AI for Digital Health: A Full-Stack Health Data Science Perspective
Fei Wang
April 7, 2023, Friday, 11:00 AM - 12:00 NOON EDT
Digital health aims at improving care delivery and making medicine more precise by technologies accounting for genetic, clinical, behavioral and environmental risk factors. In recent years, with the rapid advancement and broad deployment of various technologies including sequencing, electronic health records, mobile and wearable devices, internet and social media, and others, vast amounts of complex information have been accumulated in an unprecedented speed at individual level. This provides an opportunity and foundation for realizing digital health. Artificial Intelligence (AI) technologies, which aims at mimicking human intelligence with computer systems, have demonstrated strong potential in perceiving, synthesizing and inferring complex information. In this talk, I will present the research from my lab health in recent years on building machine learning models for analyzing different types of data involved in different levels of human life science, and the need for transitioning from conventional focused-community based strategy to holistic full-stack regime for modern health data science research. I will also talk about the challenges and opportunities.
Dr. Wang got his PhD on machine learning in 2008 from Tsinghua University in China. In 2010 he joined the healthcare analytics research group in IBM T. J. Watson Research Center focusing on developing machine learning models for analyzing healthcare data, especially electronic health records (EHR). His early research, including patient similarity analytics, disease progression modeling and deep learning for EHR analysis, has been widely recognized. In 2016, Dr. Wang joined Weill Cornell Medicine as a faculty member on health informatics to continue his research. He is the winner of the Parkinson's Progression Markers Initiative (PPMI) data challenge on subtyping Parkinson's disease in 2016 and the NeurIPS/Kaggle data challenge on classification of clinically actionable genetic mutations in 2017. Dr. Wang's current research interests include multi-modal machine learning for integrative analysis of heterogeneous biomedical data, interpretable and responsible artificial intelligence models for clinical decision support, federated and distributed models for privacy-preserving biomedical data mining, as well as algorithmic fairness.