Title

Ensemble neural network modelling for stratified HbA1c prediction: Integrating past glucose measurement as a predictor of glycaemic control

Authors

Prakruti Dash¹, Kasala Farzia¹, Dharashree Priyadarshini² & Saurav Nayak^2,*

Affiliation

1Department of Biochemistry, All India Institute of Medical Sciences, Bhubaneswar, Odisha, India; 2Department of Biochemistry, IMS & SUM Hospital Campus-II, Phulnakhara, Bhubaneswar, Odisha, India; *Corresponding author

Email

Prakruti Dash - E-mail: biochem_prakruti@aiimsbhubaneswar.edu.in

Kasala Farzia - E-mail: kayesha48222@gmail.com
Dharashree Priyadarshini - E-mail: dharashree61@gmail.com
Saurav Nayak - E-mail: sauravnayak@soa.ac.in , drsauravn@gmail.com

Article Type

Research Article

Date

Received October 1, 2025; Revised October 31, 2025; Accepted October 31, 2025, Published October 31, 2025

Abstract

Accurate assessment of glycemic control is crucial for effective diabetes management and the prevention of long-term complications. This study employed an ensemble neural network framework, combining a Multi-Layer Perceptron Regressor (MLPR) and Classifier (MLPC) model, to predict and stratify HbA1c using routine fasting (FBS) and post-prandial (PPBS) glucose values from retrospective e-laboratory data (n = 22,920, 2021–2024). The regressor, trained on mean FBS and PPBS values from the preceding three months, achieved an R² of 81 ± 3.7%, sMAPE of 9.13 ± 4.01% and RMSE of 1.1 ± 0.01, reflecting high predictive accuracy and minimal bias. Partial Dependence and ICE analyses revealed a strong, consistent positive association of FBS with HbA1c across glycaemic ranges. The classifier, based on predicted HbA1c, achieved 87.4% accuracy, 94.3% precision and a Diagnostic Odds Ratio of 35.26 ± 0.36, as confirmed by ROC analysis, which demonstrated superior discrimination compared to traditional glucose metrics.

Keywords

HbA1c prediction, fasting blood glucose, post-prandial blood glucose, ensemble neural network, multi-layer perceptron, glycaemic control, machine learning, diagnostic accuracy

Citation

Dash et al. Bioinformation 21(10): 3941-3946 (2025)

Edited by

P Kangueane

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.