Predicting a single HIV drug resistance measure from three international interpretation gold standards

摘要

ABSTRACT Objective:To investigate the possibility of combining the interpretation of three gold standard interpretation algorithms using weighted heuristics in order to produce a single resistance measure.Methods:The outputs ofHIVdb,Rega,ANRS were combined to obtain a single resistance profile using the equally weighted voting algorithm, accuracy based weighing voting algorithm and theBayesian based weighted voting algorithm techniques.Results:TheBayesian based voting combination increased the accuracy of the resistance profile prediction compared to phenotype, from58% to69%.The equal weighted voting algorithm and the accuracy based algorithm both increased the prediction accuracy to60%.Conclusions:From the result obtained it is evident that combining the gold standard interpretation algorithms may increase the predictive ability of the individual interpretation algorithms.