Meza-Fuentes Gabriela, Delgado Iris, Barbé Mario, Sánchez-Barraza Ignacio, Retamal Mauricio A, López René
Instituto de Ciencias e Innovación en Medicina, Facultad de Medicina Clínica Alemana, Universidad del Desarrollo, Santiago, Chile.
Centro de Epidemiología y Políticas de Salud, Facultad de Medicina, Clínica Alemana, Universidad del Desarrollo, Santiago, Chile.
Intensive Care Med Exp. 2025 Mar 1;13(1):29. doi: 10.1186/s40635-025-00737-9.
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.
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.
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.
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.
急性呼吸窘迫综合征（ARDS）是一种发病率和死亡率都很高的严重病症，其临床异质性显著。这种异质性使治疗方案的选择以及患者纳入临床试验变得复杂。因此，本研究的目的是利用机器学习识别ARDS的生理亚表型，并确定在床边环境中能够高效区分这些亚表型的通气变量，突出其对未来临床分层方法的潜在效用。
采用回顾性队列研究，使用我们重症监护病房（ICU）2017年至2021年的入院数据。该研究纳入了224名18岁以上根据柏林标准诊断为ARDS并接受有创机械通气（IMV）的患者。在IMV的最初24小时内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，我们应用如XGBoost等监督模型进行根本原因分析，评估患者归入这些亚组的分类情况，并衡量其性能。
我们的模型识别出两种具有显著临床差异和预后差异的ARDS亚表型。与限制性亚表型（n = 52）相比，高效亚表型（n = 172）的特点是死亡率较低、临床严重程度较低，且呈现出限制较少的模式，气体交换较好，而限制性亚表型则相反。这些模型表现出高性能，ROC曲线下面积为0.94，敏感性为94.2%，特异性为87.5%，F1分数为0.85。区分亚表型最有影响力的变量是膨胀压力、呼吸频率和呼出二氧化碳量。
本研究提出了一种改进ARDS亚表型分类的方法。通过涉及临床、通气力学和气体交换变量的机器学习生成聚类和预测模型，能够对患者进行更准确的分层。这些发现有可能优化个体化治疗选择并改善ARDS患者的临床预后。
