{"title":"基于机器学习算法回顾性研究的盆腔器官脱垂风险评估模型的建立与验证。","authors":"Ling Mei, Linbo Gao, Tao Wang, Dong Yang, Weixing Chen, Xiaoyu Niu","doi":"10.1007/s00192-025-06046-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction and hypothesis: </strong>We aimed to develop and validate a clinically applicable risk assessment model for identifying women at a high risk of pelvic organ prolapse (POP) based on a retrospective practice.</p><p><strong>Methods: </strong>This study enrolled patients with and without POP between January 2019 and December 2021. Clinical data were collected and machine learning models were applied, such as multilayer perceptron, logistic regression, random forest (RF), light gradient boosting machine and extreme gradient boosting. Two datasets were constructed, one comprising all variables and the other excluding physical examination variables. Two versions of the machine learning model were developed. One was for professional doctors, and the other was for community-health providers. The area under the curve (AUC) and its confidence interval (CI), accuracy, F1 score, sensitivity, and specificity were calculated to evaluate the model's performance. The Shapley Additive Explanations method was used to visualize and interpret the model output.</p><p><strong>Results: </strong>A total of 16,416 women were recruited, with 8,314 and 8,102 in the POP and non-POP groups respectively. Eighty-seven variables were recorded. Among all candidate models, the RF model with 13 variables showed the best performance, with an AUC of 0.806 (95% CI 0.793-0.817), accuracy of 0.723, F1 of 0.731, sensitivity of 0.742, and specificity of 0.703. Excluding the physical examination variables, the RF model with 11 variables showed an AUC, accuracy, F1 score, sensitivity, and specificity of 0.716, 0.652, 0.688, 0.757, and 0.545 respectively.</p><p><strong>Conclusions: </strong>We constructed a clinically applicable risk warning system that will help clinicians to identify women at a high risk of POP.</p>","PeriodicalId":14355,"journal":{"name":"International Urogynecology Journal","volume":" ","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Development and Validation of Risk Assessment Model for Pelvic Organ Prolapse Based on A Retrospective Study with Machine Learning Algorithms.\",\"authors\":\"Ling Mei, Linbo Gao, Tao Wang, Dong Yang, Weixing Chen, Xiaoyu Niu\",\"doi\":\"10.1007/s00192-025-06046-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction and hypothesis: </strong>We aimed to develop and validate a clinically applicable risk assessment model for identifying women at a high risk of pelvic organ prolapse (POP) based on a retrospective practice.</p><p><strong>Methods: </strong>This study enrolled patients with and without POP between January 2019 and December 2021. Clinical data were collected and machine learning models were applied, such as multilayer perceptron, logistic regression, random forest (RF), light gradient boosting machine and extreme gradient boosting. Two datasets were constructed, one comprising all variables and the other excluding physical examination variables. Two versions of the machine learning model were developed. One was for professional doctors, and the other was for community-health providers. The area under the curve (AUC) and its confidence interval (CI), accuracy, F1 score, sensitivity, and specificity were calculated to evaluate the model's performance. The Shapley Additive Explanations method was used to visualize and interpret the model output.</p><p><strong>Results: </strong>A total of 16,416 women were recruited, with 8,314 and 8,102 in the POP and non-POP groups respectively. Eighty-seven variables were recorded. Among all candidate models, the RF model with 13 variables showed the best performance, with an AUC of 0.806 (95% CI 0.793-0.817), accuracy of 0.723, F1 of 0.731, sensitivity of 0.742, and specificity of 0.703. Excluding the physical examination variables, the RF model with 11 variables showed an AUC, accuracy, F1 score, sensitivity, and specificity of 0.716, 0.652, 0.688, 0.757, and 0.545 respectively.