Machine learning-based fetal health prediction and development of smart web application.

AI / informaticsFrontiers in artificial intelligence· 2026

Machine learning-based fetal health prediction and development of smart web application.

Chetan Puri, K T V Reddy, Pradnyawant M Gote

Read paper

Prediction Models & Risk ScoresAI / informaticsQ1IF 7.8

LightGBM model classified fetal health from cardiotocography data with high accuracy.

Machine learning-based fetal health prediction and development of smart web application.

Chetan Puri … Pradnyawant M Gote

Frontiers in artificial intelligence · 2026 · Q1 in Artificial Intelligence

Background

Fetal health monitoring is critical for early identification of pregnancy-related risks.

Methods

A machine learning-based framework was developed to classify fetal health into Normal, Suspect, and Pathological categories using cardiotocography-derived clinical features.

Results

correctly classified fetal status in the vast majority of cases

96.03%

Accuracy

91.99%

Balanced accuracy

93.05%

Macro F1-score

99.02%

ROC-AUC

More results

SHAP-based explainability identified abnormal short-term variability and fetal heart rate accelerations as the most important features.

“

Conclusion

DISCUSSION: The best-performing LightGBM model was integrated into a Streamlit-based web application for real-time fetal health prediction, demonstrating its potential as a clinical decision-support tool.

Machine learning-based fetal health prediction and development of smart web application.

Machine learning-based fetal health prediction and development of smart web application.

Related papers