Julian Kreutz, Jonathan Bamberger, Lukas Harbaum, Klevis Mihali, Georgios Chatzis, Nikolaos Patsalis, Mohamed Ben Amar, Styliani Syntila, Martin C Hirsch, Fabian Lechner, Bernhard Schieffer, Birgit Markus
{"title":"评估院外心脏骤停后临时机械循环支持的个性化预测的机器学习模型。","authors":"Julian Kreutz, Jonathan Bamberger, Lukas Harbaum, Klevis Mihali, Georgios Chatzis, Nikolaos Patsalis, Mohamed Ben Amar, Styliani Syntila, Martin C Hirsch, Fabian Lechner, Bernhard Schieffer, Birgit Markus","doi":"10.1093/ehjdh/ztaf082","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>The role of temporary mechanical circulatory support (tMCS) after out-of-hospital cardiac arrest (OHCA) remains controversial. This study evaluates machine learning (ML) models for predicting mortality and neurological outcomes, highlighting their potential as a tool to guide early tMCS decision-making.</p><p><strong>Methods and results: </strong>This retrospective study analysed five years of data from 564 adult non-traumatic OHCA patients treated at Marburg University Hospital. Four ML models (ANN, SVM, RF, XGBoost) were trained to predict in-hospital mortality and neurological outcome based on demographic, clinical, and treatment-related variables. Feature selection and SHAP analysis were used to optimize performance and identify patients potentially benefiting from tMCS. Overall, 144 patients (31.2%) out of 461 patients who fulfilled the inclusion criteria received tMCS: 39 left-ventricular microaxial flow pump, 76 venoarterial extracorporeal membrane oxygenation (VA-ECMO), and 29 biventricular support (ECMELLA). In 69 patients (14.9%) VA-ECMO implantation was performed as part of extracorporeal cardiopulmonary resuscitation. The survival rate of the tMCS group was 34.7% (50/144) compared to 52.7% (167/317) in the non-tMCS group. The highest predictive power for survival probability (with/without tMCS) could be achieved by XGBoost and RF when applied to the non-tMCS group. Machine learning identified 2.5% of non-tMCS patients likely to survive if treated with tMCS. In 23 (RF model) and 31 (XGBoost model) patients, the probability of survival increased by at least 5% with tMCS compared to their predicted outcome without tMCS. RF slightly outperformed XGBoost [area under the receiver operating characteristic curve (AUC) 0.85 vs. AUC 0.82].</p><p><strong>Conclusion: </strong>XGBoost and RF models accurately predict mortality and tMCS benefit in OHCA patients, supporting ML-based personalized therapy.</p>","PeriodicalId":72965,"journal":{"name":"European heart journal. Digital health","volume":"6 5","pages":"979-988"},"PeriodicalIF":4.4000,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12450520/pdf/","citationCount":"0","resultStr":"{\"title\":\"Evaluation of machine learning models for personalized prediction of benefit from temporary mechanical circulatory support after out-of-hospital cardiac arrest.\",\"authors\":\"Julian Kreutz, Jonathan Bamberger, Lukas Harbaum, Klevis Mihali, Georgios Chatzis, Nikolaos Patsalis, Mohamed Ben Amar, Styliani Syntila, Martin C Hirsch, Fabian Lechner, Bernhard Schieffer, Birgit Markus\",\"doi\":\"10.1093/ehjdh/ztaf082\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Aims: </strong>The role of temporary mechanical circulatory support (tMCS) after out-of-hospital cardiac arrest (OHCA) remains controversial. This study evaluates machine learning (ML) models for predicting mortality and neurological outcomes, highlighting their potential as a tool to guide early tMCS decision-making.</p><p><strong>Methods and results: </strong>This retrospective study analysed five years of data from 564 adult non-traumatic OHCA patients treated at Marburg University Hospital. Four ML models (ANN, SVM, RF, XGBoost) were trained to predict in-hospital mortality and neurological outcome based on demographic, clinical, and treatment-related variables. Feature selection and SHAP analysis were used to optimize performance and identify patients potentially benefiting from tMCS. Overall, 144 patients (31.2%) out of 461 patients who fulfilled the inclusion criteria received tMCS: 39 left-ventricular microaxial flow pump, 76 venoarterial extracorporeal membrane oxygenation (VA-ECMO), and 29 biventricular support (ECMELLA). In 69 patients (14.9%) VA-ECMO implantation was performed as part of extracorporeal cardiopulmonary resuscitation. The survival rate of the tMCS group was 34.7% (50/144) compared to 52.7% (167/317) in the non-tMCS group. The highest predictive power for survival probability (with/without tMCS) could be achieved by XGBoost and RF when applied to the non-tMCS group. Machine learning identified 2.5% of non-tMCS patients likely to survive if treated with tMCS. In 23 (RF model) and 31 (XGBoost model) patients, the probability of survival increased by at least 5% with tMCS compared to their predicted outcome without tMCS. RF slightly outperformed XGBoost [area under the receiver operating characteristic curve (AUC) 0.85 vs. AUC 0.82].