predict trial success and identify and prioritize sites. Allows researchers to: Run digital trials through an end-to-end cloud platform that allows
patients, sites, CROs, and sponsors to function as team. Founded: 2012. Headquarters: Palo Alto, California, United States.
• Unlearn.ai
• Uses AI to: Simulate and generate digital control subjects that are statistically indistinguishable from actual controls. Allows researchers to: Populate control arms in clinical
trials, enabling rigorous clinical evidence with fewer subjects. Founded: 2017. Headquarters: San Francisco, California, United States.
• WinterLight Labs
• Uses AI to: Assess and monitor cognitive health by analyzing a short speech sample. Allows researchers to: Identify patients, screen patients, and evaluate response to
therapy for clinical trials of mental health treatments. Founded: 2015. Headquarters: Toronto, Ontario, Canada.
• nQ Medical
• Uses AI to: Find hidden health signals in data from personal devices such as laptops and smartphones. Allows researchers to: Optimize clinical trials for neurological
diseases, including through better, faster identification of ideal study participants, less in-clinic observation, improved compliance, and earlier measure of drug
impact. Founded: 2016. Headquarters: Cambridge, Massachusetts, United States.
•
• Deep Intelligent Pharma
• Uses AI to: Make the medical writing process more efficient and creative (amongst
other things). Allows researchers to: Save time producing documents, including
regulatory documents, while ensuring content quality and data accuracy. Founded:
2017. Headquarters: Wangjing, Beijing, China.
• sciNote
• Uses AI to: Write a draft scientific manuscript based on provided data. Allows
researchers to: Get a "head start" when writing a scientific manuscript to submit for
publishing. Founded: 2014. Headquarters: Middleton, Wisconsin, United States.
• Analyze real world evidence
• Aetion
• Uses AI to: Analyze medical and pharmacy claims data. Allows researchers to:
Understand which treatments work best for which patients at what times. Founded:
2013. Headquarters: New York, New York, United States.
• Concerto HealthAI
• Uses AI to: Extract insights from data on oncology patients' experience with
drugs. Allows researchers to: Accelerate the generation of evidence for new
therapeutic approaches. Founded: 2017. Headquarters: Boston, Massachusetts,
United States.
Machine Learning in Health Insurance
• NLP for health care finds meaning in medical records
OPtum
Clinical documentation provides the fuel by which health care organizations drive much of their operations. Patient interactions with providers are often brief, and when they leave a provider’s care, the only
lasting evidence of the patient encounter resides in the medical record documentation. NLP can automatically review electronic patient records for relevant data to help ensure that clinical documentation is
complete, so that the NLP-assigned codes are accurate. NLP engines that have been developed specifically for health care — we’ll call them clinically intelligent NLP — are focused on clinical concepts and on using
artificial intelligence to correlate interrelated medical documentation. This automation can pinpoint diagnoses, along with related conditions and procedures, required to accurately code the care provided. The
information is also necessary for appropriate reimbursement, quality initiatives and other critical health care operations. But understanding what was documented in a record is only part of what makes NLP so
valuable. The most sophisticated clinically intelligent NLP technologies can identify documentation gaps by understanding not only what is in the record, but what is missing. As a result, clinicians can receive
valuable feedback to improve documentation at the point of care. The power to review every record and identify every case with potential documentation deficiencies and/or quality events is an unprecedented
capability of clinically intelligent NLP. This “automated case-finding” helps hospitals and health systems pinpoint and address more documentation issues — at the point of care — enabling more complete and
accurate NLP coding, reimbursement and reporting.

• Clinically intelligent NLP relieves reimbursement challenges

Complete, timely and accurate documentation is essential for accurate reimbursement. Documentation gaps can lead to inaccurate coding that may diminish revenue and slow the reimbursement process or stop
it altogether. Chasing down deficiencies in documentation can impact cash flow. Claim denials resulting from inaccurate or incomplete documentation are costly to rework. Documentation deficiencies and
incomplete coding pose an even greater threat to revenue today than they did a few years ago. New risk-based models have introduced intricate rules that impact documentation, coding and reimbursement. As
payment models shift, reimbursement is also tied to quality events that must be accurately reported based on what is reflected in clinical documentation. In addition to revenue, quality reporting to the Centers
for Medicare and Medicaid Services (CMS) is public information, and the related ratings and penalties can shape community perception of the health care provider. Intelligent automation that identifies
documentation gaps and enables documentation improvement at the point of care supports accurate quality reporting, as well as accurate coding and efficient downstream

• Clinically intelligent NLP reduces resource constraints

In the ICD-10 era, coding is more complex, and documentation specificity has greater impact. Common practice for documentation improvement has been to focus only on certain payers or care categories. There
is simply too much data to manually review every case. Hiring staff to review all patient records to find potential deficiencies — while patients are still hospitalized — would be prohibitively inefficient and
expensive. Most providers are unable to accomplish 100 percent manual record review, so documentation deficiencies can go unnoticed while staff spends time reviewing only a small subset of records, many
with no issues to address. Clinically intelligent NLP can review medical records more quickly and thoroughly than traditional, manual programs to identify what may be missing and to assign appropriate codes.
What does this mean for the people whose job it is to review documentation and assign codes? Automation often brings with it fears of job security. But rather than threatening jobs, NLP helps everyone involved
in the revenue cycle by processing enormous amounts of information with a high level of precision to help them work smarter and utilize their talents better. NLP can accomplish the necessary and detailed work
that is challenging to address due to the sheer volume and complexity of health information data.

