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... Show moreAimsTakotsubo 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 (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.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. Show less
Napp, L.C.; Cammann, V.L.; Jaguszewski, M.; Szawan, K.A.; Wischnewsky, M.; Gili, S.; ... ; Templin, C. 2020
Aims Takotsubo syndrome (US) is an acute heart failure syndrome, which shares many features with acute coronary syndrome (ACS). Although TTS was initially described with angiographically normal... Show moreAims Takotsubo syndrome (US) is an acute heart failure syndrome, which shares many features with acute coronary syndrome (ACS). Although TTS was initially described with angiographically normal coronary arteries, smaller studies recently indicated a potential coexistence of coronary artery disease (CAD) in US patients. This study aimed to determine the coexistence, features, and prognostic role of CAD in a large cohort of patients with US.Methods and results Coronary anatomy and CAD were studied in patients diagnosed with US. Inclusion criteria were compliance with the International Takotsubo Diagnostic Criteria for TTS, and availability of original coronary angiographies with ventriculography performed during the acute phase. Exclusion criteria were missing views, poor quality of angiography loops, and angiography without ventriculography. A total of 1016 US patients were studied. Of those, 23.0% had obstructive CAD, 41.2% had non -obstructive CAD, and 35.7% had angiographically normal coronary arteries. A total of 47 patients (4.6%) underwent percutaneous coronary intervention, and 3 patients had acute and 8 had chronic coronary artery occlusion concomitant with US, respectively. The presence of CAD was associated with increased incidence of shock, ventilation, and death from any cause. After adjusting for confounders, the presence of obstructive CAD was associated with mortality at 30 days. Takotsubo syndrome patients with obstructive CAD were at comparable risk for shock and death and nearly at twice the risk for ventilation compared to an age- and sex-matched ACS cohort.Conclusions Coronary artery disease frequently coexists in US patients, presents with the whole spectrum of coronary pathology including acute coronary occlusion, and is associated with adverse outcome. Show less
Cammann, V.L.; Szawan, K.A.; Stahli, B.E.; Kato, K.; Budnik, M.; Wischnewsky, M.; ... ; Templin, C. 2020