Early Prediction of Sepsis using Heart Rate Signals and Genetic Optimized LSTM Algorithm

TL;DR

This paper presents four novel machine learning models, optimized with a genetic algorithm, for early sepsis prediction using heart rate data from wearable devices, aiming to enable timely intervention outside ICU settings.

Contribution

It introduces and evaluates four new machine learning algorithms optimized with genetic algorithms for early sepsis prediction on wearable devices.

Findings

Models achieved promising prediction accuracy within one-hour window.

Transfer learning extended prediction capability to four hours.

Optimized models are feasible for implementation on wearable devices.

Abstract

Sepsis, characterized by a dysregulated immune response to infection, results in significant mortality, morbidity, and healthcare costs. The timely prediction of sepsis progression is crucial for reducing adverse outcomes through early intervention. Despite the development of numerous models for Intensive Care Unit (ICU) patients, there remains a notable gap in approaches for the early detection of sepsis in non-ward settings. This research introduces and evaluates four novel machine learning algorithms designed for predicting the onset of sepsis on wearable devices by analyzing heart rate data. The architecture of these models was refined through a genetic algorithm, optimizing for performance, computational complexity, and memory requirements. Performance metrics were subsequently extracted for each model to evaluate their feasibility for implementation on wearable devices capable of accurate heart rate monitoring. The models were initially tailored for a prediction window of one hour, later extended to four hours through transfer learning. The encouraging outcomes of this study suggest the potential for wearable technology to facilitate early sepsis detection outside ICU and ward environments.