{"title":"Machine Learning-Based First-Day Mortality Prediction for Venoarterial Extracorporeal Membrane Oxygenation: The Novel RESCUE-24 Score.","authors":"Jung-Chi Hsu, Chen-Hsu Pai, Lian-Yu Lin, Chih-Hsien Wang, Ling-Yi Wei, Jeng-Wei Chen, Nai-Hsin Chi, Shu-Chien Huang, Hsi-Yu Yu, Nai-Kuan Chou, Ron-Bin Hsu, Yih-Sharng Chen","doi":"10.1097/MAT.0000000000002395","DOIUrl":null,"url":null,"abstract":"<p><p>Extracorporeal membrane oxygenation (ECMO) provides critical cardiac support, but predicting outcomes remains a challenge. We enrolled 1,748 adult venoarterial (VA)-ECMO patients at the National Taiwan University Hospital between 2010 and 2021. The overall mortality rate was 68.2%. Machine learning with the random survival forest (RSF) model demonstrated superior prediction for in-hospital mortality (area under the curve [AUC]: 0.953, 95% confidence interval (CI): 0.925-0.981), outperforming the Sequential Organ Failure Assessment (SOFA; 0.753 [0.689-0.817]), Acute Physiology and Chronic Health Evaluation (APACHE) II (0.737 [0.672-0.802]), Survival after Venoarterial ECMO (SAVE; 0.624 [0.551-0.697]), ENCOURAGE (0.675 [0.606-0.743]), and Simplified Acute Physiology Score (SAPS) III (0.604 [0.533-0.675]) scores. Failure to achieve 25% clearance at 8 hours and 50% at 16 hours significantly increased mortality risk (HR: 1.65, 95% CI: 1.27-2.14, p < 0.001; HR: 1.25, 95% CI: 1.02-1.54, p = 0.035). Based on the RSF-derived variable importance, the RESCUE-24 Score was developed, assigning points for lactic acid clearance (10 for <50% at 16 hours, 6 for <25% at 8 hours), SvO2 <75% (3 points), oliguria <500 ml (2 points), and age ≥60 years (2 points). Patients were classified into low risk (0-2), medium risk (3-20), and high risk (≥21). The medium- and high-risk groups exhibited significantly higher in-hospital mortality compared with the low-risk group (HR: 1.93 [1.46-2.55] and 5.47 [4.07-7.35], p < 0.002, respectively). Kaplan-Meier analysis confirmed that improved lactic acid clearance at 8 and 16 hours was associated with better survival (log-rank p < 0.001). The three groups of the RESCUE-24 Score also showed significant survival differences (log-rank p < 0.001). In conclusion, machine learning can help identify high-risk populations for tailored management. Achieving optimal lactic acid clearance within 24 hours is crucial for improving survival outcomes.</p>","PeriodicalId":8844,"journal":{"name":"ASAIO Journal","volume":" ","pages":""},"PeriodicalIF":3.1000,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ASAIO Journal","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1097/MAT.0000000000002395","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Extracorporeal membrane oxygenation (ECMO) provides critical cardiac support, but predicting outcomes remains a challenge. We enrolled 1,748 adult venoarterial (VA)-ECMO patients at the National Taiwan University Hospital between 2010 and 2021. The overall mortality rate was 68.2%. Machine learning with the random survival forest (RSF) model demonstrated superior prediction for in-hospital mortality (area under the curve [AUC]: 0.953, 95% confidence interval (CI): 0.925-0.981), outperforming the Sequential Organ Failure Assessment (SOFA; 0.753 [0.689-0.817]), Acute Physiology and Chronic Health Evaluation (APACHE) II (0.737 [0.672-0.802]), Survival after Venoarterial ECMO (SAVE; 0.624 [0.551-0.697]), ENCOURAGE (0.675 [0.606-0.743]), and Simplified Acute Physiology Score (SAPS) III (0.604 [0.533-0.675]) scores. Failure to achieve 25% clearance at 8 hours and 50% at 16 hours significantly increased mortality risk (HR: 1.65, 95% CI: 1.27-2.14, p < 0.001; HR: 1.25, 95% CI: 1.02-1.54, p = 0.035). Based on the RSF-derived variable importance, the RESCUE-24 Score was developed, assigning points for lactic acid clearance (10 for <50% at 16 hours, 6 for <25% at 8 hours), SvO2 <75% (3 points), oliguria <500 ml (2 points), and age ≥60 years (2 points). Patients were classified into low risk (0-2), medium risk (3-20), and high risk (≥21). The medium- and high-risk groups exhibited significantly higher in-hospital mortality compared with the low-risk group (HR: 1.93 [1.46-2.55] and 5.47 [4.07-7.35], p < 0.002, respectively). Kaplan-Meier analysis confirmed that improved lactic acid clearance at 8 and 16 hours was associated with better survival (log-rank p < 0.001). The three groups of the RESCUE-24 Score also showed significant survival differences (log-rank p < 0.001). In conclusion, machine learning can help identify high-risk populations for tailored management. Achieving optimal lactic acid clearance within 24 hours is crucial for improving survival outcomes.
期刊介绍:
ASAIO Journal is in the forefront of artificial organ research and development. On the cutting edge of innovative technology, it features peer-reviewed articles of the highest quality that describe research, development, the most recent advances in the design of artificial organ devices and findings from initial testing. Bimonthly, the ASAIO Journal features state-of-the-art investigations, laboratory and clinical trials, and discussions and opinions from experts around the world.
The official publication of the American Society for Artificial Internal Organs.