Attributes for Causal Inference in Longitudinal Observational Databases

TL;DR

This paper explores attributes derived from Bradford-Hill criteria to improve causal inference in longitudinal observational medical data for better detection of drug side effects.

Contribution

It introduces specific attributes based on causality criteria and evaluates their effectiveness in identifying side effects from observational data.

Findings

Attributes based on specificity improve side effect detection

Experiment and dosage attributes did not add significant value

Feature selection identified the most relevant causality-based attributes

Abstract

The pharmaceutical industry is plagued by the problem of side effects that can occur anytime a prescribed medication is ingested. There has been a recent interest in using the vast quantities of medical data available in longitudinal observational databases to identify causal relationships between drugs and medical events. Unfortunately the majority of existing post marketing surveillance algorithms measure how dependant or associated an event is on the presence of a drug rather than measuring causality. In this paper we investigate potential attributes that can be used in causal inference to identify side effects based on the Bradford-Hill causality criteria. Potential attributes are developed by considering five of the causality criteria and feature selection is applied to identify the most suitable of these attributes for detecting side effects. We found that attributes based on the specificity criterion may improve side effect signalling algorithms but the experiment and dosage criteria attributes investigated in this paper did not offer sufficient additional information.