# Noninvasive Risk Prediction Models for Heart Failure Using Proportional Jaccard Indices and Comorbidity Patterns

## TL;DR

This paper introduces a noninvasive heart failure risk prediction system using electronic medical records and novel similarity indices for comorbidity patterns.

## Contribution

The study introduces novel similarity indices (PJI, OPJI, APJI) for analyzing comorbidity patterns in EMRs to predict heart failure risk.

## Key findings

- The optimal model achieved 82.1% accuracy and an AUC of 0.878 in predicting high-risk heart failure.
- The models were effective across different age groups and sexes, showing demographic adaptability.
- The proposed indices offer a practical and straightforward method for comorbidity pattern matching in EMRs.

## Abstract

In the post-coronavirus disease 2019 (COVID-19) era, remote diagnosis and precision
preventive medicine have emerged as pivotal clinical medicine applications. This
study aims to develop a digital health-monitoring tool that utilizes electronic
medical records (EMRs) as the foundation for performing a non-random correlation
analysis among different comorbidity patterns for heart failure (HF).

Novel similarity indices, including proportional Jaccard index
(PJI), multiplication of the odds ratio proportional Jaccard index (OPJI), and
alpha proportional Jaccard index (APJI), provide a fundamental framework for
constructing machine learning models to predict the risk conditions associated
with HF.

Our models were constructed for different age groups
and sexes and yielded accurate predictions of high-risk HF across demographics.
The results indicated that the optimal prediction model achieved a notable
accuracy of 82.1% and an area under the curve (AUC) of 0.878.

Our noninvasive HF risk prediction system is based on
historical EMRs and provides a practical approach. The proposed indices provided
simple and straightforward comparative indicators of comorbidity pattern matching
within individual EMRs. All source codes developed for our noninvasive prediction
models can be retrieved from GitHub.