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

AIMS

Takotsubo 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 RESULTS

A ridge logistic regression-based ML model for predicting in-hospital death was developed on 3482 TTS patients from the International Takotsubo (InterTAK) 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). Thirty-one clinically relevant variables were included in the prediction model. Model performance represented the primary endpoint and was assessed according to area under the curve (AUC), sensitivity and specificity. As secondary endpoint, a K-medoids clustering algorithm was designed to stratify patients into phenotypic groups based on the 10 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), a sensitivity of 0.85 (0.78-0.95) and a specificity of 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. 1.0.8% vs. 0.5%) which were consistent also in the external cohort.

CONCLUSION

A 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.

Age-Related Variations in Takotsubo Syndrome

BACKGROUND

Takotsubo syndrome (TTS) occurs predominantly in post-menopausal women but is also found in younger patients.

OBJECTIVES

This study aimed to investigate age-related differences in TTS.

METHODS

Patients diagnosed with TTS and enrolled in the International Takotsubo Registry between January 2011 and February 2017 were included in this analysis and were stratified by age (younger: ≤50 years, middle-age: 51 to 74 years, elderly: ≥75 years). Baseline characteristics, hospital course, as well as short- and long-term mortality were compared among groups.

RESULTS

Of 2,098 TTS patients, 242 (11.5%) patients were ≤50 years of age, 1,194 (56.9%) were 51 to 74 years of age, and 662 (31.6%) were ≥75 years of age. Younger patients were more often men (12.4% vs. 10.9% vs. 6.3%; p = 0.002) and had an increased prevalence of acute neurological (16.3% vs. 8.4% vs. 8.8%; p = 0.001) or psychiatric disorders (14.1% vs. 10.3% vs. 5.6%; p < 0.001) compared with middle-aged and elderly TTS patients. Furthermore, younger patients had more often cardiogenic shock (15.3% vs. 9.1% vs. 8.1%; p = 0.004) and had a numerically higher in-hospital mortality (6.6% vs. 3.6% vs. 5.1%; p = 0.07). At multivariable analysis, younger (odds ratio: 1.60; 95% confidence interval: 0.86 to 3.01; p = 0.14) and older age (odds ratio: 1.09; 95% confidence interval: 0.66 to 1.80; p = 0.75) were not independently associated with in-hospital mortality using the middle-aged group as a reference. There were no differences in 60-day mortality rates among groups.

CONCLUSIONS

A substantial proportion of TTS patients are younger than 50 years of age. TTS is associated with severe complications requiring intensive care, particularly in younger patients.