A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery
{"title":"A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery","authors":"","doi":"10.1016/j.amjsurg.2024.115912","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Delayed clinically important postoperative nausea and vomiting (CIPONV) could lead to significant consequences following surgery. We aimed to develop a prediction model for it using machine learning algorithms utilizing perioperative data from patients undergoing laparoscopic gastrointestinal surgery.</p></div><div><h3>Methods</h3><p>All 1154 patients in the FDP-PONV trial were enrolled. The optimal features for model development were selected by least absolute shrinkage and selection operator and stepwise regression from 81 perioperative variables. The machine learning algorithm with the best area under the receiver operating characteristic curve (ROCAUC) was determined and assessed. The interpretation of the prediction model was performed by the SHapley Additive Explanations library.</p></div><div><h3>Results</h3><p>Six important predictors were identified. The random forest model showed the best performance in predicting delayed CIPONV, achieving an ROCAUC of 0.737 in the validation cohort.</p></div><div><h3>Conclusion</h3><p>This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.</p></div>","PeriodicalId":7771,"journal":{"name":"American journal of surgery","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0002961024004641/pdfft?md5=d0a527ddb5319445771bba1fd6ab07d7&pid=1-s2.0-S0002961024004641-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of surgery","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0002961024004641","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SURGERY","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Delayed clinically important postoperative nausea and vomiting (CIPONV) could lead to significant consequences following surgery. We aimed to develop a prediction model for it using machine learning algorithms utilizing perioperative data from patients undergoing laparoscopic gastrointestinal surgery.
Methods
All 1154 patients in the FDP-PONV trial were enrolled. The optimal features for model development were selected by least absolute shrinkage and selection operator and stepwise regression from 81 perioperative variables. The machine learning algorithm with the best area under the receiver operating characteristic curve (ROCAUC) was determined and assessed. The interpretation of the prediction model was performed by the SHapley Additive Explanations library.
Results
Six important predictors were identified. The random forest model showed the best performance in predicting delayed CIPONV, achieving an ROCAUC of 0.737 in the validation cohort.
Conclusion
This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.
期刊介绍:
The American Journal of Surgery® is a peer-reviewed journal designed for the general surgeon who performs abdominal, cancer, vascular, head and neck, breast, colorectal, and other forms of surgery. AJS is the official journal of 7 major surgical societies* and publishes their official papers as well as independently submitted clinical studies, editorials, reviews, brief reports, correspondence and book reviews.