Advancing CTG-Based Fetal Monitoring with Multi-Modal Machine Learning and Explainable AI

View at publisher Summarise with VIRAT
Authors: M. S., M. S., Blessed Sam B
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Cardiotocography (CTG) plays an essential role in the continuous monitoring of fetal well-being, yet its interpretation often varies depending on clinician experience, workload, and environmental constraints. These inconsistencies can delay crucial medical decisions during labor. To address this, the present study proposes a multi-modal machine learning framework capable of classifying fetal health into three standard categories-normal, suspicious, and pathological. The system evaluates seven supervised learning models and incorporates advanced data augmentation techniques including SMOTE and Generative Adversarial Networks (GANs) to counter the scarcity of minority samples. The integration of Explainable AI (XAI) techniques such as SHAP and LIME provides transparency to model predictions, making the system clinically interpretable. A prototype Clinical Decision Support System (CDSS) is also developed to demonstrate real-time applicability. The proposed approach aims to elevate CTG analysis toward a more objective, accurate, and clinically trustworthy solution.

Fields of Study & Subjects

Artificial Intelligence in Healthcare ECG Monitoring and Analysis Machine Learning in Healthcare

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
480–483
Publication date
21 January 2026
Language
EN