</p><p><strong>Conclusion: </strong>XGBoost and RF models accurately predict mortality and tMCS benefit in OHCA patients, supporting ML-based personalized therapy.</p>\",\"PeriodicalId\":72965,\"journal\":{\"name\":\"European heart journal. Digital health\",\"volume\":\"6 5\",\"pages\":\"979-988\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2025-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12450520/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European heart journal. Digital health\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/ehjdh/ztaf082\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/9/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q1\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European heart journal. Digital health","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/ehjdh/ztaf082","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/9/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
摘要
目的：院外心脏骤停（OHCA）后临时机械循环支持（tMCS）的作用仍然存在争议。本研究评估了预测死亡率和神经预后的机器学习（ML）模型，强调了它们作为指导早期tMCS决策工具的潜力。方法和结果：本回顾性研究分析了在马尔堡大学医院治疗的564名成年非创伤性OHCA患者的5年数据。训练四种ML模型（ANN、SVM、RF、XGBoost），根据人口统计学、临床和治疗相关变量预测住院死亡率和神经预后。使用特征选择和SHAP分析来优化性能并确定可能受益于tMCS的患者。总体而言，461例符合纳入标准的患者中有144例（31.2%）接受了tMCS: 39例左心室微轴流泵，76例静脉体外膜氧合（VA-ECMO）， 29例双心室支持（ECMELLA）。在69例（14.9%）患者中，VA-ECMO植入作为体外心肺复苏的一部分。tMCS组生存率为34.7%(50/144)，非tMCS组为52.7%（167/317）。当应用于非tMCS组时，XGBoost和RF对生存概率（有/没有tMCS）的预测能力最高。机器学习识别出2.5%的非tMCS患者在接受tMCS治疗后可能存活。在23例（RF模型）和31例（XGBoost模型）患者中，与没有tMCS的预测结果相比，tMCS的生存概率至少增加了5%。RF略优于XGBoost[接收器工作特性曲线下面积（AUC） 0.85 vs AUC 0.82]。结论：XGBoost和RF模型可准确预测OHCA患者的死亡率和tMCS获益，支持基于ml的个性化治疗。
Evaluation of machine learning models for personalized prediction of benefit from temporary mechanical circulatory support after out-of-hospital cardiac arrest.
Aims: The role of temporary mechanical circulatory support (tMCS) after out-of-hospital cardiac arrest (OHCA) remains controversial. This study evaluates machine learning (ML) models for predicting mortality and neurological outcomes, highlighting their potential as a tool to guide early tMCS decision-making.
Methods and results: This retrospective study analysed five years of data from 564 adult non-traumatic OHCA patients treated at Marburg University Hospital. Four ML models (ANN, SVM, RF, XGBoost) were trained to predict in-hospital mortality and neurological outcome based on demographic, clinical, and treatment-related variables. Feature selection and SHAP analysis were used to optimize performance and identify patients potentially benefiting from tMCS. Overall, 144 patients (31.2%) out of 461 patients who fulfilled the inclusion criteria received tMCS: 39 left-ventricular microaxial flow pump, 76 venoarterial extracorporeal membrane oxygenation (VA-ECMO), and 29 biventricular support (ECMELLA). In 69 patients (14.9%) VA-ECMO implantation was performed as part of extracorporeal cardiopulmonary resuscitation. The survival rate of the tMCS group was 34.7% (50/144) compared to 52.7% (167/317) in the non-tMCS group. The highest predictive power for survival probability (with/without tMCS) could be achieved by XGBoost and RF when applied to the non-tMCS group. Machine learning identified 2.5% of non-tMCS patients likely to survive if treated with tMCS. In 23 (RF model) and 31 (XGBoost model) patients, the probability of survival increased by at least 5% with tMCS compared to their predicted outcome without tMCS. RF slightly outperformed XGBoost [area under the receiver operating characteristic curve (AUC) 0.85 vs. AUC 0.82].
Conclusion: XGBoost and RF models accurately predict mortality and tMCS benefit in OHCA patients, supporting ML-based personalized therapy.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
