Crea, Filippo

ABSTRACT 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.

Background Clinical characteristics and outcomes of takotsubo syndrome ( TTS ) patients with malignancy have not been fully elucidated. This study sought to explore differences in clinical characteristics and to investigate short‐ and long‐term outcomes in TTS patients with or without malignancy. Methods and Results TTS patients were enrolled from the International Takotsubo Registry. The TTS cohort was divided into patients with and without malignancy to investigate differences in clinical characteristics and to assess short‐ and long‐term mortality. A subanalysis was performed comparing long‐term mortality between a subset of TTS patients with or without malignancy and acute coronary syndrome (ACS) patients with or without malignancy. Malignancy was observed in 16.6% of 1604 TTS patients. Patients with malignancy were older and more likely to have physical triggers, but less likely to have emotional triggers compared with those without malignancy. Long‐term mortality was higher in patients with malignancy ( P <0.001), while short‐term outcome was comparable ( P =0.17). In a subanalysis, long‐term mortality was comparable between TTS patients with malignancies and ACS patients with malignancies ( P =0.13). Malignancy emerged as an independent predictor of long‐term mortality. Conclusions A substantial number of TTS patients show an association with malignancy. History of malignancy might increase the risk for TTS , and therefore, appropriate screening for malignancy should be considered in these patients. Clinical Trial Registration URL : http://www.clinicaltrial.gov . Unique identifier: NCT 01947621.