Bayesian hierarchical rule modeling for predicting medical conditions

TL;DR

The paper introduces HARM, a Bayesian hierarchical model that predicts future medical conditions by selecting and personalizing association rules based on patient history, even with limited individual data.

Contribution

It presents a novel hierarchical Bayesian approach for selecting and personalizing predictive association rules in medical condition prediction.

Findings

Effective in predicting conditions with limited patient data

Personalizes predictions using hierarchical Bayesian modeling

Outperforms traditional rule-based methods

Abstract

We propose a statistical modeling technique, called the Hierarchical Association Rule Model (HARM), that predicts a patient's possible future medical conditions given the patient's current and past history of reported conditions. The core of our technique is a Bayesian hierarchical model for selecting predictive association rules (such as "condition 1 and condition 2 $\rightarrow$ condition 3") from a large set of candidate rules. Because this method "borrows strength" using the conditions of many similar patients, it is able to provide predictions specialized to any given patient, even when little information about the patient's history of conditions is available.