PHDA partner, UPMC Enterprises, sponsored a workshop at the WSDM conference, the ACM WSDM Health Search and Data Mining workshop (HSDM 2020), held on February 3rd. The workshop brought together the information retrieval and data mining communities to tackle challenges in the healthcare domain. Dr. Yubin Kim, Director of Technology at UPMC Enterprises and CMU graduate, organized the workshop.
Dr. Zachary Lipton, CMU Assistant Professor of Business Technologies and Machine Learning and PHDA-supported investigator, gave a keynote talk titled “Machine Learning for Healthcare: Beyond i.i.d. Prediction” with the following abstract:
Following breakthroughs in computer vision and natural language processing, widespread excitement and financial support have buoyed a rapidly growing field of machine learning for healthcare. And yet, while most of machine learnings most impressive results concern point estimates under strict i.i.d. assumptions, medical decision-making often requires something more. Conditions shift (due to seasonality, changing prevalence of illnesses, and availability of tests), the quantities of interest are often counterfactual (causal) quantities, uncertainty quantification is often essential, and individuals are characterized by data from multiple modalities. In this talk, Dr. Lipton will discuss recent breakthroughs in deep learning for healthcare, as well as his own group’s work pioneering RNNs for multivariate clinical time series data and then focus on their more recent efforts to address aspects of decision-making that are fundamentally missing in the standard machine learning setup.
Dr. Lipton has received funding from the PHDA for his work developing and applying machine learning algorithms and other AI-driven approaches to overcome challenges in healthcare. He received additional support from AWS (read more about the PHDA and AWS teaming up here) for his project titled “Multi-Modal Learning from Imaging and EHR Data.”