Huang, Helen, Perone, Francesco, Leung, Keith Sai Kit, Ullah, Irfan, Lee, Quinncy, Chew, Nicholas, Liu, Tong, Tse, Gary (2024) The utility of artificial intelligence and machine learning in the diagnosis of Takotsubo cardiomyopathy: a systematic review. Heart and Mind, 8 (3). pp. 165-176. ISSN 2468-6476. E-ISSN 2468-6484. (doi:10.4103/hm.hm-d-23-00061) (KAR id:106791)
PDF
Publisher pdf
Language: English
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
|
|
Download this file (PDF/3MB) |
Preview |
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.4103/hm.hm-d-23-00061 |
Abstract
Introduction: Takotsubo cardiomyopathy (TTC) is a cardiovascular disease caused by physical/psychological stressors with significant morbidity if left untreated. Because TTC often mimics acute myocardial infarction in the absence of obstructive coronary disease, the condition is often underdiagnosed in the population. Our aim was to discuss the role of artificial intelligence (AI) and machine learning (ML) in diagnosing TTC.
Methods: We systematically searched electronic databases from inception until April 8, 2023, for studies on the utility of AI- or ML-based algorithms in diagnosing TTC compared with other cardiovascular diseases or healthy controls. We summarized major findings in a narrative fashion and tabulated relevant numerical parameters.
Results: Five studies with a total of 920 patients were included. Four hundred and forty-seven were diagnosed with TTC via International Classification of Diseases codes or the Mayo Clinic diagnostic criteria, while there were 473 patients in the comparator group (29 of healthy controls, 429 of myocardial infarction, and 14 of acute myocarditis). Hypertension and smoking were the most common comorbidities in both cohorts, but there were no statistical differences between TTC and comparators. Two studies utilized deep-learning algorithms on transthoracic echocardiographic images, while the rest incorporated supervised ML on cardiac magnetic resonance imaging, 12-lead electrocardiographs, and brain magnetic resonance imaging. All studies found that AI-based algorithms can increase the diagnostic rate of TTC when compared to healthy controls or myocardial infarction patients. In three of these studies, AI-based algorithms had higher sensitivity and specificity compared to human readers.
Conclusion: AI and ML algorithms can improve the diagnostic capacity of TTC and additionally reduce erroneous human error in differentiating from MI and healthy individuals.
Item Type: | Article |
---|---|
DOI/Identification number: | 10.4103/hm.hm-d-23-00061 |
Uncontrolled keywords: | artificial intelligence, diagnostics, precision medicine, takotsubo cardiomyopathy |
Subjects: | R Medicine |
Divisions: | Divisions > Division of Natural Sciences > Kent and Medway Medical School |
Funders: | University of Kent (https://ror.org/00xkeyj56) |
SWORD Depositor: | JISC Publications Router |
Depositing User: | JISC Publications Router |
Date Deposited: | 05 Aug 2024 14:05 UTC |
Last Modified: | 06 Aug 2024 08:00 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/106791 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):