Dr. Peter Yu's expertise lies in the intersection of medical informatics, healthcare operations and public policy. While President of the American Society of Clinical Oncology, ASCO launched CancerLinq, which aggregates medical oncology data across U.S. academic and community practices, and 2 journals; JCO Global Oncology and JCO Cancer Clinical Informatics (Associate Editor). In his position as Clinical Member, Memorial Sloan Kettering Cancer Center he is on the leadership team for the strategic partnership between MSK and Hartford HealthCare whose mission is to accelerate the dissemination of knowledge from academic medical centers to community healthcare systems. Hartford HealthCare is a 7-hospital system caring for 1/3 of the Connecticut population. Dr. Yu serves on Hutchinson Institute for Cancer Outcomes Research (HICOR) Fred Hutchinson Cancer Research Center External Advisory Board, California Cancer Registry Advisory Committee, Epic Systems Adult Oncology Steering Board, and the American Joint Committee on Cancer (AJCC) Implementation Committee.
Machine Learning Models of Chemotherapy Induced Neutropenia
Structured data in the EHRs of 2806 patients who received a total of 17,513 chemotherapy treatments was aggregated and de-identified to develop a predictive algorithm for risk of chemotherapy induced febrile neutropenia. Linear, tree-based or ensemble methods were developed and an optimal algorithm using only 20 clinical features was identified.
The value of data in healthcare is undeniable and realized when raw information is successfully converted into knowledge that changes clinical practice. To drive value improvements and ensure that the right patient receives the right care requires the right data in combination with the right data analytics. This session will cover various aspects and challenges of data science in hospitals and health systems that drive healthcare with better outcomes.