Cover Image

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 logis...

Full description

Saved in:
Bibliographic Details
Main Authors: De Filippo, Ovidio (Author) , Cammann, Victoria Lucia (Author) , Pancotti, Corrado (Author) , Di Vece, Davide (Author) , Silverio, Angelo (Author) , Schweiger, Victor (Author) , Niederseer, David (Author) , Szawan, Konrad Andreas (Author) , Würdinger, Michael (Author) , Koleva, Iva (Author) , Dusi, Veronica (Author) , Bellino, Michele (Author) , Vecchione, Carmine (Author) , Parodi, Guido (Author) , Bossone, Eduardo (Author) , Gili, Sebastiano (Author) , Neuhaus, Michael (Author) , Franke, Jennifer (Author) , Meder, Benjamin (Author) , Jaguszewski, Milosz (Author) , Noutsias, Michel (Author) , Knorr, Maike Christina (Author) , Jansen, Thomas (Author) , Dichtl, Wolfgang (Author) , Lewinski, Dirk von (Author) , Burgdorf, Christof (Author) , Kherad, Behrouz (Author) , Tschöpe, Carsten (Author) , Sarcon, Annahita (Author) , Shinbane, Jerold (Author) , Rajan, Lawrence (Author) , Michels, Guido (Author) , Pfister, Roman (Author) , Cuneo, Alessandro (Author) , Jacobshagen, Claudius (Author) , Karakas, Mahir (Author) , Koenig, Wolfgang (Author) , Pott, Alexander (Author) , Meyer, Philippe (Author) , Roffi, Marco (Author) , Banning, Adrian (Author) , Wolfrum, Mathias (Author) , Cuculi, Florim (Author) , Kobza, Richard (Author) , Fischer, Thomas A. (Author) , Vasankari, Tuija (Author) , Airaksinen, K. E. Juhani (Author) , Napp, Christian (Author) , Dworakowski, Rafal (Author) , MacCarthy, Philip (Author) , Kaiser, Christoph A. (Author) , Osswald, Stefan (Author) , Galiuto, Leonarda (Author) , Chan, Christina (Author) , Bridgman, Paul (Author) , Beug, Daniel (Author) , Delmas, Clément (Author) , Lairez, Olivier (Author) , Gilyarova, Ekaterina (Author) , Shilova, Alexandra (Author) , Gilyarov, Mikhail (Author) , El-Battrawy, Ibrahim (Author) , Akın, Ibrahim (Author) , Poledniková, Karolina (Author) , Toušek, Petr (Author) , Winchester, David E. (Author) , Massoomi, Michael (Author) , Galuszka, Jan (Author) , Ukena, Christian (Author) , Poglajen, Gregor (Author) , Carrilho-Ferreira, Pedro (Author) , Hauck, Christian (Author) , Paolini, Carla (Author) , Bilato, Claudio (Author) , Kobayashi, Yoshio (Author) , Kato, Ken (Author) , Ishibashi, Iwao (Author) , Himi, Toshiharu (Author) , Din, Jehangir (Author) , Al-Shammari, Ali (Author) , Prasad, Abhiram (Author) , Rihal, Charanjit S. (Author) , Liu, Kan (Author) , Schulze, Paul Christian (Author) , Bianco, Matteo (Author) , Jörg, Lucas (Author) , Rickli, Hans (Author) , Pestana, Gonçalo (Author) , Nguyen, Thanh H. (Author) , Böhm, Michael (Author) , Maier, Lars Siegfried (Author) , Pinto, Fausto J. (Author) , Widimský, Petr (Author) , Felix, Stephan (Author) , Braun-Dullaeus, Ruediger C. (Author) , Rottbauer, Wolfgang (Author) , Hasenfuß, Gerd (Author) , Pieske, Burkert M. (Author) , Schunkert, Heribert (Author) , Budnik, Monika (Author) , Opolski, Grzegorz (Author) , Thiele, Holger (Author) , Bauersachs, Johann (Author) , Horowitz, John D. (Author) , Di Mario, Carlo (Author) , Bruno, Francesco (Author) , Kong, William (Author) , Dalakoti, Mayank (Author) , Imori, Yoichi (Author) , Münzel, Thomas (Author) , Crea, Filippo (Author) , Lüscher, Thomas F. (Author) , Bax, Jeroen J. (Author) , Ruschitzka, Frank (Author) , De Ferrari, Gaetano Maria (Author) , Fariselli, Piero (Author) , Templin-Ghadri, Jelena-Rima (Author) , Citro, Rodolfo (Author) , D'Ascenzo, Fabrizio (Author) , Templin, Christian (Author)
Format: Article (Journal)
Language:English
Published: 2023
In: European journal of heart failure
Year: 2023, Volume: 25, Issue: 12, Pages: 2299-2311
ISSN:1879-0844
DOI:10.1002/ejhf.2983
Online Access:Resolving-System, kostenfrei: https://doi.org/10.1002/ejhf.2983
Resolving-System, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/10.1002/ejhf.2983
Resolving-System, kostenfrei: https://doi.org/10.25673/117261
Get full text
Author Notes:Ovidio De Filippo, Jennifer Franke, Benjamin Meder, Michel Noutsias, Ibrahim El-Battrawy, Ibrahim Akin [und viele andere]
Description
Summary: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.
Item Description:Online veröffentlicht: 31. Juli 2023
Physical Description:Online Resource
ISSN:1879-0844
DOI:10.1002/ejhf.2983

Similar Items