</p><p><strong>Conclusions: </strong>We constructed a clinically applicable risk warning system that will help clinicians to identify women at a high risk of POP.</p>\",\"PeriodicalId\":14355,\"journal\":{\"name\":\"International Urogynecology Journal\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2025-02-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Urogynecology Journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s00192-025-06046-9\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"OBSTETRICS & GYNECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Urogynecology Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s00192-025-06046-9","RegionNum":3,"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
摘要
前言和假设:我们的目的是建立和验证一个临床适用的风险评估模型,以识别盆腔器官脱垂(POP)的高风险女性。方法:本研究招募了2019年1月至2021年12月期间患有和不患有POP的患者。收集临床数据,应用多层感知器、逻辑回归、随机森林(RF)、光梯度增强机和极端梯度增强等机器学习模型。构建了两个数据集,一个包含所有变量,另一个不包括体检变量。开发了两个版本的机器学习模型。一个是针对专业医生的,另一个是针对社区卫生服务提供者的。计算曲线下面积(AUC)及其置信区间(CI)、准确性、F1评分、敏感性和特异性来评价模型的性能。Shapley加性解释方法用于可视化和解释模型输出。结果:共招募了16416名女性,其中POP组8314名,非POP组8102名。记录了87个变量。在所有候选模型中,包含13个变量的RF模型表现最佳,AUC为0.806 (95% CI 0.793 ~ 0.817),准确率为0.723,F1为0.731,敏感性为0.742,特异性为0.703。剔除体检变量后,包含11个变量的RF模型AUC、准确率、F1评分、敏感性和特异性分别为0.716、0.652、0.688、0.757和0.545。结论:我们构建了一个临床适用的风险预警系统,可以帮助临床医生识别POP的高危女性。
Development and Validation of Risk Assessment Model for Pelvic Organ Prolapse Based on A Retrospective Study with Machine Learning Algorithms.
Introduction and hypothesis: We aimed to develop and validate a clinically applicable risk assessment model for identifying women at a high risk of pelvic organ prolapse (POP) based on a retrospective practice.
Methods: This study enrolled patients with and without POP between January 2019 and December 2021. Clinical data were collected and machine learning models were applied, such as multilayer perceptron, logistic regression, random forest (RF), light gradient boosting machine and extreme gradient boosting. Two datasets were constructed, one comprising all variables and the other excluding physical examination variables. Two versions of the machine learning model were developed. One was for professional doctors, and the other was for community-health providers. The area under the curve (AUC) and its confidence interval (CI), accuracy, F1 score, sensitivity, and specificity were calculated to evaluate the model's performance. The Shapley Additive Explanations method was used to visualize and interpret the model output.
Results: A total of 16,416 women were recruited, with 8,314 and 8,102 in the POP and non-POP groups respectively. Eighty-seven variables were recorded. Among all candidate models, the RF model with 13 variables showed the best performance, with an AUC of 0.806 (95% CI 0.793-0.817), accuracy of 0.723, F1 of 0.731, sensitivity of 0.742, and specificity of 0.703. Excluding the physical examination variables, the RF model with 11 variables showed an AUC, accuracy, F1 score, sensitivity, and specificity of 0.716, 0.652, 0.688, 0.757, and 0.545 respectively.
Conclusions: We constructed a clinically applicable risk warning system that will help clinicians to identify women at a high risk of POP.
期刊介绍:
The International Urogynecology Journal is the official journal of the International Urogynecological Association (IUGA).The International Urogynecology Journal has evolved in response to a perceived need amongst the clinicians, scientists, and researchers active in the field of urogynecology and pelvic floor disorders. Gynecologists, urologists, physiotherapists, nurses and basic scientists require regular means of communication within this field of pelvic floor dysfunction to express new ideas and research, and to review clinical practice in the diagnosis and treatment of women with disorders of the pelvic floor. This Journal has adopted the peer review process for all original contributions and will maintain high standards with regard to the research published therein. The clinical approach to urogynecology and pelvic floor disorders will be emphasized with each issue containing clinically relevant material that will be immediately applicable for clinical medicine. This publication covers all aspects of the field in an interdisciplinary fashion