The development of a scoring and ranking strategy for a patient-tailored adverse drug reaction prediction in polypharmacy

Abstract

Only few applications are currently dealing with personalized adverse drug reactions (ADRs) prediction in case of polypharmacy. The study aimed to develop a patient-tailored ADR web application, considering characteristics from 734 drugs and relevant patient related factors. The application was designed in Python using a scoring and ranking system based on frequency and severity, computed for each ADR and expressed through an online platform. A neural networks algorithm was used for predicting the severity of ADRs. The application inputs are: age, gender, drugs, relevant pathologies. The outputs are: an overall severity profile (hospitalization and mortality risk), a stratified risk on specific ADR groups and a sorted list of the most important ADRs depending on frequency and severity. The Severity prediction model validation resulted in 79.7–85.1% Area Under the Receiver Operating Characteristic Curve Score, which lies in the good cut-off of 75–90%. The program offers a complex view regarding the ADR profile of a given patient and could be used by the physician and clinical pharmacist during patient safety monitoring, for a coherent therapy choice or medication adjustment, due to the good therapy coverage and the inclusion of relevant patient comorbidities.