A hybrid bio-inspired optimization framework for modeling infant neurodevelopment from maternal mental health and biometric data
Abstract
The primary identification and marking of infants at risk of adverse neurodevelopmental outcomes constitutes a critical public-health challenge, especially in resource-limited environments. This work builds on a hybrid (mimicking the actions of both whales and fireflies) optimization model, Hybrid Whale–Firefly Optimization with Enhanced Extreme Gradient Boosting (HWFO-EXGBoost), and introduces a set of biometric and maternal mental-health determinants, along with longitudinal clinical predictors, to enhance and accelerate the prediction of 12-month developmental status. A multimodal maternal–fetal monitoring framework combining psychometric scores, characteristics of the mothers' blood chemistry and obstetric history, and physiological parameters and infant anthropometry connected with the mother-infant dyad is used to produce the dataset, which consists of 199 mother–infant dyads. Hybrid Whale-Firefly Optimization mechanism allows for better feature selection and model hyperparameters to get better discrimination and calibration. The metrics that are used to evaluative comparative development include 12 performance measures, such as MCC, AUROC, AUPRC, and calibration metrics as per two established benchmarks NBTV-ND ¹ and ML-PND-SR ² . HWFO-EXGBoost always achieves better performance with 94.47% accuracy, 96.34% specificity, AUROC of 0.953, 88.57% sensitivity and AUPRC of 0.742, and excellent calibration properties. The results illustrate how maternal mental health scores overlaid on biometric baselines in an optimised institutional learning system is a powerful decision-making tool for detecting early neurodevelopmental risk, allowing planning of interventions in maternal-child health care systems.
Related
- A Gaussian quantum-inspired optimization framework for robust medical image watermarking
- A Dual-Stream Feature Learning Framework with Adaptive Bio-Inspired Protozoa-Starfish Optimization for Melanoma Classification.
- ConvWaveFormer: a hybrid wavelet and CNN-transformer framework for ECG biometric identification
- A hybrid deep learning and cryptographic framework using signcryption for robust biometric template protection
- A fault-aware, explainable proximal policy optimization based intelligent control framework with neuromorphic-inspired encoding for voltage and frequency stability
BibTeX
@article{ramachandran2026hybrid,
title = {{A hybrid bio-inspired optimization framework for modeling infant neurodevelopment from maternal mental health and biometric data}},
author = {Rajeswari Ramachandran and A. Muthusamy and C. Balaji and Shashi Kant Gupta},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-72522-x},
url = {https://www.nature.com/articles/s41598-026-72522-x},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A hybrid bio-inspired optimization framework for modeling infant neurodevelopment from maternal mental health and biometric data
AU - Rajeswari Ramachandran
AU - A. Muthusamy
AU - C. Balaji
AU - Shashi Kant Gupta
PY - 2026
DA - 2026/10/31
JO - Scientific Reports
DO - 10.1038/s41598-026-72522-x
UR - https://www.nature.com/articles/s41598-026-72522-x
AB - The primary identification and marking of infants at risk of adverse neurodevelopmental outcomes constitutes a critical public-health challenge, especially in resource-limited environments. This work builds on a hybrid (mimicking the actions of both whales and fireflies) optimization model, Hybrid Whale–Firefly Optimization with Enhanced Extreme Gradient Boosting (HWFO-EXGBoost), and introduces a set of biometric and maternal mental-health determinants, along with longitudinal clinical predictors, to enhance and accelerate the prediction of 12-month developmental status. A multimodal maternal–fetal monitoring framework combining psychometric scores, characteristics of the mothers' blood chemistry and obstetric history, and physiological parameters and infant anthropometry connected with the mother-infant dyad is used to produce the dataset, which consists of 199 mother–infant dyads. Hybrid Whale-Firefly Optimization mechanism allows for better feature selection and model hyperparameters to get better discrimination and calibration. The metrics that are used to evaluative comparative development include 12 performance measures, such as MCC, AUROC, AUPRC, and calibration metrics as per two established benchmarks NBTV-ND ¹ and ML-PND-SR ² . HWFO-EXGBoost always achieves better performance with 94.47% accuracy, 96.34% specificity, AUROC of 0.953, 88.57% sensitivity and AUPRC of 0.742, and excellent calibration properties. The results illustrate how maternal mental health scores overlaid on biometric baselines in an optimised institutional learning system is a powerful decision-making tool for detecting early neurodevelopmental risk, allowing planning of interventions in maternal-child health care systems.
SN - 2045-2322
ER -