小于胎龄儿预测跨站点整合方法研究
Cross-site pooling with feature harmonization for small-for-gestational-age (SGA) prediction across heterogeneous feature spaces
该研究开发了一种跨站点整合框架,利用特征特定插补和泄漏安全的五折分割,评估了马来西亚和印度的产前数据。在印度测试集上,特征协调方法的AUROC为0.673,略高于仅使用印度数据的方法(0.553),但在马来西亚测试集上与仅使用马来西亚数据的方法相似(0.823 vs. 0.825)。研究显示,即使在特征异质性情况下,跨站点整合也是可行的,但需独立验证和前瞻性评估才能临床应用。
- Article
- Open access
- Published: 05 November 2026
- Jia Yu Lim1,
- Praveen Kumar Nirmalan2,
- Rijo Mathew Choorakuttil2,
- Neha Sethi A/P Naresh Sethi1,
- Azanna Ahmad Kamar4,
- Rahmah Saaid3,
- Nurul Syazwani Jalil3,
- Kwan Hoong Ng5,6 &
- …
- Shier Nee Saw ORCID: orcid.org/0000-0002-2598-84521
Scientific Reports (2026) Cite this article
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
Small-for-gestational-age (SGA) neonates face health risks when undetected, yet machine learning (ML) models are difficult to apply across sites with heterogeneous feature availability. We developed a cross-site pooling framework, incorporating feature-specific imputation and leakage-safe five-fold partitioning, for SGA prediction using Malaysian (n = 18,582) and Indian (n = 1,760) antenatal data. The framework is evaluated on a held-out partition of 853 complete records including 184 SGA events. Three training strategies were evaluated: (i) country-specific training using common features (baseline), (ii) pooled training with feature harmonization, and (iii) cross-country transfer using common features. In the Malaysia test set (n = 807, 169 SGA), the AUROCs were 0.825, 0.823, and 0.606, whereas in India test set (n = 46, 15 SGA), they were 0.553, 0.673, and 0.695. The feature-harmonized approach showed results similar to the country-specific baseline in Malaysia (0.823 vs. 0.825) and numerically higher than the India-only baseline in India (0.673 vs. 0.553) with wide overlapping CIs on 46 scans (15 SGA). In a training size-matched analysis, pooling Malaysian data raised India AUROC from 0.573 to 0.653 (95% CI 0.604–0.706) while adding the harmonized feature gave 0.655 (95% CI 0.608–0.706), no measurable difference. Compared to clinical diagnosis using EFW<10th centile, the model achieved slightly lower AUROC (Malaysia: 0.823 vs. 0.838; India: 0.673 vs. 0.695). We showed that cross-site pooling was feasible despite heterogeneous feature availability. Feature harmonization enabled integration of datasets with differing feature spaces rather than providing discriminative gain. Independent validation on unseen sites, clinically justified operating thresholds, and prospective evaluation are required before clinical deployment.
Abbreviations
- SGA:
-
Small-for-gestational-age
- AGA:
-
Appropriate-for-gestational-age
- FGR:
-
Fetal growth restriction
- PE:
-
Pre-eclampsia (high_risk_pe: high-risk pre-eclampsia)
- PIH:
-
Pregnancy-induced hypertension
- DM:
-
Diabetes mellitus
- GA:
-
Gestational age (at scanning)
- EFW:
-
Estimated fetal weight
- HC:
-
Head circumference
- AC:
-
Abdominal circumference
- FL:
-
Femur length
- BPD:
-
Biparietal diameter
- CPR:
-
Cerebroplacental ratio
- AF / af:
-
Amniotic fluid condition
- AFI / afi:
-
Amniotic fluid index
- ute_api:
-
Uterine artery pulsatility index
- ute_ari:
-
Uterine artery resistance index
- umb_api:
-
Umbilical artery pulsatility index
- psv:
-
Peak systolic velocity
- m_age:
-
Maternal age
- m_height:
-
Maternal height
- m_weight:
-
Maternal weight
- prev_failed_preg:
-
Previous failed pregnancy
- last_preg_sga / _fgr / _normal:
-
Outcome of last pregnancy (SGA / FGR / normal)
- ML:
-
Machine learning
- AI:
-
Artificial intelligence
- LR:
-
Logistic regression
- RF:
-
Random forest
- SVC:
-
Support vector classifier
- NN:
-
Neural network
- MICE:
-
Multiple Imputation by Chained Equations
- SMOTENC:
-
Synthetic Minority Oversampling Technique for Nominal and Continuous features
- SHAP:
-
SHapley Additive exPlanations
- CORAL:
-
Correlation Alignment
- IRM:
-
Invariant Risk Minimization
- DANN:
-
Domain-Adversarial Neural Networks
- AUROC:
-
Area under the receiver operating characteristic curve
- AUPRC:
-
Area under the precision-recall curve
- PPV:
-
Positive predictive value
- NPV:
-
Negative predictive value
- ECE:
-
Expected Calibration Error
- MAE:
-
Mean absolute error
- RMSE:
-
Root mean square error
- MAPE:
-
Mean absolute percentage error
- R2 :
-
Coefficient of determination (R-squared)
- CI:
-
Confidence interval
Acknowledgements
We would like to extend our sincere gratitude to the doctors, sonographers, and nurses from the Departments of Obstetrics and Gynaecology, as well as Paediatrics, for their invaluable contributions in providing prenatal care and ultrasound scan measurements for this study.