• Clinically intelligent NLP reveals important documentation issues to clinicians

Clinicians focus on providing patient care. Accurately documenting that care requires time away from their patients, and can seem burdensome. However, generating the revenue that allows physicians to
practice does depend on documentation, creating a natural tension between care providers and those running the business. Clinically intelligent NLP helps ease some of that tension. The technology can find
documentation in need of change and provide the reason physician clarification is needed. With NLP assistance, only the cases that truly need improvement are brought to physicians’ attention, allowing them to
effect change earlier, at the point of care. Due to improved documentation, organizations capture more appropriate revenue with reporting that accurately reflects the care provided and appropriately reflects
quality metrics.
 Aetna
• Aetna has created artificial intelligence (AI) software to settle claims, a solution
that could provide a blueprint for broader automation of complex processes at
the health insurance giant. The software rapidly parses complex healthcare
provider contracts, whose blend of information about medical conditions and
financial data often tax the patience of the trained humans who process them.
• Aetna’s SIU (Special Investigation Unit) is responsible for identifying and
investigating insurance fraud. Its investigators scrutinize the claims and billing
process to uncover the tell-tale signs of overbilling, false coding, and other
shady or wasteful practices. (And the cost is significant – it’s estimated that as
much as 3% of the total US healthcare expenditure is lost to fraudulent or
wasteful practices.) Tracking down fraud means going through reams and reams
of data, encompassing both claims and medical info. SIU previously used a
vendor-designed analytics dashboard to pore through the millions of healthcare
transactions in Aetna’s systems – but Lazarevic notes that the analytics solution
was relatively unsophisticated, and SIU struggled to make good use of it.
 CIGNA
• Ensuring that patients are taking their meds correctly has long been a challenge for
providers, as it can often be the difference between a prescription’s success or failure
when it comes to addressing the targeted condition or disease.
• But while a new AI-driven monitoring system from US health plan Cigna aims to take
big steps toward resolving that challenge, some experts fear that the new technology
could also work against the interest of millions of patients.
• The product, called Health Connect 360, integrates data from a combination of
sources and analytical tools and was originally developed for treatment of chronic
diseases, including diabetes and heart disease, as well as for pain management. The
system aggregates medical, pharmacy, lab and biometric data—such as information
from glucometers, which measure blood-sugar levels—into a dashboard that is
accessible through an online interface.”
• Via that interface, doctors and nurses will be able to constantly keep an eye on
patients' health and step in when they have cause for concern. For example, an alert
may be triggered if patients forget to pick up their prescription or miss an
appointment.
• The tool also combines algorithms “with predictive models to generate
recommendations and ways to best engage a patient, whether through an app or in
person.”
 Humana

• Humana has been using an AI bot known as Cogito Dialog in its

customer service centers to identify poor member experiences in real
time and deliver instant feedback to its staff.
 WellCare
• To improve patient care out in the field, WellCare is turning to a
combination of artificial intelligence and mobile technology.
• The insurer, which serves Medicare and Medicaid patients, is creating one
version of a new AI-powered system for patients and another for
caregivers.
• The company has rolled out an early version of its patient-focused
system—called Care Plan—in three states so far and plans to deploy it to its
full membership by the end of the year. The system works by analyzing
data that members enter into the MyWellCare mobile app, along with
WellCare’s own data, to suggest treatment plans and interventions for
potential health issues it identifies.
• The more data it gathers, the more successful Care Plan will be, Ghanayem
told the publication, noting that WellCare has been encouraging members
to download its mobile app.
 Blue Cross
• Blue Cross NC recently piloted a machine learning model that was able to predict, with
a degree of certainty, when a patient is likely to experience a health event requiring
readmission to a hospital. This example demonstrates how technology can assist
health care professionals in caring for patients and improving their health.
• Anthem Blue Cross will collaborate with Stanford researchers to better understand the
role of AI for increasing price transparency, fostering patient engagement, and helping
members make more informed choices about spending and wellness.
• Price transparency will be first area of focus for the collaboration. Both payers and
providers are finding it challenging to offer meaningful information about out-of-
pocket spending to consumers.
• Many payers are working to complement federal efforts to increase price
transparency on the provider side in an effort to raise consumer satisfaction and retain
market share in a very competitive environment.
• Automating the delivery of pricing information through AI-driven apps or other tools
could improve consumer decision-making and reduce costs across the care continuum.
 Health Care Service Corporation

• The model uses machine learning to drive an enhanced predictive

analytics model that learns from data and identifies patterns to better
detect potential drivers of provider performance. It evaluates claims
by type of care and compares the cost of managing the condition for
each provider to similar treatments by peer providers. HCSC uses the
results from the platforms to build better-performing provider
networks and improve existing networks.
• HCSC's providers have deep information about patient interactions
with members. The information includes all the meetings those
members have and clinical data, such as tests they've undergone and
the results of those tests.
 CVS
• With a connected information system, CVS will be able to keep track
of insurance claims, review clinic visits, and offer relevant prescription
benefits to delight customers.
• A digitally-enabled database system that is powered with connected
devices will also allow CVS to engage with customers on a more
personal level.
• Customers that have not visited a clinic for a certain amount of time
can also be sent an automated reminder, resulting in better care and
a more precise customer healthcare management system.
• While other improvements may include setting up a digital platform
that would ease the process of checking the availability of clinics and
the booking of clinic appointments, Bhathena believes that at the end
of the day, it is about creating connected healthcare services.
 Useful Links
• https://blog.benchsci.com/pharma-companies-using-artificial-
intelligence-in-drug-discovery

• https://www.pharmatutor.org/articles/top-ten-pharmaceutical-
industries-using-artificial-intelligence