Combining clinical data from millions of patients, and behaviors of tens of thousands of care providers to assist doctors and patients in making better diagnoses, prognoses and therapeutic decisions.

Faculty

Areas of Focus

AI to Accelerate the Life Sciences/Drug Discovery

Alternative Models to Trials Using Real-World Data

Driving Gene-by-Environment Discovery in Biobanked Data

Leveraging EHR Biobank Data to Explore Alternative Indications and Potential Side Effects

Shortening the Duration of Clinical Trials

Cautions and Limitations of AI

Meta-Science Approaches and Data to Probe Assumptions in Model Building

Clinical Applications of AI

Antibiotic Resistance Prediction

to come

Autism Detection and Retaxonomization

to come

Medical Image Interpretation

Pathology Image Analysis

Fundamentals of AI

Federated Learning with Heterogeneous High-Dimensional Data from Multiple Institutions

Learning from Limited Labeled Data Using Self-Supervised and Supervised Pre-Training

Learning from Multimodal Data with Graph Neural Networks

ML to Assist in Cross-Institutional EHR Data Harmonization

In the News

Adverse Drug Effects During the COVID-19 Pandemic (October 13, 2021)
Research links public health emergencies, adverse drug reactions

More Intelligent Medicine (March 11, 2021)
Leaders in biomedical informatics chart roadmap for harnessing the promise of medical AI

Got Resistance? (April 29, 2019)
When it comes to TB, the computer has the answer

The Doctor and the Machine (April 3, 2019)
In new report, Harvard Med, Google scientists outline the promises and pitfalls of machine learning in medicine.

One Giant Step (Winter 2019)
Researchers are building an artificial intelligence system that can mimic human clinical decision making