Machine Learning in Distributed Data Networks like the FDA Sentinel System: Opportunities, Challenges, and Considerations

Access to larger amounts and more complex types of electronic health data in distributed data networks like the FDA Sentinel System has created a growing interest in the use of data-adaptive machine learning techniques to enhance their activities. However, the siloed storage and diverse nature of the databases in distributed data networks create unique challenges. This presentation discussed various opportunities for machine learning in distributed data networks like the FDA Sentinel System that conduct activities in pharmacoepidemiology and pharmacovigilance and presents unique challenges and considerations they face when applying such methods.