Citation

Nor Hisham Shah, Norliyana and Abdul Razak, Normy Norfiza and Abdul Razak, Athirah and Khalid, Ahmad Shahrafidz and Tang, Tong Boon and Ahmad Fauzi, Mohammad Faizal and Jan, Rashid and Singh, Jaspaljeet (2025) Classifications of Multiple Organ Failures Using SOFA Score. In: 1st International Conference on Smart Cities, ICSC 2024, 10 - 11 September 2024, Sabah, Malaysia.

Text 4.pdf - Published Version Restricted to Repository staff only Download (225kB)

Abstract

Multiple organ failures are the main cause of mortality and morbidity, especially in intensive care units. The Sequential Organ Failure Assessment (SOFA) score has been used to evaluate organ function for patients in the ICU. This study aims to apply machine learning models for the multiclass classification of mild, moderate, and severe multiple organ failures based on total SOFA score. A sample of 3999 patients was chosen for assessment from the Medical Information Mart for Intensive Care III (MIMIC III) database. The results showed that the bagging algorithm achieved an accuracy of 96.2% for the multiclass classification. Using the correlation feature selection method, the bagging algorithm achieved an accuracy of 91.2% with 84.3% precision and 80.2% recall for the classification of multiple organ failures.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Machine Learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	27 Aug 2025 03:14
Last Modified:	29 Aug 2025 09:51
URII:	http://shdl.mmu.edu.my/id/eprint/14418

Downloads

Edit (login required)