A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery
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 surger...
Gespeichert in:
Veröffentlicht in: | The American journal of surgery 2024-11, Vol.237, p.115912, Article 115912 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | 115912 |
container_title | The American journal of surgery |
container_volume | 237 |
creator | Zheng, Zhinan Huang, Yabin Zhao, Yingyin Shi, Jiankun Zhang, Shimin Zhao, Yang |
description | 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.
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.
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.
This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.
•Delayed clinically important PONV is linked to predisposing and precipitating factors.•The prediction model for delayed clinically important PONV was developed.•The model included six simple variables and was visualized by SHAP. |
doi_str_mv | 10.1016/j.amjsurg.2024.115912 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3097149647</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0002961024004641</els_id><sourcerecordid>3097149647</sourcerecordid><originalsourceid>FETCH-LOGICAL-c318t-2ab3809f4f022ac453a672b4a5ee4f8a0742ce6b09f8e71c5b3f20f657850e723</originalsourceid><addsrcrecordid>eNqFkcuO1DAQRS0EYpqBTwBZYsMmje28nBUajYaHNBIbWFsVp5J2cOxgOy31d_GDuNUNCzasSrbPva6qS8hrzvac8eb9vIdljluY9oKJas953XHxhOy4bLuCS1k-JTvGmCi6hrMb8iLGOR85r8rn5KbsuBRCNjvy644uoA_GIbUIwRk3FT1EHOgacDA6Ge_o4ge0dPSB5gqn_KitcUaDtSdqltWHBC7R1cfkVwyQzBGpgy0iUHADPfrFpOxMjaMHMx2KYOIPumYOXYp0cwOGyZ8BCysEH7VfjaYTxBTydcKY1WDpeVwMp5fk2Qg24qtrvSXfPz58u_9cPH799OX-7rHQJZepENCXknVjNTIhQFd1CU0r-gpqxGqUwNpKaGz6jEhsua77chRsbOpW1gxbUd6SdxffNfifW25CLSZqtBYc-i2qknUtr7qmajP69h909lvIPWeKZ0y2tWgyVV8onWeMAUe1BrNAOCnO1DlVNatrquqcqrqkmnVvru5bv-DwV_Unxgx8uACY13E0GFTUebc6JxhQJzV4858vfgO1Crsq</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3109787526</pqid></control><display><type>article</type><title>A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Zheng, Zhinan ; Huang, Yabin ; Zhao, Yingyin ; Shi, Jiankun ; Zhang, Shimin ; Zhao, Yang</creator><creatorcontrib>Zheng, Zhinan ; Huang, Yabin ; Zhao, Yingyin ; Shi, Jiankun ; Zhang, Shimin ; Zhao, Yang</creatorcontrib><description>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.
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.
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.
This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.
•Delayed clinically important PONV is linked to predisposing and precipitating factors.•The prediction model for delayed clinically important PONV was developed.•The model included six simple variables and was visualized by SHAP.</description><identifier>ISSN: 0002-9610</identifier><identifier>ISSN: 1879-1883</identifier><identifier>EISSN: 1879-1883</identifier><identifier>DOI: 10.1016/j.amjsurg.2024.115912</identifier><identifier>PMID: 39182286</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>Adult ; Aged ; Algorithms ; Artificial intelligence ; Datasets ; Delayed clinically important postoperative nausea and vomiting ; Digestive System Surgical Procedures - adverse effects ; Female ; Gastrointestinal surgery ; Humans ; Laparoscopy ; Laparoscopy - adverse effects ; Learning algorithms ; Machine Learning ; Male ; Middle Aged ; Missing data ; Nausea ; Patients ; Performance evaluation ; Performance prediction ; Postoperative nausea and vomiting ; Postoperative Nausea and Vomiting - epidemiology ; Postoperative Nausea and Vomiting - prevention & control ; Prediction model ; Prediction models ; Predictor ; Regression models ; Risk ; Risk Assessment - methods ; Risk Factors ; Risk groups ; ROC Curve ; Surgery ; Variables ; Vomiting</subject><ispartof>The American journal of surgery, 2024-11, Vol.237, p.115912, Article 115912</ispartof><rights>2024 The Authors</rights><rights>Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.</rights><rights>2024. The Authors</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c318t-2ab3809f4f022ac453a672b4a5ee4f8a0742ce6b09f8e71c5b3f20f657850e723</cites><orcidid>0000-0002-5603-9735 ; 0009-0004-0616-314X ; 0009-0001-0031-0864</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S0002961024004641$$EHTML$$P50$$Gelsevier$$Hfree_for_read</linktohtml><link.rule.ids>314,776,780,3537,27903,27904,65309</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39182286$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zheng, Zhinan</creatorcontrib><creatorcontrib>Huang, Yabin</creatorcontrib><creatorcontrib>Zhao, Yingyin</creatorcontrib><creatorcontrib>Shi, Jiankun</creatorcontrib><creatorcontrib>Zhang, Shimin</creatorcontrib><creatorcontrib>Zhao, Yang</creatorcontrib><title>A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery</title><title>The American journal of surgery</title><addtitle>Am J Surg</addtitle><description>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.
