WIP: Medical Incident Prediction Through Analysis of Electronic Medical Records Using Machine Lerning: Fall Prediction

TL;DR

This study explores fall risk prediction using machine learning on electronic medical records, highlighting the importance of analyzing explanatory variables for improved accuracy in a hospital setting.

Contribution

It introduces a preliminary approach to predict medical incidents, especially falls, by analyzing EMR data with machine learning, emphasizing variable importance.

Findings

Explanatory variable analysis improves prediction accuracy.

Handling data imbalance enhances model performance.

Algorithm comparison identifies the most effective machine learning methods.

Abstract

This paper reports our preliminary work on medical incident prediction in general, and fall risk prediction in specific, using machine learning. Data for the machine learning are generated only from the particular subset of the electronic medical records (EMR) at Osaka Medical and Pharmaceutical University Hospital. As a result of conducting three experiments such as (1) machine learning algorithm comparison, (2) handling imbalance, and (3) investigation of explanatory variable contribution to the fall incident prediction, we find the investigation of explanatory variables the most effective.