Machine learning-based identification of efficient and restrictive physiological subphenotypes in acute respiratory distress syndrome.

IF 2.8 Q2 CRITICAL CARE MEDICINE
Gabriela Meza-Fuentes, Iris Delgado, Mario Barbé, Ignacio Sánchez-Barraza, Mauricio A Retamal, René López
{"title":"Machine learning-based identification of efficient and restrictive physiological subphenotypes in acute respiratory distress syndrome.","authors":"Gabriela Meza-Fuentes, Iris Delgado, Mario Barbé, Ignacio Sánchez-Barraza, Mauricio A Retamal, René López","doi":"10.1186/s40635-025-00737-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Acute respiratory distress syndrome (ARDS) is a severe condition with high morbidity and mortality, characterized by significant clinical heterogeneity. This heterogeneity complicates treatment selection and patient inclusion in clinical trials. Therefore, the objective of this study is to identify physiological subphenotypes of ARDS using machine learning, and to determine ventilatory variables that can effectively discriminate between these subphenotypes in a bedside setting with high performance, highlighting potential utility for future clinical stratification approaches.</p><p><strong>Methodology: </strong>A retrospective cohort study was conducted using data from our ICU, covering admissions from 2017 to 2021. The study included 224 patients over 18 years of age diagnosed with ARDS according to the Berlin criteria and undergoing invasive mechanical ventilation (IMV). Data on physiological and ventilatory variables were collected during the first 24 h IMV. We applied machine learning techniques to categorize subphenotypes in ARDS patients. Initially, we employed the unsupervised Gaussian Mixture Classification Model approach to group patients into subphenotypes. Subsequently, we applied supervised models such as XGBoost to perform root cause analysis, evaluate the classification of patients into these subgroups, and measure their performance.</p><p><strong>Results: </strong>Our models identified two ARDS subphenotypes with significant clinical differences and significant outcomes. Subphenotype Efficient (n = 172) was characterized by lower mortality, lower clinical severity and presented a less restrictive pattern with better gas exchange compared to Subphenotype Restrictive (n = 52), which showed the opposite. The models demonstrated high performance with an area under the ROC curve of 0.94, sensitivity of 94.2% and specificity of 87.5%, in addition to an F1 score of 0.85. The most influential variables in the discrimination of subphenotypes were distension pressure, respiratory frequency and exhaled carbon dioxide volume.</p><p><strong>Conclusion: </strong>This study presents an approach to improve subphenotype categorization in ARDS. The generation of clustering and prediction models by machine learning involving clinical, ventilatory mechanics, and gas exchange variables allowed for more accurate stratification of patients. These findings have the potential to optimize individualized treatment selection and improve clinical outcomes in patients with ARDS.</p>","PeriodicalId":13750,"journal":{"name":"Intensive Care Medicine Experimental","volume":"13 1","pages":"29"},"PeriodicalIF":2.8000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11872963/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intensive Care Medicine Experimental","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1186/s40635-025-00737-9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CRITICAL CARE MEDICINE","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Acute respiratory distress syndrome (ARDS) is a severe condition with high morbidity and mortality, characterized by significant clinical heterogeneity. This heterogeneity complicates treatment selection and patient inclusion in clinical trials. Therefore, the objective of this study is to identify physiological subphenotypes of ARDS using machine learning, and to determine ventilatory variables that can effectively discriminate between these subphenotypes in a bedside setting with high performance, highlighting potential utility for future clinical stratification approaches.

Methodology: A retrospective cohort study was conducted using data from our ICU, covering admissions from 2017 to 2021. The study included 224 patients over 18 years of age diagnosed with ARDS according to the Berlin criteria and undergoing invasive mechanical ventilation (IMV). Data on physiological and ventilatory variables were collected during the first 24 h IMV. We applied machine learning techniques to categorize subphenotypes in ARDS patients. Initially, we employed the unsupervised Gaussian Mixture Classification Model approach to group patients into subphenotypes. Subsequently, we applied supervised models such as XGBoost to perform root cause analysis, evaluate the classification of patients into these subgroups, and measure their performance.

Results: Our models identified two ARDS subphenotypes with significant clinical differences and significant outcomes. Subphenotype Efficient (n = 172) was characterized by lower mortality, lower clinical severity and presented a less restrictive pattern with better gas exchange compared to Subphenotype Restrictive (n = 52), which showed the opposite. The models demonstrated high performance with an area under the ROC curve of 0.94, sensitivity of 94.2% and specificity of 87.5%, in addition to an F1 score of 0.85. The most influential variables in the discrimination of subphenotypes were distension pressure, respiratory frequency and exhaled carbon dioxide volume.

Conclusion: This study presents an approach to improve subphenotype categorization in ARDS. The generation of clustering and prediction models by machine learning involving clinical, ventilatory mechanics, and gas exchange variables allowed for more accurate stratification of patients. These findings have the potential to optimize individualized treatment selection and improve clinical outcomes in patients with ARDS.

Abstract Image

Abstract Image

Abstract Image

基于机器学习识别急性呼吸窘迫综合征中的高效和限制性生理亚型。
简介:急性呼吸窘迫综合征(Acute respiratory distress syndrome, ARDS)是一种高发病率、高死亡率的重症疾病,具有明显的临床异质性。这种异质性使临床试验的治疗选择和患者纳入复杂化。因此,本研究的目的是利用机器学习识别ARDS的生理亚表型,并确定通气变量,以便在床边环境中高效地区分这些亚表型,强调未来临床分层方法的潜在效用。方法:回顾性队列研究使用ICU的数据,涵盖2017年至2021年的入院患者。本研究纳入224例年龄在18岁以上,根据柏林标准诊断为ARDS并接受有创机械通气(IMV)治疗的患者。在IMV的前24小时收集生理和通气变量数据。我们应用机器学习技术对ARDS患者的亚表型进行分类。最初,我们采用无监督高斯混合分类模型方法将患者分组为亚表型。随后,我们应用监督模型(如XGBoost)进行根本原因分析,评估患者在这些亚组中的分类,并衡量他们的表现。结果:我们的模型确定了两种具有显著临床差异和显著预后的ARDS亚表型。与限制性亚表型(n = 52)相比,高效亚表型(n = 172)的特点是死亡率更低,临床严重程度更低,限制性模式更少,气体交换更好,结果相反。模型的ROC曲线下面积为0.94,灵敏度为94.2%,特异性为87.5%,F1评分为0.85。对亚表型区分影响最大的变量是扩张压、呼吸频率和呼出的二氧化碳量。结论:本研究提供了一种改善ARDS亚表型分型的方法。通过机器学习生成的聚类和预测模型涉及临床、通气力学和气体交换变量,可以更准确地对患者进行分层。这些发现有可能优化个体化治疗选择,改善ARDS患者的临床结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Intensive Care Medicine Experimental
Intensive Care Medicine Experimental CRITICAL CARE MEDICINE-
CiteScore
5.10
自引率
2.90%
发文量
48
审稿时长
13 weeks
×
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:604180095
Book学术官方微信