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.
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.
This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.
•Delayed clinically important PONV is linked to predisposing and precipitating factors.•The prediction model for delayed clinically important PONV was developed.•The model included six simple variables and was visualized by SHAP.</description><subject>Adult</subject><subject>Aged</subject><subject>Algorithms</subject><subject>Artificial intelligence</subject><subject>Datasets</subject><subject>Delayed clinically important postoperative nausea and vomiting</subject><subject>Digestive System Surgical Procedures - adverse effects</subject><subject>Female</subject><subject>Gastrointestinal surgery</subject><subject>Humans</subject><subject>Laparoscopy</subject><subject>Laparoscopy - adverse effects</subject><subject>Learning algorithms</subject><subject>Machine Learning</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Missing data</subject><subject>Nausea</subject><subject>Patients</subject><subject>Performance evaluation</subject><subject>Performance prediction</subject><subject>Postoperative nausea and vomiting</subject><subject>Postoperative Nausea and Vomiting - epidemiology</subject><subject>Postoperative Nausea and Vomiting - prevention & control</subject><subject>Prediction model</subject><subject>Prediction models</subject><subject>Predictor</subject><subject>Regression models</subject><subject>Risk</subject><subject>Risk Assessment - methods</subject><subject>Risk Factors</subject><subject>Risk groups</subject><subject>ROC Curve</subject><subject>Surgery</subject><subject>Variables</subject><subject>Vomiting</subject><issn>0002-9610</issn><issn>1879-1883</issn><issn>1879-1883</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><sourceid>8G5</sourceid><sourceid>BENPR</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><recordid>eNqFkcuO1DAQRS0EYpqBTwBZYsMmje28nBUajYaHNBIbWFsVp5J2cOxgOy31d_GDuNUNCzasSrbPva6qS8hrzvac8eb9vIdljluY9oKJas953XHxhOy4bLuCS1k-JTvGmCi6hrMb8iLGOR85r8rn5KbsuBRCNjvy644uoA_GIbUIwRk3FT1EHOgacDA6Ge_o4ge0dPSB5gqn_KitcUaDtSdqltWHBC7R1cfkVwyQzBGpgy0iUHADPfrFpOxMjaMHMx2KYOIPumYOXYp0cwOGyZ8BCysEH7VfjaYTxBTydcKY1WDpeVwMp5fk2Qg24qtrvSXfPz58u_9cPH799OX-7rHQJZepENCXknVjNTIhQFd1CU0r-gpqxGqUwNpKaGz6jEhsua77chRsbOpW1gxbUd6SdxffNfifW25CLSZqtBYc-i2qknUtr7qmajP69h909lvIPWeKZ0y2tWgyVV8onWeMAUe1BrNAOCnO1DlVNatrquqcqrqkmnVvru5bv-DwV_Unxgx8uACY13E0GFTUebc6JxhQJzV4858vfgO1Crsq</recordid><startdate>202411</startdate><enddate>202411</enddate><creator>Zheng, Zhinan</creator><creator>Huang, Yabin</creator><creator>Zhao, Yingyin</creator><creator>Shi, Jiankun</creator><creator>Zhang, Shimin</creator><creator>Zhao, Yang</creator><general>Elsevier Inc</general><general>Elsevier Limited</general><scope>6I.</scope><scope>AAFTH</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7QO</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FD</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>M2O</scope><scope>MBDVC</scope><scope>P64</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0002-5603-9735</orcidid><orcidid>https://orcid.org/0009-0004-0616-314X</orcidid><orcidid>https://orcid.org/0009-0001-0031-0864</orcidid></search><sort><creationdate>202411</creationdate><title>A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery</title><author>Zheng, Zhinan ; Huang, Yabin ; Zhao, Yingyin ; Shi, Jiankun ; Zhang, Shimin ; Zhao, Yang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c318t-2ab3809f4f022ac453a672b4a5ee4f8a0742ce6b09f8e71c5b3f20f657850e723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Algorithms</topic><topic>Artificial intelligence</topic><topic>Datasets</topic><topic>Delayed clinically important postoperative nausea and vomiting</topic><topic>Digestive System Surgical Procedures - adverse effects</topic><topic>Female</topic><topic>Gastrointestinal surgery</topic><topic>Humans</topic><topic>Laparoscopy</topic><topic>Laparoscopy - adverse effects</topic><topic>Learning algorithms</topic><topic>Machine Learning</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Missing data</topic><topic>Nausea</topic><topic>Patients</topic><topic>Performance evaluation</topic><topic>Performance prediction</topic><topic>Postoperative nausea and