Medicine, Biomedical Informatics Research (BMIR)

Multi-omics, multi-modal, multi-scale data fusion for precision medicine

Vast amounts of molecular data characterizing the genome, epi-genome and transcriptome are becoming available for a wide range of complex disease such as cancer and neurodegenerative diseases. In addition, new computational tools for quantitatively analyzing medical and pathological images are creating new types of phenotypic data.  Now we have the opportunity to integrate the data at molecular, cellular and tissue scale to create a more comprehensive view of key biological processes underlying complex diseases.

Our research focus is in computational systems biology, primarily in cancer and more recently in neurodegenerative diseases.  We develop and apply methods to understand biological processes underlying disease, using high-throughput genomic and proteomic datasets and integrating them with phenotypes and clinical outcomes. A key interest is dissecting how the cellular composition and organization of tissues affects their behaviour in disease; and how these things might be targeted for therapy or diagnostic purposes.

We analyze multiple types of health data (EHR, Claims, Wearables, Weblogs, and Patient blogs), to answer clinical questions, generate insights, and build predictive models for the learning health system. Our group runs the country's only bedside consult service to enable better medical decisions using aggregate EHR and Claims data at the point of care. Our team leads the Stanford Medicine Program for Artificial Intelligence in Healthcare, which makes predictions that allow taking mitigating actions, and studies the ethical implications of using machine learning in clinical care.

Multi-omics, multi-modal, multi-scale data fusion in complex diseases using machine learning