The holy grail of pharmacovigilance systems has been to identify, with certainty, those post-marketed drugs that cause unexpected reactions with one another. These poly-pharmaceutical reactions may have gone unnoticed due to the absence of sufficient evidence and/or their reaction severity was not sufficiently strong enough to draw researcher attention. We plan to automate the signal detection process of adverse drug combinations with the TylerADE system by using the FDA's Adverse Effects Reporting System (FAERS). Once collected, the data will be machine learned to identify potential n-drug adverse reactions. This system could assist in prioritizing bench studies more efficiently as well as be used in a clinical setting at the point of prescription to calculate potential adverse reactions.
Elath, Harshini; Dixit, Rohit R.; Schumaker, Robert P.; and Veronin, Michael A., "Predicting Deadly Drug Combinations through a Machine Learning Approach" (2018). PACIS 2018 Proceedings. 177.