Machine Learning–Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory-Wide Cohort Study

IF 1.5 4区医学 Q3 OBSTETRICS & GYNECOLOGY

Journal of Obstetrics and Gynaecology Research Pub Date : 2025-09-30 DOI:10.1111/jog.70087

Claire Chenwen Zhong, Junjie Huang, Zehuan Yang, Zhaojun Li, Yu Jiang, Jinqiu Yuan, Xiaodan Huang, Xiaofang Liu, Queran Lin, Han Wang, Jonathan Poon, Qi Dou, Irene Xin Yin Wu, Martin C. S. Wong

{"title":"Machine Learning–Predictive Models for Survival in Uterine Cancer Patients With Type 2 Diabetes: A Territory-Wide Cohort Study","authors":"Claire Chenwen Zhong, Junjie Huang, Zehuan Yang, Zhaojun Li, Yu Jiang, Jinqiu Yuan, Xiaodan Huang, Xiaofang Liu, Queran Lin, Han Wang, Jonathan Poon, Qi Dou, Irene Xin Yin Wu, Martin C. S. Wong","doi":"10.1111/jog.70087","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Aim</h3>\n \n <p>This study aimed to develop predictive models and establish a risk scoring system to identify risk factors associated with survival in uterine cancer patients with type 2 diabetes (T2D) and estimate their survival probabilities.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Data were collected from the Hong Kong Hospital Authority Data Collaboration Laboratory (HADCL) from 2000 to 2020. Cox proportional hazards regression, survival tree, LASSO Cox regression, boosting, and random survival forest (RSF) were utilized to develop predictive models for survival. Key risk factors were identified through Shapley Additive Explanations analysis, whereas the AutoScore-Survival package facilitated the development of a risk scoring system.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>This cohort study included 2047 uterine cancer patients with T2D. The average survival time was 100.82 (standard deviation: 72.75) months. The RSF model demonstrated the strongest predictive performance, achieving a time-dependent area under the curve (AUC) of 0.823 and a <i>C</i>-index of 0.90. A risk scoring system was created based on several criteria: age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium level, low-density lipoprotein cholesterol level (LDL-C) level, body mass index (BMI), and triglycerides level. This scoring system classified 31.4% of patients as high-risk, resulting in a 5-year survival probability of 43.5%, about 1.7 times lower than that of the low-risk group.</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>This study leveraged machine learning to identify key survival predictors and develop a clinically interpretable risk scoring system for uterine cancer patients with T2D. Key predictors, including age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium levels, LDL-C levels, BMI, and triglycerides levels, effectively stratified survival risk. These findings demonstrate the potential of data-driven models to enhance individualized prediction and inform targeted clinical management.</p>\n </section>\n </div>","PeriodicalId":16593,"journal":{"name":"Journal of Obstetrics and Gynaecology Research","volume":"51 10","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12484716/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Obstetrics and Gynaecology Research","FirstCategoryId":"3","ListUrlMain":"https://obgyn.onlinelibrary.wiley.com/doi/10.1111/jog.70087","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"OBSTETRICS & GYNECOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Aim

This study aimed to develop predictive models and establish a risk scoring system to identify risk factors associated with survival in uterine cancer patients with type 2 diabetes (T2D) and estimate their survival probabilities.

Methods

Data were collected from the Hong Kong Hospital Authority Data Collaboration Laboratory (HADCL) from 2000 to 2020. Cox proportional hazards regression, survival tree, LASSO Cox regression, boosting, and random survival forest (RSF) were utilized to develop predictive models for survival. Key risk factors were identified through Shapley Additive Explanations analysis, whereas the AutoScore-Survival package facilitated the development of a risk scoring system.

Results

This cohort study included 2047 uterine cancer patients with T2D. The average survival time was 100.82 (standard deviation: 72.75) months. The RSF model demonstrated the strongest predictive performance, achieving a time-dependent area under the curve (AUC) of 0.823 and a C-index of 0.90. A risk scoring system was created based on several criteria: age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium level, low-density lipoprotein cholesterol level (LDL-C) level, body mass index (BMI), and triglycerides level. This scoring system classified 31.4% of patients as high-risk, resulting in a 5-year survival probability of 43.5%, about 1.7 times lower than that of the low-risk group.

Conclusion

This study leveraged machine learning to identify key survival predictors and develop a clinically interpretable risk scoring system for uterine cancer patients with T2D. Key predictors, including age at cancer diagnosis, duration of T2D, creatinine levels, serum potassium levels, LDL-C levels, BMI, and triglycerides levels, effectively stratified survival risk. These findings demonstrate the potential of data-driven models to enhance individualized prediction and inform targeted clinical management.

Abstract Image

查看原文本刊更多论文

机器学习-子宫癌合并2型糖尿病患者生存预测模型：一项区域性队列研究。

目的：本研究旨在建立子宫癌合并2型糖尿病（T2D）患者的预测模型和风险评分系统，以识别影响其生存的危险因素，并估计其生存概率。方法：数据收集自香港医院管理局数据协作实验室（HADCL） 2000年至2020年的数据。采用Cox比例风险回归、生存树、LASSO Cox回归、boosting和随机生存森林（RSF）建立生存预测模型。通过Shapley加性解释分析确定关键风险因素，而AutoScore-Survival包促进了风险评分系统的开发。结果：本队列研究纳入2047例子宫癌合并T2D患者。平均生存时间为100.82个月（标准差为72.75）。RSF模型的预测效果最好，曲线下面积（AUC）随时间变化为0.823，c指数为0.90。基于以下几个标准创建了一个风险评分系统：癌症诊断时的年龄、T2D持续时间、肌酐水平、血清钾水平、低密度脂蛋白胆固醇水平（LDL-C）水平、体重指数（BMI）和甘油三酯水平。该评分系统将31.4%的患者归为高危组，5年生存率为43.5%，比低危组低约1.7倍。结论：本研究利用机器学习识别关键的生存预测因素，并为子宫癌合并T2D患者开发临床可解释的风险评分系统。关键预测指标，包括癌症诊断年龄、t2dm持续时间、肌酐水平、血清钾水平、LDL-C水平、BMI和甘油三酯水平，可有效分层生存风险。这些发现证明了数据驱动模型在增强个性化预测和有针对性的临床管理方面的潜力。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Obstetrics and Gynaecology Research 医学-妇产科学

CiteScore

3.10

自引率

0.00%

发文量

376

审稿时长

3-6 weeks

期刊介绍： The Journal of Obstetrics and Gynaecology Research is the official Journal of the Asia and Oceania Federation of Obstetrics and Gynecology and of the Japan Society of Obstetrics and Gynecology, and aims to provide a medium for the publication of articles in the fields of obstetrics and gynecology. The Journal publishes original research articles, case reports, review articles and letters to the editor. The Journal will give publication priority to original research articles over case reports. Accepted papers become the exclusive licence of the Journal. Manuscripts are peer reviewed by at least two referees and/or Associate Editors expert in the field of the submitted paper.