Early Sepsis Prediction using Hybrid LightGBM and LSTM Model

Title

Early Sepsis Prediction using Hybrid LightGBM and LSTM Model

Creator

Lizzy Angelin Alphonsa, G.; Mary Jasmine, E.; Rajavel, Rajkumar

Description

Sepsis is a critical organ malfunction that results from an abnormal response of the body to infection and might be lethal. The early detection of sepsis is essential for the patient's life. However, the traditional clinical diagnostic systems are not capable of analyzing the complicated changes in the patient's vitals over time. Therefore, a hybrid predictive framework that merges Light Gradient Boosting Machine (LightGBM) and Long Short-Term Memory (LSTM) networks for fast and accurate sepsis detection in real-time using freely accessible MIMIC-III data, has been proposed in this research. Using LightGBM, the nonlinear relationships among the features are learnt very fast and efficient, while the LSTM gives the temporal dependencies in the sequence of the patient vital signs. The combined output of the two models is said to be more sensitive and robust than that of the single models. A Streamlit-based clinical dashboard is being provided, allowing for real-time predictions and visualization for healthcare professionals. The proposed system has shown a considerable increase in the accuracy of early sepsis detection and offers a non-restricted method for AI-assisted ICU monitoring. 2025 IEEE.

Source

International Conference on NexGen Networks and Cybernetics, IC2NC 2025 - Proceedings;pp.794-800

Date

01-01-2025

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

Hybrid Model; LightGBM; LSTM; MIMIC-III Dataset; Sepsis Prediction; Streamlit

Coverage

Lizzy Angelin Alphonsa G., Christ University, Department of AI, Ml & Data Science, Bangalore, India; Mary Jasmine E., Christ University, Department of AI, Ml & Data Science, Bangalore, India; Rajavel R., Christ University, Department of AI, Ml & Data Science, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833159484-8;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/IC2NC67409.2025.11376300

https://www.scopus.com/pages/publications/105035598002?origin=resultslist