Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Dec;25(12):2299-2311.
doi: 10.1002/ejhf.2983. Epub 2023 Sep 18.

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

Ovidio De Filippo  1 , Victoria L Cammann  2 , Corrado Pancotti  3 , Davide Di Vece  2 , Angelo Silverio  4 , Victor Schweiger  2 , David Niederseer  2 , Konrad A Szawan  2 , Michael Würdinger  2 , Iva Koleva  2 , Veronica Dusi  1 , Michele Bellino  4 , Carmine Vecchione  4   5 , Guido Parodi  6 , Eduardo Bossone  7 , Sebastiano Gili  8 , Michael Neuhaus  9 , Jennifer Franke  10 , Benjamin Meder  10 , Miłosz Jaguszewski  11 , Michel Noutsias  12 , Maike Knorr  13 , Thomas Jansen  13 , Wolfgang Dichtl  14 , Dirk von Lewinski  15 , Christof Burgdorf  16 , Behrouz Kherad  17 , Carsten Tschöpe  17 , Annahita Sarcon  18 , Jerold Shinbane  19 , Lawrence Rajan  20 , Guido Michels  21 , Roman Pfister  22 , Alessandro Cuneo  23 , Claudius Jacobshagen  24   25 , Mahir Karakas  26   27 , Wolfgang Koenig  28   29 , Alexander Pott  30 , Philippe Meyer  31 , Marco Roffi  31 , Adrian Banning  32 , Mathias Wolfrum  33 , Florim Cuculi  33 , Richard Kobza  33 , Thomas A Fischer  34 , Tuija Vasankari  35 , K E Juhani Airaksinen  35 , L Christian Napp  36 , Rafal Dworakowski  37 , Philip MacCarthy  37 , Christoph Kaiser  38 , Stefan Osswald  38 , Leonarda Galiuto  39 , Christina Chan  40 , Paul Bridgman  40 , Daniel Beug  41   42 , Clément Delmas  43 , Olivier Lairez  43 , Ekaterina Gilyarova  44 , Alexandra Shilova  44 , Mikhail Gilyarov  44 , Ibrahim El-Battrawy  45   46 , Ibrahim Akin  45   46 , Karolina Poledniková  47 , Petr Toušek  47 , David E Winchester  48 , Michael Massoomi  48 , Jan Galuszka  49 , Christian Ukena  50 , Gregor Poglajen  51 , Pedro Carrilho-Ferreira  52 , Christian Hauck  53 , Carla Paolini  54 , Claudio Bilato  54 , Yoshio Kobayashi  55 , Ken Kato  55 , Iwao Ishibashi  56 , Toshiharu Himi  57 , Jehangir Din  58 , Ali Al-Shammari  58 , Abhiram Prasad  59 , Charanjit S Rihal  59 , Kan Liu  60 , P Christian Schulze  61 , Matteo Bianco  62 , Lucas Jörg  63 , Hans Rickli  63 , Gonçalo Pestana  64 , Thanh H Nguyen  65 , Michael Böhm  50 , Lars S Maier  53 , Fausto J Pinto  52 , Petr Widimský  47 , Stephan B Felix  41   42 , Ruediger C Braun-Dullaeus  66 , Wolfgang Rottbauer  30 , Gerd Hasenfuß  24 , Burkert M Pieske  17   67 , Heribert Schunkert  28   29 , Monika Budnik  68 , Grzegorz Opolski  68 , Holger Thiele  69 , Johann Bauersachs  36 , John D Horowitz  65 , Carlo Di Mario  70 , Francesco Bruno  1 , William Kong  71 , Mayank Dalakoti  71 , Yoichi Imori  72 , Thomas Münzel  13 , Filippo Crea  39 , Thomas F Lüscher  73   74 , Jeroen J Bax  75 , Frank Ruschitzka  2 , Gaetano Maria De Ferrari  1 , Piero Fariselli  3 , Jelena R Ghadri  2 , Rodolfo Citro  5   76 , Fabrizio D'Ascenzo  1 , Christian Templin  2
Affiliations
Free article

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

Ovidio De Filippo et al. Eur J Heart Fail. 2023 Dec.
Free article

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.

Keywords: Artificial intelligence; Machine learning; Mortality prediction; Outcome; Takotsubo syndrome.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: none declared.

Comment in

References

    1. Sato H. Tako-tsubo-like left ventricular dysfunction due to multivessel coronary spasm. In: Kodama K, Haze K, Hori M, eds. Clinical aspect of myocardial injury: From ischemia to heart failure. Tokyo: Kagakuhyoronsha Publishing Co; 1990. p56-64.
    1. Templin C, Ghadri JR, Diekmann J, Napp LC, Bataiosu DR, Jaguszewski M, et al. Clinical features and outcomes of Takotsubo (stress) cardiomyopathy. N Engl J Med 2015;373:929-938. https://doi.org/10.1056/NEJMoa1406761
    1. Ghadri JR, Kato K, Cammann VL, Gili S, Jurisic S, Di Vece D, et al. Long-term prognosis of patients with Takotsubo syndrome. J Am Coll Cardiol 2018;72:874-882. https://doi.org/10.1016/j.jacc.2018.06.016
    1. Kim H, Senecal C, Lewis B, Prasad A, Rajiv G, Lerman LO, et al. Natural history and predictors of mortality of patients with Takotsubo syndrome. Int J Cardiol 2018;267:22-27. https://doi.org/10.1016/j.ijcard.2018.04.139
    1. Uribarri A, Nunez-Gil IJ, Conty DA, Vedia O, Almendro-Delia M, Duran Cambra A, et al. Short- and long-term prognosis of patients with Takotsubo syndrome based on different triggers: Importance of the physical nature. J Am Heart Assoc 2019;8:e013701. https://doi.org/10.1161/JAHA.119.013701

Publication types