×
Home Current Archive Editorial board
Instructions for papers
For Authors Aim & Scope Contact
Original scientific article

PREDICTION OF TOXIC-METABOLIC DISORDERS AT EMERGENCY CONDITIONS USING MULTI-LABEL CLASSIFICATION IN MACHINE LEARNING

By
S. Ramadoss Orcid logo ,
S. Ramadoss

Bharath Institute of Higher Education and Research , Chennai , India

A. Kumaravel Orcid logo
A. Kumaravel

Bharath Institute of Higher Education and Research , Chennai , India

Abstract

Diagnosing critical conditions like Acute Liver Failure (ALF), Methanol Toxicity (MT), Alcohol Poisoning (AP), and Diabetic Ketoacidosis (DKA) is difficult due to similar symptoms and complex interdependent metabolism, often resulting in delayed and incorrect diagnoses in historic clinical practice. We present a hybrid machine learning framework integrating multilabel classification and association rule learning that provides better precision in diagnostics and uncovers complex interrelated conditions. Our methodology uses a Random Forest-based Multi-Output Classifier for multilabel classification, which demonstrates an 18% improvement on the accuracy of traditional single-label-based diagnoses and employs the Apriori Algorithm to find significant co-occurrence, finding that Alcohol Poisoning is linked to Acute Liver Failure with 82% confidence. We assessed our models on a heterogeneous dataset of 10,487 patient cases from Electronic Health Records (EHRs) from 2018-2023. The models developed perform well with LightGBM and XGBoost, providing accuracies of 85.2% and 84.7%, respectively, and validated on a subsequent dataset from EHRs from 2023-2024. As part of a Clinical Decision Support System (CDSS) prototype, the framework provides real-time and interpretable diagnostic support by using SHAP explanations and complies with HIPAA and FDA standards while providing a scalable risk assessment tool to improve patient safety and outcomes in critical care.

References

1.
Kumar V, Shah M. Multi Disease Prediction Using Deep Learning Framework for Electric Health Record. International Academic Journal of Science and Engineering. 2021;8(4):24-8.
2.
Ebrahimi A, Wiil UK, Schmidt T, Naemi A, Nielsen AS, Shaikh GM, et al. Predicting the risk of alcohol use disorder using machine learning: a systematic literature review. IEEE Access. 2021 Nov 8;9:151697-712.
3.
Jagadeeswaran l, Prasath S, Thyagarajan, & Nagarajan. Machine Learning Model to Detect the Liver Disease. International Academic Journal of Innovative Research.;9(1):06-12. 2022.
4.
Jagadish M. Association rule and its applications in machine learning. Machine Learning Tutorial [Internet]. 2025 Jan 23.
5.
Vij P, Prashant PM. International Journal of Aquatic Research and Environmental Studies. 2024;4(S1):39-44.

Citation

This is an open access article distributed under the  Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Article metrics

Google scholar: See link

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.