Explainable Artificial Intelligence for Biology and Health
Modern machine learning (ML) models can accurately predict patient progress, an individual's phenotype, or molecular events such as transcription factor binding. However, they do not explain why selected features make sense or why a particular prediction was made. For example, a model may predict that a patient will get chronic kidney disease, which can lead to kidney failure. The lack of explanations about which features drove the prediction – e.g., high systolic blood pressure, high BMI, or others – hinders medical professionals in making diagnoses and decisions on appropriate clinical actions. I will briefly describe my group’s efforts to develop interpretable ML techniques for varied biological and medical applications, including treating cancer based on a patient’s own molecular profile, identifying therapeutic targets for Alzheimer’s, predicting kidney diseases, preventing complications during surgery, enabling pre-hospital diagnoses for trauma patients, and improving our understanding of pan-cancer biology and genome biology. My talk will focus in greater detail on interpretable ML techniques to identify molecular markers for anti-cancer drugs for acute myeloid leukemia, published in Nature Communications (Jan 2018) and our more recent works in collaboration with Harvard Medical School; our explainable artificial intelligence system, Prescience, for preventing hypoxemia in patients under anesthesia, featured on the cover of Nature Biomedical Engineering (Oct 2018); SHAP, our general ML framework on model interpretability, published as a full oral presentation at NeurIPS (2017; cited >500 over 2 years after publication); Tree explainer, our polynomial time algorithm for computing SHAP values for tree models, published in Nature Machine Intelligence as a cover article (Jan 2020) and our ML approach to identifying Alzheimer's disease therapeutic targets.
Prof. Su-In Lee is an Associate Professor in the Paul G. Allen School of Computer Science & Engineering and an Adjunct Associate Professor in the Departments of Genome Sciences, Electrical Engineering, and Biomedical Informatics and Medical Education at the University of Washington. She completed her PhD in 2009 at Stanford University with Prof. Daphne Koller in the Stanford Artificial Intelligence Laboratory. Before joining the UW in 2010, Lee was a visiting Assistant Professor in the Computational Biology Department at Carnegie Mellon University School of Computer Science. She has received the National Science Foundation CAREER Award and been named an American Cancer Society Research Scholar. She has received generous grants from the National Institutes of Health, the National Science Foundation, and the American Cancer Society.
The research done by Prof. Lee's group has conceptually and fundamentally advanced how AI can be integrated with biomedicine by addressing novel, forward-looking, and stimulating questions, enabled by AI possibilities. For example, although the primary focus of AI applications in the field of medicine had been on accurately predicting a patient’s phenotype (e.g., predicting the response to certain chemotherapy based on the patient’s gene expression profile), Prof. Lee focused on why a certain prediction was made, which can point to the molecular mechanisms underlying patient’s phenotype (e.g., drug sensitivity). This line of work has led to highly cited seminal publications in the field of foundational AI, clinical medicine, and computational molecular biology. Her research aims to push the boundaries of both foundational AI and molecular biomedicine, to address new questions and make novel discoveries from high-throughput molecular data or patient's medical record data.