CCEB Seminar-Qi Long, PhD

Rapid advances in technology have enabled generation of enormous amounts of health-related data such as electronic health records (EHRs) data and mobile health (mHealth) data. Such rich, yet complex data offer remarkable opportunities for enhancing and transforming a learning health system, and, at the same time, present significant analytical challenges. In this talk, I will share our research group's recent journey on developing and applying innovative statistical and machine learning methods for EHRs data and mHealth data to advance precision medicine in a learning health system. The first project that will be discussed aims to develop distributed learning methods for predicting medical events using EHRs data from multiple healthcare systems without sharing subject-level data across them. The proposed approach can use both structured and unstructured EHRs data collected over irregular time points and can be incorporated into an EHR system as a clinical decision support system. The second project that will be presented seeks to develop a clinical decision support system for accurate diagnosis of kidney obstruction which includes a robust prediction model developed using renogram imaging data and relevant clinical variables in EHRs. The third project that will be shared aims to develop an mHealth/telemedicine tool for improving pain management of sickle cell disease patients which includes a hybrid statistical and mechanistic model for optimizing individualized treatment recommendations. Our recent journey has demonstrated the significant value of health data science in creating and enhancing a robust learning health system. Our experience also suggests that building on the core principles of statistical thinking a multi-disciplinary, team science approach offers great promises to accelerate innovation and fully harness the power of ever-growing health data to tackle complex real world problems in precision medicine and population health. *Basic understanding of statistical and machine learning methods is helpful but not required. Learning ObjectivesDescribe the value that health data science creates for a learning health system Give examples of and understand how advanced statistical and machine learning methods can be employed to develop and enhance clinical decision support system 3. Give examples of and understand how advanced statistical and machine learning methods can be employed to advance telemedicine