伊朗新生儿死亡预测:基于机器学习模型的校准与表型探索
Neonatal mortality prediction under extreme class imbalance: calibrated supervised models and exploratory phenotype analysis in a population-based Iranian registry
伊朗Shiraz大学医学科学中心团队开发L2正则化逻辑回归(LR)和LightGBM模型,在61,517名新生儿(含131例死亡)的伊朗注册库中验证,LR在τ*=0.004阈值下实现97.3%特异性,捕获87.8%死亡病例;外部验证604例死亡病例中LR标记69.5%。
Abstract
Neonatal mortality remains a leading contributor to under-five deaths, yet early, individualized risk prediction is hampered by the rarity of the outcome and by limited attention to calibration and interpretability in prior models. We developed and stress-tested machine learning (ML) models for neonatal mortality prediction in a large, population-based cohort, integrating probability calibration, explainable AI, and exploratory unsupervised phenotyping. The development cohort of 61,517 neonates (131 deaths; class imbalance 1:469) was used to train L2-regularized logistic regression (LR) and LightGBM models on 60 routinely available perinatal features. performance was assessed by discrimination (AUROC, AUPRC), calibration, and decision-curve analysis, while SHAP and four unsupervised methods (UMAP, K-means, Isolation Forest, Apriori) characterized the underlying risk structure. Locked models then underwent a one-time case-only external stress test on 604 deceased neonates from a separate center and later period. LR achieved an AUROC of 0.955 (LightGBM, 0.944); at the optimal threshold (τ*=0.004) it captured 87.8% of deaths at 97.3% specificity, and positive net clinical benefit. In the external stress test, LR flagged 69.5% of deaths. Exploratory unsupervised analyses, fitted without outcome labels and evaluated post hoc against mortality, described a single high-risk phenotype; a K-means cluster comprising 6.7% of neonates contained 89.3% of all deaths. In this large, heterogeneous cohort, well-regularized ML models provided calibrated, interpretable, and early neonatal mortality risk stratification. The case-only design of the external cohort permits assessment of sensitivity only; external discrimination and calibration remain to be established, and prospective evaluation is warranted before clinical deployment.
Acknowledgements
The authors thank the IMAN registry team and participating neonatal centers for their contribution to data collection and quality assurance. The authors acknowledge the use of artificial intelligence–based language editing tools solely for improving grammar, clarity, and language quality during manuscript preparation.
Funding
This research received no external funding.
Author information
Authors and Affiliations
Department of Obstetrics and Gynecology, Maternal-Fetal Medicine Research Center, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
Shaghayegh Moradi Alamdarloo, Nasrin Asadi, Khadijeh Bazrafshan & Atefe Hashemi
Department of Computer Science, Faculty of Engineering, University of Freiburg, Freiburg, Germany
Amirreza Kanafchian
Neonatal Research Center, Shiraz University of Medical Sciences, Shiraz, Iran
Hamideh Barzegar
Maternal-Fetal Medicine Research Center, Iranian Society of Perinatology, Shiraz University of Medical Sciences, Shiraz, Iran
Homeira Vafaei Cisakht
Graduate School of Management and Economics, Sharif University of Technology, Tehran, Iran
Fatemeh Asghari
Department of Anesthesiology, School of Medicine, Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran
Alireza Montaseri
Neonatal Research Center, Department of Pediatrics, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
Reza Bahrami
Student Research Committee, School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran
Ali Haghighi
Authors
- Shaghayegh Moradi Alamdarloo
- Amirreza Kanafchian
- Hamideh Barzegar
- Homeira Vafaei Cisakht
- Nasrin Asadi
- Fatemeh Asghari
- Alireza Montaseri
- Reza Bahrami
- Khadijeh Bazrafshan
- Atefe Hashemi
- Ali Haghighi
Corresponding authors
Correspondence to Atefe Hashemi or Ali Haghighi.
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics approval and consent to participate
The study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Shiraz University of Medical Sciences, Shiraz, Iran (IR.SUMS.REC.1405.176). The analysis used de‑identified registry data, and the requirement for informed consent was waived by the ethics committee due to the retrospective nature of the study and the use of anonymized data.
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/.
About this article
Cite this article
Alamdarloo, S.M., Kanafchian, A., Barzegar, H. et al. Neonatal mortality prediction under extreme class imbalance: calibrated supervised models and exploratory phenotype analysis in a population-based Iranian registry. Sci Rep (2026). https://doi.org/10.1038/s41598-026-76979-8
Received: 04 July 2026
Accepted: 16 October 2026
Published: 20 October 2026
DOI: https://doi.org/10.1038/s41598-026-76979-8
Keywords
来源:Nature 健康护理主题 · nature.com