Funding
This work was supported in part by the Ministry of Higher Education, Fundamental Research Grant Scheme (FRGS/1/2023/SKK05/UM/02/3).
Author information
Authors and Affiliations
Department of Artificial Intelligence, Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur, 50603, Malaysia
Jia Yu Lim, Neha Sethi A/P Naresh Sethi & Shier Nee Saw
AMMA Center for Diagnosis and Preventive Medicine Pvt Ltd, Kochi, Kerala, India
Praveen Kumar Nirmalan & Rijo Mathew Choorakuttil
Department of Obstetrics and Gynaecology, Faculty of Medicine, Universiti Malaya, Kuala Lumpur, 50603, Malaysia
Rahmah Saaid & Nurul Syazwani Jalil
Department of Paediatrics, Faculty of Medicine, Universiti Malaya, Kuala Lumpur, 50603, Malaysia
Azanna Ahmad Kamar
Department of Biomedical Imaging, Faculty of Medicine, Universiti Malaya, Kuala Lumpur, 50603, Malaysia
Kwan Hoong Ng
Faculty of Medicine and Health Sciences, UCSI University, Springhill, Negeri Sembilan, Malaysia
Kwan Hoong Ng
Authors
- Jia Yu Lim
- Praveen Kumar Nirmalan
- Rijo Mathew Choorakuttil
- Neha Sethi A/P Naresh Sethi
- Azanna Ahmad Kamar
- Rahmah Saaid
- Nurul Syazwani Jalil
- Kwan Hoong Ng
- Shier Nee Saw
Corresponding author
Correspondence to Shier Nee Saw.
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval statement
The retrospective study protocols were approved by the Medical Research Ethical Committee at the University Malaya Medical Centre, Malaysia (Medical Research Ethical Committee ID NO: 2021329-9997) and AMMA Center for Diagnosis and Preventive Medicine Pvt Ltd, Kochi, Kerala, India (Ethical Committee NO: 05/2023).
Patient consent statement
Patient informed consent is waived by the Medical Research Ethical Committee at the University Malaya Medical Centre, Malaysia (Medical Research Ethical Committee ID NO: 2021329-9997) and AMMA Center for Diagnosis and Preventive Medicine Pvt Ltd, Kochi, Kerala, India (Ethical Committee NO: 05/2023).
Study protocol and registration
A study protocol was prepared as part of the ethics application and approval process. However, the protocol was not published or registered in a publicly accessible repository. The study design, model development procedures, and statistical analyses are described in detail in the Methods section.
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-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, 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 you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. 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-nc-nd/4.0/.
About this article
Cite this article
Lim, J.Y., Nirmalan, P.K., Choorakuttil, R.M. et al. Cross-site pooling with feature harmonization for small-for-gestational-age (SGA) prediction across heterogeneous feature spaces. Sci Rep (2026). https://doi.org/10.1038/s41598-026-78973-6
Received: 21 April 2026
Accepted: 29 October 2026
Published: 05 November 2026
DOI: https://doi.org/10.1038/s41598-026-78973-6
Keywords
来源:Nature 健康护理主题 · nature.com