vomiting</topic><topic>Postoperative Nausea and Vomiting - epidemiology</topic><topic>Postoperative Nausea and Vomiting - prevention & control</topic><topic>Prediction model</topic><topic>Prediction models</topic><topic>Predictor</topic><topic>Regression models</topic><topic>Risk</topic><topic>Risk Assessment - methods</topic><topic>Risk Factors</topic><topic>Risk groups</topic><topic>ROC Curve</topic><topic>Surgery</topic><topic>Variables</topic><topic>Vomiting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Zhinan</creatorcontrib><creatorcontrib>Huang, Yabin</creatorcontrib><creatorcontrib>Zhao, Yingyin</creatorcontrib><creatorcontrib>Shi, Jiankun</creatorcontrib><creatorcontrib>Zhang, Shimin</creatorcontrib><creatorcontrib>Zhao, Yang</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Biotechnology Research Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Research Library</collection><collection>Research Library (Corporate)</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><jtitle>The American journal of surgery</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zheng, Zhinan</au><au>Huang, Yabin</au><au>Zhao, Yingyin</au><au>Shi, Jiankun</au><au>Zhang, Shimin</au><au>Zhao, Yang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery</atitle><jtitle>The American journal of surgery</jtitle><addtitle>Am J Surg</addtitle><date>2024-11</date><risdate>2024</risdate><volume>237</volume><spage>115912</spage><pages>115912-</pages><artnum>115912</artnum><issn>0002-9610</issn><issn>1879-1883</issn><eissn>1879-1883</eissn><abstract>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.
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.
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.
This study developed an interpretable model predicting personalized risk for delayed CIPONV, aiding high-risk patient identification and prevention strategies.
•Delayed clinically important PONV is linked to predisposing and precipitating factors.•The prediction model for delayed clinically important PONV was developed.•The model included six simple variables and was visualized by SHAP.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><pmid>39182286</pmid><doi>10.1016/j.amjsurg.2024.115912</doi><orcidid>https://orcid.org/0000-0002-5603-9735</orcidid><orcidid>https://orcid.org/0009-0004-0616-314X</orcidid><orcidid>https://orcid.org/0009-0001-0031-0864</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0002-9610 |
ispartof | The American journal of surgery, 2024-11, Vol.237, p.115912, Article 115912 |
issn | 0002-9610 1879-1883 1879-1883 |
language | eng |
recordid | cdi_proquest_miscellaneous_3097149647 |
source | MEDLINE; Elsevier ScienceDirect Journals |
subjects | Adult Aged Algorithms Artificial intelligence Datasets Delayed clinically important postoperative nausea and vomiting Digestive System Surgical Procedures - adverse effects Female Gastrointestinal surgery Humans Laparoscopy Laparoscopy - adverse effects Learning algorithms Machine Learning Male Middle Aged Missing data Nausea Patients Performance evaluation Performance prediction Postoperative nausea and vomiting Postoperative Nausea and Vomiting - epidemiology Postoperative Nausea and Vomiting - prevention & control Prediction model Prediction models Predictor Regression models Risk Risk Assessment - methods Risk Factors Risk groups ROC Curve Surgery Variables Vomiting |
title | A machine learning-based prediction model for delayed clinically important postoperative nausea and vomiting in high-risk patients undergoing laparoscopic gastrointestinal surgery |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T00%3A40%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20machine%20learning-based%20prediction%20model%20for%20delayed%20clinically%20important%20postoperative%20nausea%20and%20vomiting%20in%20high-risk%20patients%20undergoing%20laparoscopic%20gastrointestinal%20surgery&rft.jtitle=The%20American%20journal%20of%20surgery&rft.au=Zheng,%20Zhinan&rft.date=2024-11&rft.volume=237&rft.spage=115912&rft.pages=115912-&rft.artnum=115912&rft.issn=0002-9610&rft.eissn=1879-1883&rft_id=info:doi/10.1016/j.amjsurg.2024.115912&rft_dat=%3Cproquest_cross%3E3097149647%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3109787526&rft_id=info:pmid/39182286&rft_els_id=S0002961024004641&rfr_iscdi=true |