biostudies-literatureUnknown6(5)Kreutz J<h4>Aims</h4>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.<h4>Methods and results</h4>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 patieEuropean heart journal. Digital health979-988https://www.ebi.ac.uk/biostudies/studies/S-EPMC12450520biostudies-literatureEvaluation of machine learning models for personalized prediction of benefit from temporary mechanical circulatory support after out-of-hospital cardiac arrest.PMC12450520Syntila SBamberger JLechner FSchieffer BMihali KMarkus BKreutz JChatzis GHarbaum LPatsalis NHirsch MCBen Amar MfalseEvaluation of machine learning models for personalized prediction of benefit from temporary mechanical circulatory support after out-of-hospital cardiac arrest.<h4>Aims</h4>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.<h4>Methods and results</h4>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 patie2025-01-01T00:00:00Z2025 Sep2026-06-03T17:18:16.768Z2026-04-29T03:13:01.943ZS-EPMC124505204098499510.1093/ehjdh/ztaf082