Neural Bandits for Data Mining: Searching for Dangerous Polypharmacy

TL;DR

This paper introduces OptimNeuralTS, a neural bandit approach combining Neural Thompson Sampling and differential evolution to efficiently identify potentially inappropriate drug combinations in large claims datasets, improving detection accuracy.

Contribution

The paper presents a novel neural bandit method for optimizing the search for risky drug combinations, addressing computational challenges in polypharmacy data mining.

Findings

Detects up to 72% of PIPs in simulated data

Achieves 99% average precision with 30,000 steps

Efficiently handles large drug combination datasets

Abstract

Polypharmacy, most often defined as the simultaneous consumption of five or more drugs at once, is a prevalent phenomenon in the older population. Some of these polypharmacies, deemed inappropriate, may be associated with adverse health outcomes such as death or hospitalization. Considering the combinatorial nature of the problem as well as the size of claims database and the cost to compute an exact association measure for a given drug combination, it is impossible to investigate every possible combination of drugs. Therefore, we propose to optimize the search for potentially inappropriate polypharmacies (PIPs). To this end, we propose the OptimNeuralTS strategy, based on Neural Thompson Sampling and differential evolution, to efficiently mine claims datasets and build a predictive model of the association between drug combinations and health outcomes. We benchmark our method using two datasets generated by an internally developed simulator of polypharmacy data containing 500 drugs and 100 000 distinct combinations. Empirically, our method can detect up to 72% of PIPs while maintaining an average precision score of 99% using 30 000 time steps.