Machine learning-based prediction of respiratory depression during sedation for liposuction

Abstract Procedural sedation is often performed by non-anesthesiologists in various settings and can lead to respiratory depression. A tool that enables early detection of respiratory compromise could not only enhance patient safety during procedural sedation, but also reduce the risk of medical lia...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin-Woo Kim, Jae Hee Woo, Jaewon Seo, Hajin Kim, Sunho Lee, Younchan Park, Jaehyun Ahn, Seonghun Hong, Hye-Min Jeong, Yuncheol Kang
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-04505-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850223839814877184
author Jin-Woo Kim
Jae Hee Woo
Jaewon Seo
Hajin Kim
Sunho Lee
Younchan Park
Jaehyun Ahn
Seonghun Hong
Hye-Min Jeong
Yuncheol Kang
author_facet Jin-Woo Kim
Jae Hee Woo
Jaewon Seo
Hajin Kim
Sunho Lee
Younchan Park
Jaehyun Ahn
Seonghun Hong
Hye-Min Jeong
Yuncheol Kang
author_sort Jin-Woo Kim
collection DOAJ
description Abstract Procedural sedation is often performed by non-anesthesiologists in various settings and can lead to respiratory depression. A tool that enables early detection of respiratory compromise could not only enhance patient safety during procedural sedation, but also reduce the risk of medical liability. In this study, we aimed to develop a machine learning model that integrates detailed body composition data from patients undergoing liposuction to enhance the prediction of respiratory depression during procedural sedation. Features from bioelectrical impedance analysis, 3D body scanning, and manual measurements were extracted and used to train machine learning models. SHAP analysis, an explainable AI approach, was conducted to visually interpret feature importance. The XGBoost model, particularly when incorporating 3D body scanning data, demonstrated superior predictive performance, achieving an AUROC of 0.856 and a sensitivity of 0.805. The main predictors identified were upper abdominal volume, BMI, and age, highlighting the importance of the acquisition of detailed body composition data for assessing respiratory risks during sedation. The developed model effectively predicts the risk of respiratory depression in patients undergoing liposuction, offering a potential for personalized sedation protocols.
format Article
id doaj-art-0800541baae94d86873b099f89042e38
institution OA Journals
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0800541baae94d86873b099f89042e382025-08-20T02:05:48ZengNature PortfolioScientific Reports2045-23222025-06-0115111210.1038/s41598-025-04505-3Machine learning-based prediction of respiratory depression during sedation for liposuctionJin-Woo Kim0Jae Hee Woo1Jaewon Seo2Hajin Kim3Sunho Lee4Younchan Park5Jaehyun Ahn6Seonghun Hong7Hye-Min Jeong8Yuncheol Kang9Department of Oral and Maxillofacial Surgery, College of Medicine, Ewha Womans UniversityDepartment of Anesthesiology and Pain Medicine, College of Medicine, Ewha Womans University365mc Daegu Liposuction Hospital365mc Seoul Liposuction HospitalGlobal 365mc Deajon Liposuction Hospital365mc Busan Liposuction HospitalGlobal 365mc Incheon Liposuction Hospital365mc Busan Liposuction HospitalDepartment of Artificial Intelligence Convergence, Ewha Womans UniversitySchool of Business, Ewha Womans UniversityAbstract Procedural sedation is often performed by non-anesthesiologists in various settings and can lead to respiratory depression. A tool that enables early detection of respiratory compromise could not only enhance patient safety during procedural sedation, but also reduce the risk of medical liability. In this study, we aimed to develop a machine learning model that integrates detailed body composition data from patients undergoing liposuction to enhance the prediction of respiratory depression during procedural sedation. Features from bioelectrical impedance analysis, 3D body scanning, and manual measurements were extracted and used to train machine learning models. SHAP analysis, an explainable AI approach, was conducted to visually interpret feature importance. The XGBoost model, particularly when incorporating 3D body scanning data, demonstrated superior predictive performance, achieving an AUROC of 0.856 and a sensitivity of 0.805. The main predictors identified were upper abdominal volume, BMI, and age, highlighting the importance of the acquisition of detailed body composition data for assessing respiratory risks during sedation. The developed model effectively predicts the risk of respiratory depression in patients undergoing liposuction, offering a potential for personalized sedation protocols.https://doi.org/10.1038/s41598-025-04505-3
spellingShingle Jin-Woo Kim
Jae Hee Woo
Jaewon Seo
Hajin Kim
Sunho Lee
Younchan Park
Jaehyun Ahn
Seonghun Hong
Hye-Min Jeong
Yuncheol Kang
Machine learning-based prediction of respiratory depression during sedation for liposuction
Scientific Reports
title Machine learning-based prediction of respiratory depression during sedation for liposuction
title_full Machine learning-based prediction of respiratory depression during sedation for liposuction
title_fullStr Machine learning-based prediction of respiratory depression during sedation for liposuction
title_full_unstemmed Machine learning-based prediction of respiratory depression during sedation for liposuction
title_short Machine learning-based prediction of respiratory depression during sedation for liposuction
title_sort machine learning based prediction of respiratory depression during sedation for liposuction
url https://doi.org/10.1038/s41598-025-04505-3
work_keys_str_mv AT jinwookim machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT jaeheewoo machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT jaewonseo machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT hajinkim machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT sunholee machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT younchanpark machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT jaehyunahn machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT seonghunhong machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT hyeminjeong machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction
AT yuncheolkang machinelearningbasedpredictionofrespiratorydepressionduringsedationforliposuction