Interpretable machine learning model for identification and risk factor of premature rupture of membranes (PROM) and its association with nutritional inflammatory index - a retrospective study

Aug 5, 2026

Upload by Skyler

Premature rupture of membranes (PROM) threatens maternal and neonatal outcomes, and clinical risk assessment remains limited. This retrospective study builds and evaluates an interpretable machine learning prediction model for PROM risk using screened variables and quantifies the relationship between PROM and the nutritional inflammatory index. Ridge regression and Boruta-selected features feed multiple algorithms, with selection and performance judged by ROC-AUC and classification metrics. SHAP-derived contributions support a nomogram for clinical interpretation and decision support.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Background

Systemic inflammation and nutritional indicators

Methods

Study design and data splitting

Feature selection and statistical modeling

Machine learning algorithms and evaluation

SHAP interpretation and nomogram

Results

Dataset and model performance

Key predictive factors

Conclusion

TYPE Original Research PUBLISHED 18 June 2025 DOI 10.3389/fmed.2025.1557919 OPEN ACCESS EDITED BY Maria Luisa Ojeda, University of Seville, Spain REVIEWED BY Takuya Kondo, Kyushu University, Japan Yefang Huang, Hospital of Chengdu University of Traditional Chinese Medicine, China Akihiro Yasui, Nagoya University, Japan *CORRESPONDENCE Qiulan Yu [18914631090@163.com](18914631090@163.com) RECEIVED 09 January 2025 ACCEPTED 20 May 2025 PUBLISHED 18 June 2025 CITATION Zheng M, Zhang X, Wang H, Yuan P and Yu Q (2025) Interpretable machine learning model for identiﬁcation and risk factor of premature rupture of membranes (PROM) and its association with nutritional inﬂammatory index: a retrospective study. Front. Med. 12:1557919 . doi: 10.3389/fmed.2025.1557919 COPYRIGHT © 2025 Zheng, Zhang, Wang, Yuan and Yu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Interpretable machine learning model for identiﬁcation and risk factor of premature rupture of membranes (PROM) and its association with nutritional inﬂammatory index: a retrospective study Meng Zheng, Xiaowei Zhang, Haihong Wang, Ping Yuan and Qiulan Yu* Department of Obstetrics and Gynecology, Binhai County People’s Hospital, Yancheng, Jiangsu, China Background: Premature rupture of membranes (PROM) poses signiﬁcant risks to both maternal and neonatal health. This study aims to construct a risk factor prediction model related to PROM by using machine learning technology and explore the association with nutritional inﬂammatory index. Methods: A retrospective analysis was conducted on patients with PROM. Based on the variables screened out by ridge regression and Boruta algorithm, univariate and multivariate logistic regression analyses were further adopted. According to the sample data, it is divided into the training set and the internal validation set in a ratio of 7:3 . The research group adopted four machine learning algorithms: Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF) . The selected variables were incorporated into model construction, with the area under the receiver operating characteristic (ROC) curve (AUC) serving as a criterion for model selection. Model performance was assessed using AUC values, sensitivity, speciﬁcity, recall, F1 score, and accuracy. The variables were selected based on the contribution degree of the variables in Shapley additive Interpretation (SHAP) to construct the nomogram. Results: A retrospective analysis was conducted involving 800 parturients at Binhai County People’s Hospital from January 2023 to October 2024, comprising 400 with PROM and 400 with normal delivery. The RF model demonstrated superior performance with an AUC of 0.757, sensitivity of 67.4%, and speciﬁcity of 65 . 1% . Key predictive factors identiﬁed included body mass index (BMI), prognostic nutritional index (PNI), platelet, albumin, and aggregate index of systemic inﬂammation (AISI) . The ROC of the model also showed good efﬁcacy, with an AUC of 0 .777. Frontiers in Medicine 01 [frontiersin.org](frontiersin.org) Conclusion: This study highlights the potential of machine learning in enhancing the understanding and prediction of PROM, and emphasizes the signiﬁcance of inﬂammatory and nutritional indicators, paving the way for future research in maternal-fetal medicine. KEYWORDS PROM, machine learning, nomogram, nutritional inﬂammation index, predictive models 1 Introduction Premature rupture of membranes (PROM) is a well-known risk factor for pre

FAQs

What is the purpose of the interpretable machine learning model in this study?

The study aims to construct a risk factor prediction model for PROM using machine learning and to examine how PROM relates to the nutritional inflammatory index.

How were predictive variables selected and models evaluated?

Variables were screened using ridge regression and Boruta, then incorporated into multiple machine learning models. Model selection and evaluation used ROC AUC and additional metrics such as sensitivity, specificity, recall, F1 score, and accuracy.

Which factors were identified as key predictors of PROM?

The study reports key predictive factors including BMI, PNI, platelet, albumin, and AISI, with model performance assessed through ROC characteristics.

Aug 5, 2026

Upload by Skyler