Abstract:
|
Drug-induced cardiovascular adverse events have been a major concern for the Food and Drug Administration (FDA) and pharmaceutical companies. Drug-induced cardio-toxicity is observed in association with classes of drugs, including anticancer, antibiotics, antidepression, antipsychotics, and antidiabetics. FDA Adverse Event Reporting System (FAERS) has been a core pharmacovigilance system to support the FDA post-marketing safety surveillance program for all approved drug and therapeutic products. Current methods focus on identifying high reporting rates in a particular drug and a particular adverse event (AE). However, a single drug and AE combination should not be considered in isolation, but combinations of other AEs with that drug and other combinations of that AE and that drug should be considered. This study utilizes machine learning algorithms to identify sets of drugs that share common profiles of AEs and their relationships, and develops statistical models for signal detection and analysis of two particular reporting rates of interest, such as sex-related differences in drug-induced cardiac risks.
|