Machine learning‐based prediction of in‐hospital death for patients with takotsubo syndrome: The InterTAK‐ML model

Abstract

AimsTakotsubo syndrome (TTS) is associated with a substantial rate of adverse events. We sought to design a machine‐learning (ML) based model to predict the risk of in‐hospital death and to perform a clustering of TTS patients to identify different risk profiles.Methods and resultsA Ridge Logistic Regression‐based ML model for predicting in‐hospital death was developed on 3482 TTS patients from the International Takotsubo Registry, randomly split in a train and an internal validation cohort (75% and 25% of the sample size, respectively) and evaluated in an external validation cohort (1037 patients). 31 clinically relevant variables were included in the prediction model. Model performance represented the primary endpoint and was assessed according to area under the receiver‐operating characteristic curve (AUC), Sensitivity and Specificity. As secondary endpoint, a K‐Medoids clustering algorithm was designed to stratify patients into phenotypic groups based on the ten most relevant features emerging from the main model. The overall incidence of in‐hospital death was 5.2%. The InterTAK‐ML model showed an AUC of 0.89 (0.85‐0.92), Sensitivity 0.85 (0.78‐0.95) and Specificity 0.76 (0.74‐0.79) in the internal validation cohort and an AUC of 0.82 (0.73‐0.91), a sensitivity of 0.74 (0.61‐0.87) and a specificity of 0.79 (0.77‐0.81) in the external cohort for in‐hospital death prediction. By exploiting the 10 variables showing the highest feature importance, TTS patients were clustered into six groups associated with different risks of in‐hospital death (28.8% vs 15.5% vs 5.4% vs 0.8% vs 0.5%) which were consistent also in the external cohort.ConclusionA ML‐based approach for the identification of TTS patients at risk of adverse short‐term prognosis is feasible and effective. The InterTAK‐ML model showed unprecedented discriminative capability for the prediction of in‐hospital death.This article is protected by copyright. All rights reserved.

Deep Learning-Based Prediction Model of Heart Failure with Improved Ejection Fraction

“…Over the past few years, an increasing number of studies concentrate on deep learning models, and most of them are based on visualizations such as ECG, echocardiogram and cardiac magnetic resonance to train models 14 . Currently, studies have been conducted domestically and worldwide to analyze diverse types of clinical data such as electrocardiograms and echocardiograms, which based on deep learning to classify and evaluate the three traditional types of heart failure and risk stratification 3,15 . However, until recently, there is no research about constructing a prediction model for HFimpEF concerning deep learning.…”

Revolutionizing Cardiology through Artificial Intelligence—Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment—A Comprehensive Review of the Past 5 Years

“…Another study, which looked at 3284 patients with TTS, showed that an ML-based approach identified patients at risk of a poor short-term prognosis in the hospital. The Inter-TAK-ML model has shown its usefulness for predicting in-hospital death in patients with TTS [ 59 ].…”

December 2023 at a glance: Focus on medical therapy in chronic and acute heart failure

“…Considering the 10 most important variables, patients were clustered into six groups, and each group was associated with a specific risk of in-hospital death. 37 The rationale and design of the ESC Heart Failure III Registry is published. 38 .…”