子痫前期预测中的机器学习算法与经典回归模型:系统综述。

IF 3.9 2区 医学 Q1 PERIPHERAL VASCULAR DISEASE
Current Hypertension Reports Pub Date : 2024-07-01 Epub Date: 2024-05-28 DOI:10.1007/s11906-024-01297-1
Sofonyas Abebaw Tiruneh, Tra Thuan Thanh Vu, Daniel Lorber Rolnik, Helena J Teede, Joanne Enticott
{"title":"子痫前期预测中的机器学习算法与经典回归模型:系统综述。","authors":"Sofonyas Abebaw Tiruneh, Tra Thuan Thanh Vu, Daniel Lorber Rolnik, Helena J Teede, Joanne Enticott","doi":"10.1007/s11906-024-01297-1","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose of review: </strong>Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.</p><p><strong>Recent findings: </strong>From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.</p>","PeriodicalId":10963,"journal":{"name":"Current Hypertension Reports","volume":" ","pages":"309-323"},"PeriodicalIF":3.9000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11199280/pdf/","citationCount":"0","resultStr":"{\"title\":\"Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review.\",\"authors\":\"Sofonyas Abebaw Tiruneh, Tra Thuan Thanh Vu, Daniel Lorber Rolnik, Helena J Teede, Joanne Enticott\",\"doi\":\"10.1007/s11906-024-01297-1\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose of review: </strong>Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.</p><p><strong>Recent findings: </strong>From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.</p>\",\"PeriodicalId\":10963,\"journal\":{\"name\":\"Current Hypertension Reports\",\"volume\":\" \",\"pages\":\"309-323\"},\"PeriodicalIF\":3.9000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11199280/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Current Hypertension Reports\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s11906-024-01297-1\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/28 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"PERIPHERAL VASCULAR DISEASE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current Hypertension Reports","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11906-024-01297-1","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/28 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"PERIPHERAL VASCULAR DISEASE","Score":null,"Total":0}
引用次数: 0

摘要

综述目的:机器学习(ML)方法是医疗风险预测的一种新兴替代方法。我们旨在综合有关探索潜在预后因素的 ML 和经典回归研究的文献,并比较先兆子痫的预测性能:在检索到的 9382 项研究中,有 82 项被纳入。其中 66 篇出版物专门报告了 84 个经典回归模型,用于预测子痫前期的不同发病时间。另有 6 篇文献报道了纯粹的 ML 算法,另有 10 篇文献报道了同一样本中的 ML 算法和经典回归模型,其中 8 篇的结果显示 ML 算法优于经典回归模型。最常见的预后因素包括年龄、孕前体重指数、慢性疾病、胎次、子痫前期病史、平均动脉压、子宫动脉搏动指数、胎盘生长因子和妊娠相关血浆蛋白 A。与神经网络相比,竞争风险模型具有相似的性能(AUC = 0.92,95% CI 0.91-0.92)。大多数论文未报告校准性能。在子痫前期预测方面,ML 算法的性能优于传统回归模型。随机森林和增强型算法的预测效果最好。进一步的研究应侧重于使用相同的样本和评估指标将 ML 算法与经典回归模型进行比较,以深入了解其性能。有必要对 ML 算法进行外部验证,以深入了解其通用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review.

Machine Learning Algorithms Versus Classical Regression Models in Pre-Eclampsia Prediction: A Systematic Review.

Purpose of review: Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthesise the literature on ML and classical regression studies exploring potential prognostic factors and to compare prediction performance for pre-eclampsia.

Recent findings: From 9382 studies retrieved, 82 were included. Sixty-six publications exclusively reported eighty-four classical regression models to predict variable timing of onset of pre-eclampsia. Another six publications reported purely ML algorithms, whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre-pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placental growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 95% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Calibration performance was not reported in the majority of publications. ML algorithms had better performance compared to classical regression models in pre-eclampsia prediction. Random forest and boosting-type algorithms had the best prediction performance. Further research should focus on comparing ML algorithms to classical regression models using the same samples and evaluation metrics to gain insight into their performance. External validation of ML algorithms is warranted to gain insights into their generalisability.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Current Hypertension Reports
Current Hypertension Reports 医学-外周血管病
CiteScore
10.50
自引率
0.00%
发文量
65
审稿时长
6-12 weeks
期刊介绍: This journal intends to provide clear, insightful, balanced contributions by international experts that review the most important, recently published clinical findings related to the diagnosis, treatment, management, and prevention of hypertension. We accomplish this aim by appointing international authorities to serve as Section Editors in key subject areas, such as antihypertensive therapies, associated metabolic disorders, and therapeutic trials. Section Editors, in turn, select topics for which leading experts contribute comprehensive review articles that emphasize new developments and recently published papers of major importance, highlighted by annotated reference lists. An international Editorial Board reviews the annual table of contents, suggests articles of special interest to their country/region, and ensures that topics are current and include emerging research. Commentaries from well-known figures in the field are also provided.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信