Fri, Nov 19, 2021, 09:00 – 10:00AM (PDT), 12:00 – 1:00PM (EST)
There has been a continued surge in both the availability of patient data along with computational advances that have pushed forward the possibilities for more personalized medicine. Most patient data are available in the form of Electronic Health Records (EHR) which serves as an effective basis by which to make important scientific discoveries. This data source is not without bias, however, limiting the potential impact of translating findings into practice. Other types of patient data that are linked to EHR, such as images and notes, can work in tandem to derive more translatable and generalizable insights from retrospective data, especially when used in machine learning frameworks. However, there are still challenges in how these data can effectively be fused together. In this talk, we invited Dr. Benjamin Glicksberg, Assistant Professor from Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, who will present on clinical applications of multi-modal patient data analyses in COVID-19 and a framework to allow for prospective evaluation of machine learning models. Dr. Glicksberg will also discuss in depths about extensions of this framework to other clinical domains, particularly cardiovascular disease with an emphasis on fusing electrophysiological waveforms with other patient data.
Dr. Glicksberg, Benjamin
a. Assistant Professor
b. Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai
c. Benjamin Glicksberg, PhD is an Assistant Professor at the Icahn School of Medicine at Mount Sinai. Dr. Glicksberg works in the realm of clinical informatics particularly involving Electronic Health Record data. He uses machine learning to couple multi-omic patient health data to forward personalized medicine. He completed his PhD in Neuroscience at the Icahn School of Medicine at Mount Sinai in 2017 and post-doctoral work at the University of California, San Francisco in 2019.