BIDS-BCHSI Research Xchange Forum

Research Talk — Lowry Kirkby, 2019-2021 I4H Fellow.

TITLE: Using a Biomedical Knowledge Graph for Medical Diagnosis Prediction

ABSTRACT:  Neurodegenerative diseases and dementias are heterogeneous in their underlying brain dysfunction and symptomatic experience, however, objective methods for subtyping these complex disorders are lacking. As such, patients often receive a catch-all diagnosis and undergo a trial-and-error approach to symptom management, which can result in chronic disability and long-term suffering. Through the Innovate for Health Fellowship, Dr. Kirkby is developing an analytic framework for patient stratification and early dementia risk prediction by leveraging a Biomedical Knowledge Graph that is currently in development by researchers at UCSF. The Knowledge Graph incorporates information across multiple biological scales, including diseases, genes, proteins, anatomy, medications, and side effects. Combining this relational knowledge with data from patients’ Electronic Health Records offers the potential to uncover unique patient-specific signatures of disease and risk, which in turn may improve early disease detection and diagnosis.

Register here to receive virtual access link.