利用机器学习预测术后恶心和呕吐:模型开发与验证研究。

IF 2.3 3区 医学 Q2 ANESTHESIOLOGY
Maxim Glebov, Teddy Lazebnik, Maksim Katsin, Boris Orkin, Haim Berkenstadt, Svetlana Bunimovich-Mendrazitsky
{"title":"利用机器学习预测术后恶心和呕吐:模型开发与验证研究。","authors":"Maxim Glebov, Teddy Lazebnik, Maksim Katsin, Boris Orkin, Haim Berkenstadt, Svetlana Bunimovich-Mendrazitsky","doi":"10.1186/s12871-025-02987-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Postoperative nausea and vomiting (PONV) is a frequently observed complication in patients undergoing surgery under general anesthesia. Moreover, it is a frequent cause of distress and dissatisfaction in the early postoperative period. Currently, the classical scores used for predicting PONV have not yielded satisfactory results. Therefore, prognostic models for the prediction of early and delayed PONV were developed in this study to achieve satisfactory predictive performance.</p><p><strong>Methods: </strong>The retrospective data of inpatient adult patients admitted to the post-anesthesia care unit after undergoing surgical procedures under general anesthesia at the Sheba Medical Center, Israel, between September 1, 2018, and September 1, 2023, were used in this study. An ensemble model of machine-learning algorithms trained on the data of 35,003 patients was developed. The k-fold cross-validation method was used followed by splitting the data to train and test sets that optimally preserve the sociodemographic features of the patients.</p><p><strong>Results: </strong>Among the 35,003 patients, early and delayed PONV were observed in 1,340 (3.82%) and 6,582 (18.80%) patients, respectively. The proposed PONV prediction models correctly predicted early and delayed PONV in 83.6% and 74.8% of cases, respectively, outperforming the second-best PONV prediction score (Koivuranta score) by 13.0% and 10.4%, respectively. Feature importance analysis revealed that the performance of the proposed prediction tools aligned with previous clinical knowledge, indicating their utility.</p><p><strong>Conclusions: </strong>The machine learning-based models developed in this study enabled improved PONV prediction, thereby facilitating personalized care and improved patient outcomes.</p>","PeriodicalId":9190,"journal":{"name":"BMC Anesthesiology","volume":"25 1","pages":"135"},"PeriodicalIF":2.3000,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924648/pdf/","citationCount":"0","resultStr":"{\"title\":\"Predicting postoperative nausea and vomiting using machine learning: a model development and validation study.\",\"authors\":\"Maxim Glebov, Teddy Lazebnik, Maksim Katsin, Boris Orkin, Haim Berkenstadt, Svetlana Bunimovich-Mendrazitsky\",\"doi\":\"10.1186/s12871-025-02987-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Postoperative nausea and vomiting (PONV) is a frequently observed complication in patients undergoing surgery under general anesthesia. Moreover, it is a frequent cause of distress and dissatisfaction in the early postoperative period. Currently, the classical scores used for predicting PONV have not yielded satisfactory results. Therefore, prognostic models for the prediction of early and delayed PONV were developed in this study to achieve satisfactory predictive performance.</p><p><strong>Methods: </strong>The retrospective data of inpatient adult patients admitted to the post-anesthesia care unit after undergoing surgical procedures under general anesthesia at the Sheba Medical Center, Israel, between September 1, 2018, and September 1, 2023, were used in this study. An ensemble model of machine-learning algorithms trained on the data of 35,003 patients was developed. The k-fold cross-validation method was used followed by splitting the data to train and test sets that optimally preserve the sociodemographic features of the patients.</p><p><strong>Results: </strong>Among the 35,003 patients, early and delayed PONV were observed in 1,340 (3.82%) and 6,582 (18.80%) patients, respectively. The proposed PONV prediction models correctly predicted early and delayed PONV in 83.6% and 74.8% of cases, respectively, outperforming the second-best PONV prediction score (Koivuranta score) by 13.0% and 10.4%, respectively. Feature importance analysis revealed that the performance of the proposed prediction tools aligned with previous clinical knowledge, indicating their utility.</p><p><strong>Conclusions: </strong>The machine learning-based models developed in this study enabled improved PONV prediction, thereby facilitating personalized care and improved patient outcomes.</p>\",\"PeriodicalId\":9190,\"journal\":{\"name\":\"BMC Anesthesiology\",\"volume\":\"25 1\",\"pages\":\"135\"},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2025-03-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924648/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BMC Anesthesiology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s12871-025-02987-2\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ANESTHESIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Anesthesiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s12871-025-02987-2","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ANESTHESIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

本文章由计算机程序翻译,如有差异,请以英文原文为准。
Predicting postoperative nausea and vomiting using machine learning: a model development and validation study.

Background: Postoperative nausea and vomiting (PONV) is a frequently observed complication in patients undergoing surgery under general anesthesia. Moreover, it is a frequent cause of distress and dissatisfaction in the early postoperative period. Currently, the classical scores used for predicting PONV have not yielded satisfactory results. Therefore, prognostic models for the prediction of early and delayed PONV were developed in this study to achieve satisfactory predictive performance.

Methods: The retrospective data of inpatient adult patients admitted to the post-anesthesia care unit after undergoing surgical procedures under general anesthesia at the Sheba Medical Center, Israel, between September 1, 2018, and September 1, 2023, were used in this study. An ensemble model of machine-learning algorithms trained on the data of 35,003 patients was developed. The k-fold cross-validation method was used followed by splitting the data to train and test sets that optimally preserve the sociodemographic features of the patients.

Results: Among the 35,003 patients, early and delayed PONV were observed in 1,340 (3.82%) and 6,582 (18.80%) patients, respectively. The proposed PONV prediction models correctly predicted early and delayed PONV in 83.6% and 74.8% of cases, respectively, outperforming the second-best PONV prediction score (Koivuranta score) by 13.0% and 10.4%, respectively. Feature importance analysis revealed that the performance of the proposed prediction tools aligned with previous clinical knowledge, indicating their utility.

Conclusions: The machine learning-based models developed in this study enabled improved PONV prediction, thereby facilitating personalized care and improved patient outcomes.

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
BMC Anesthesiology
BMC Anesthesiology ANESTHESIOLOGY-
CiteScore
3.50
自引率
4.50%
发文量
349
审稿时长
>12 weeks
期刊介绍: BMC Anesthesiology is an open access, peer-reviewed journal that considers articles on all aspects of anesthesiology, critical care, perioperative care and pain management, including clinical and experimental research into anesthetic mechanisms, administration and efficacy, technology and monitoring, and associated economic issues.
×
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