Machine learning electrocardiography model to differentiate takotsubo syndrome from myocardial infarction
Machine learning models could discriminate TTS from MI (NSTEMI and STEMI) and suspected MI with high sensitivity and NPV, outperforming cardiologists using conventional criteria. The models require further refinement to increase PPV, precision-recall and external validation, but it holds promise for TTS screening aiding the clinician in ruling out TTS.
Authors
- Loghman Henareh
- Carl Henrik Ek (ORCID: https://orcid.org/0000-0003-1302-6309)
- Vincent Dutordoir
- Ingrid Nilsson (ORCID: https://orcid.org/0000-0002-6621-3418)
- Jonas Spaak (ORCID: https://orcid.org/0000-0002-2135-1294)
- Felicia Håkansson
- Per Tornvall
- Christina Ekenbäck (ORCID: https://orcid.org/0000-0002-4401-7117)
- Mikael Andersson (ORCID: https://orcid.org/0000-0002-9837-4486)
- Thomas Olsson
- Erik Bodin
- Axel Gemvik
Institutions
- University of Cambridge (GB)
- Karolinska Institutet (SE)
- Stockholm South General Hospital (SE)
- Saint Göran Hospital (SE)
Publication Details
- Journal
- European Heart Journal - Digital Health
- Published
- 2025-06-22
- DOI
- https://doi.org/10.1093/ehjdh/ztaf073
- Primary Topic
- Takotsubo Cardiomyopathy and Associated Phenomena
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Hjärt-Lungfonden