While few scores are available for risk stratification of patients hospitalized for AHF using traditional statistical methods, the potential benefit of machine learning (ML) is not established.

To investigate the feasibility and accuracy of a ML model using clinical, biological, and echocardiographic data to predict in-hospital major adverse events (MAE) in patients hospitalized for AHF and compare its performance to traditional models and existing scores.

Three ML models were developed using clinical and echocardiographic parameters to predict in-hospital MAE, including death, resuscitated cardiac arrest or cardiogenic shock requiring medical or mechanical hemodynamic support. The study cohort consists of consecutive patients admitted for AHF from a French nationwide, multicenter, prospective, study involving 39 centers (NCT05063097). Immediately on arrival in ICCU a standardized exhaled carbon monoxide (CO) was systematically measured, and the presence of illicit drugs was determined through an urine drug assay (NarcoCheck®). Least absolute shrinkage and selection operator (LASSO) regression was used to select variables and prevent model over-fitting. The three ML models (LASSO, random forest and XGBoost) were then trained on 70% of patients and evaluated on the other 30% as internal validation. Their performance was compared against standard logistic regression model.

Among 459 consecutive patients included (age 68±14 years, 68% male), 47 had in-hospital MAE (9.8%). Out of 28 clinical, biological, ECG, and echocardiographic variables, seven were selected as being the most important in predicting MAE in the training set (n=322): mean arterial pressure (MAP), ischemic etiology, VTI, E/e’, TAPSE (tricuspid annular plane systolic excursion), illicit drugs and Carbon monoxide. The random forest model showed the best performance compared with the other ML models (AUROC=0.82, PR-AUC=0.48, F1 score=0.56) (Fig. 1). Our proposed ML model exhibited a higher AUC compared with an existing score for prediction of MAE (AUROC for our ML model: 0.82 vs. acute HF-score: 0.57; P<0.001).

Our ML-model including seven clinical and echocardiographic variables, including carbon monoxide level and illicit drugs use, exhibited a better performance than traditional statistical methods to predict in-hospital outcomes in patients admitted for AHF.