Abstract: Palliative care can improve patient experience and satisfaction but identifying patients appropriate for referral remains a challenge. The difficulty compounds when there is a need to develop consistent referral processes across multiple patient populations diverse in age, health, and coverage status. This is a common paradigm in healthcare data science – there is often a need to develop predictive recommendation systems that are consistent and equitable across vastly different inputs.
In this talk I will discuss how predictive analytics and machine learning can be utilized to identify patients appropriate for a palliative care path. I will then describe a particular use case – developing a palliative care referral mechanism that works well for both commercially insured adults and Medicare Advantage plan members – and use it to illustrate how data scientists can modify their modeling processes for success. I will discuss several approaches to modeling and demonstrate how each can be adjusted to work well within the bounds of multiple variations of one problem. I will also illustrate the limits of several common predictive algorithms in building niche models. Along the way I will give several deep dives into the practical challenges associated with predicting rare events such as palliative care need and discuss the limits of using claims data to develop measurable proxies for palliative care need and other health related events.
Attendees will learn how to reframe difficult problems into straightforward predictive analytics questions. Furthermore, they will learn how to select algorithms appropriate to answer those questions and how to modify modeling parameters to best suit even atypical modeling scenarios.
Bio: Evie Fowler is a data scientist based in Pittsburgh, Pennsylvania. She currently works in the healthcare sector leading a team of data scientists who develop predictive models centered on the patient care experience. She holds a particular interest in the ethical application of predictive analytics and in exploring how qualitative methods can inform data science work. She holds an undergraduate degree from Brown University and a master's degree from Carnegie Mellon.