Outcome prediction for adult mechanically ventilated patients using machine learning models and comparison with conventional statistical methods: a single-centre retrospective study

Author:

Ong Wei Jun Dan1,How Chun Hung2,Chong Woon Hean Keenan1,Khan Faheem Ahmed1,Ngiam Kee Yuan3,Kansal Amit1

Affiliation:

1. Ng Teng Fong General Hospital

2. National University Health System

3. National University of Singapore

Abstract

Abstract In this retrospective single-centre study spanning five years (2016–2021) and involving 2,368 adult Intensive Care Unit (ICU) patients requiring over four hours of mechanical ventilation (MV) in a tertiary care hospital, we investigated the feasibility and accuracy of using machine learning (ML) models in predicting outcomes post-ICU discharge compared to conventional statistical methods (CSM). The study aimed to identify associated risk factors impacting these outcomes. Poor outcomes, defined as ICU readmission, mortality, and prolonged hospital stays, affected 40.2% of the discharged MV patients. The Extreme Gradient Boost (XGBoost) ML model showed superior performance compared to CSM (Area under the receiver operating characteristic curve: 0.693 vs. 0.667; p-value = 0.03). At 95% specificity, XGBoost displayed enhanced sensitivity (30.6% vs. 23.8%) and accuracy (0.706 vs. 0.703) compared to CSM. Risk factors such as Glasgow Coma Score at ICU discharge, GCS best motor score during ICU admission, MV duration, ICU length of stay, and Charlson Comorbidity Index were identified. While both ML and CSM exhibited moderate accuracy, the study suggests ML algorithms have the potential for better predictive capabilities and individual risk factor identification, potentially aiding in the improvement of patient outcomes by identifying high-risk patients requiring closer monitoring. Further validation in larger studies is necessary, but the study underscores the potential for real-time application of ML algorithms developed from the increasing availability of electronic medical records (EMR).

Publisher

Research Square Platform LLC

Reference28 articles.

1. Schneeweiss S. N Engl J Med. 2014;370:2161–3. doi: 10. 1056/NEJMp1401111. Learning from Big Health Care Data.

2. The risk assessment tool for intensive care unit readmission: A systematic review and meta-analysis;Long J;Intensive Crit Care Nurs,2023

3. Machine learning in medicine;Deo RC;Circulation,2015

4. Scoring systems in the intensive care unit: A compendium;Rapsang AG;Indian J Crit Care Med,2014

5. Predicting Intensive Care Unit Readmission with Machine Learning Using Electronic Health Record Data;Rojas JC;Ann Am Thorac Soc,2018

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3