# Probabilistic classification of late treatment failure in uncomplicated falciparum malaria

## TL;DR

This paper introduces PfRecur, a Bayesian software tool that improves the accuracy of identifying treatment failure in malaria by accounting for complex infections.

## Contribution

The paper introduces PfRecur, a novel Bayesian probabilistic classifier for distinguishing treatment failure from reinfection in polyclonal malaria infections.

## Key findings

- Current match-counting methods may overestimate treatment failure due to high false-discovery rates in polyclonal infections.
- PfRecur provides accurate Bayesian posterior probabilities for treatment failure in recurrent falciparum malaria.
- The tool was successfully applied to data from Angola, demonstrating its utility in high transmission settings.

## Abstract

Distinguishing treatment failure (recrudescence) from reinfection in uncomplicated falciparum malaria is essential for characterising antimalarial treatment efficacy in malaria endemic areas. Classification of recrudescence versus reinfection is usually based on a comparison of parasite allelic calls derived from PCR amplification and electrophoresis of individual polymorphic markers in the acute and recurrent blood samples. Match-counting methods (e.g., 3/3 or 2/3 matching alleles) have usually been applied, but these do not account for multiple comparisons per-marker when infections are polyclonal. We show that when infections are polyclonal, as is common in high transmission settings, currently used match-counting and model-based methods may have unacceptably high false-discovery rates leading to overestimation of treatment failure. We develop the software PfRecur which provides analytical Bayesian posterior probabilities of treatment failure in recurrent falciparum malaria. We use data from a recent study in Angola to demonstrate the potential utility of our model in resolving complex polyclonal P. falciparum infections, thereby providing more accurate estimation of treatment failure rates.

Distinguishing treatment failure from reinfection is crucial for assessing antimalarial efficacy in endemic regions. Here the authors introduce the probabilistic classifier PfRecur, a software utilizing Bayesian analysis to improve accuracy in identifying treatment failures in polyclonal infections, and apply it to data from Angola.