Supervised Adverse Drug Reaction Signalling Framework Imitating Bradford Hill's Causality Considerations

TL;DR

This paper introduces a supervised learning framework that uses Bradford Hill's causality considerations to better distinguish causal drug side effects from mere associations in large observational medical datasets.

Contribution

It combines Bradford Hill's causality principles with supervised learning to automate causal inference in drug safety signal detection, improving accuracy over existing methods.

Findings

Achieved AUC between 0.792-0.940, outperforming existing methods.

Demonstrated efficient calculation and update of features for big data.

Framework effectively discriminates causal from non-causal drug-outcome relationships.

Abstract

Big longitudinal observational medical data potentially hold a wealth of information and have been recognised as potential sources for gaining new drug safety knowledge. Unfortunately there are many complexities and underlying issues when analysing longitudinal observational data. Due to these complexities, existing methods for large-scale detection of negative side effects using observational data all tend to have issues distinguishing between association and causality. New methods that can better discriminate causal and non-causal relationships need to be developed to fully utilise the data. In this paper we propose using a set of causality considerations developed by the epidemiologist Bradford Hill as a basis for engineering features that enable the application of supervised learning for the problem of detecting negative side effects. The Bradford Hill considerations look at various perspectives of a drug and outcome relationship to determine whether it shows causal traits. We taught a classifier to find patterns within these perspectives and it learned to discriminate between association and causality. The novelty of this research is the combination of supervised learning and Bradford Hill's causality considerations to automate the Bradford Hill's causality assessment. We evaluated the framework on a drug safety gold standard know as the observational medical outcomes partnership's nonspecified association reference set. The methodology obtained excellent discriminate ability with area under the curves ranging between 0.792-0.940 (existing method optimal: 0.73) and a mean average precision of 0.640 (existing method optimal: 0.141). The proposed features can be calculated efficiently and be readily updated, making the framework suitable for big observational data.