Cardio-Respiratory Engineering and Technology Laboratory, Department of Mechanical and Aerospace Engineering, Monash University, Melbourne, Australia.
Lab 2, Level 2, Victorian Heart Hospital, 631 Blackburn Road, Melbourne, 3800, Australia.
Intensive Care Med. 2023 Sep;49(9):1090-1099. doi: 10.1007/s00134-023-07157-x. Epub 2023 Aug 7.
Venoarterial extracorporeal membrane oxygenation (VA-ECMO) is a complex and high-risk life support modality used in severe cardiorespiratory failure. ECMO survival scores are used clinically for patient prognostication and outcomes risk adjustment. This study aims to create the first artificial intelligence (AI)-driven ECMO survival score to predict in-hospital mortality based on a large international patient cohort.
A deep neural network, ECMO Predictive Algorithm (ECMO PAL) was trained on a retrospective cohort of 18,167 patients from the international Extracorporeal Life Support Organisation (ELSO) registry (2017-2020), and performance was measured using fivefold cross-validation. External validation was performed on all adult registry patients from 2021 (N = 5015) and compared against existing prognostication scores: SAVE, Modified SAVE, and ECMO ACCEPTS for predicting in-hospital mortality.
Mean age was 56.8 ± 15.1 years, with 66.7% of patients being male and 50.2% having a pre-ECMO cardiac arrest. Cross-validation demonstrated an inhospital mortality sensitivity and precision of 82.1 ± 0.2% and 77.6 ± 0.2%, respectively. Validation accuracy was only 2.8% lower than training accuracy, reducing from 75.5% to 72.7% [99% confidence interval (CI) 71.1-74.3%]. ECMO PAL accuracy outperformed the ECMO ACCEPTS (54.7%), SAVE (61.1%), and Modified SAVE (62%) scores.
ECMO PAL is the first AI-powered ECMO survival score trained and validated on large international patient cohorts. ECMO PAL demonstrated high generalisability across ECMO regions and outperformed existing, widely used scores. Beyond ECMO, this study highlights how large international registry data can be leveraged for AI prognostication for complex critical care therapies.
静脉-动脉体外膜肺氧合（VA-ECMO）是一种用于严重心肺衰竭的复杂且高风险的生命支持方式。ECMO 生存评分用于临床患者预后和结果风险调整。本研究旨在创建第一个基于大型国际患者队列的人工智能（AI）驱动的 ECMO 生存评分，以预测院内死亡率。
一种深度神经网络，即 ECMO 预测算法（ECMO PAL），在国际体外生命支持组织（ELSO）注册中心的 18167 例回顾性队列中进行了训练（2017-2020 年），并通过五重交叉验证来衡量其性能。在 2021 年（N=5015）对所有成年登记患者进行了外部验证，并与现有的预后评分进行了比较：SAVE、改良 SAVE 和 ECMO ACCEPTS 用于预测院内死亡率。
平均年龄为 56.8±15.1 岁，66.7%的患者为男性，50.2%的患者在 ECMO 前发生心脏骤停。五重交叉验证显示院内死亡率的敏感性和精度分别为 82.1±0.2%和 77.6±0.2%。验证准确性仅比训练准确性低 2.8%，从 75.5%降至 72.7%（99%置信区间[CI]71.1-74.3%）。ECMO PAL 的准确性优于 ECMO ACCEPTS（54.7%）、SAVE（61.1%）和改良 SAVE（62%）评分。
ECMO PAL 是第一个在大型国际患者队列中进行训练和验证的基于 AI 的 ECMO 生存评分。ECMO PAL 在 ECMO 区域具有很高的通用性，优于现有的广泛使用的评分。超出 ECMO 范围，本研究强调了如何利用大型国际登记数据为复杂的重症监护治疗进行 AI 预后。
