William Crown, Chief Science office of Optum Labs will speak Wednesday, March 23 at 4:00 p.m. in Olin 114.
Traditional analytic methods are often ill-suited to the evolving world of health care Big Data which is characterized by massive volume, complexity, and velocity of information. Methods are needed that can extract inferences and construct predictive models efficiently using very large datasets containing healthcare utilization data, clinical data, data from personal devices, and many other sources. Although very large, such datasets can also be quite sparse (e.g., device data may only be available for a small subset of individuals) which creates problems for traditional statistical models. Many machine learning methods address such limitations effectively but are still subject to the usual sources of bias that commonly arise in observational studies.
This talk will provide (1) an overview to the rapidly changing environment of Big Data in healthcare, (2) an introduction to a common type of machine learning method called random forest, (3) an example of the application of machine learning methods to healthcare data, and (4) some cautions and thoughts about where the field is headed.
This lecture is sponsored by the Ronneberg Lecture Series and the department of Math and Computer Science.