跳到正文
原文
Nature 健康护理主题·· 20 天前AI 评分43

一种仿生优化模型用于预测婴儿神经发育

A hybrid bio-inspired optimization framework for modeling infant neurodevelopment from maternal mental health and biometric data

AI 导读

该研究提出了一种结合鲸鱼和萤火虫行为的优化模型(HWFO-EXGBoost),结合母亲心理健康和生物测量数据,预测婴儿12个月的神经发育状况。该模型在199对母婴数据集上实现了94.47%的准确率、96.34%的特异性、0.953的AUROC和0.742的AUPRC,表明优化后的模型能有效预测婴儿神经发育风险,有助于早期干预。

正文

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

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-ND1 and ML-PND-SR2. 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.

Acknowledgements

There is no acknowledgement involved in this work.

Funding

No funding is involved in this work.

Author information

Authors and Affiliations

  1. LGPR Postdoctoral Researcher, Lincoln University College, Petaling Jaya, Malaysia

    Rajeswari Ramachandran

  2. Department of Computer Technology, Kongu Engineering College, Erode, Tamil Nadu, India

    A. Muthusamy

  3. Department of Computer Applications, SRM Institute of Science and Technology Tiruchirappalli, Tiruchirappalli, India

    C. Balaji

  4. Adjunct Faculty (Research), Lincoln University College Malaysia, Petaling Jaya, Malaysia

    Shashi Kant Gupta

Authors

  1. Rajeswari Ramachandran
  2. A. Muthusamy
  3. C. Balaji
  4. Shashi Kant Gupta

Corresponding author

Correspondence to Rajeswari Ramachandran.

Ethics declarations

Competing interests

Competing interests is not applicable in this work.

Ethics approval and consent to participate

No participation of humans takes place in this implementation process.

Human and animal participants

No violation of Human and Animal Rights is involved.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ramachandran, R., Muthusamy, A., Balaji, C. et al. A hybrid bio-inspired optimization framework for modeling infant neurodevelopment from maternal mental health and biometric data. Sci Rep (2026). https://doi.org/10.1038/s41598-026-72522-x

Download citation

  • Received: 03 February 2026

  • Accepted: 16 September 2026

  • Published: 31 October 2026

  • DOI: https://doi.org/10.1038/s41598-026-72522-x

Keywords

来源:Nature 健康护理主题 · nature.com