The Hope and the Hype of Artificial Intelligence for Syncope Management
(2025) In European Heart Journal - Digital Health- Abstract
- Importance
Syncope remains a diagnostic challenge despite advancements in testing and treatment. Cardiac syncope is an independent predictor of mortality and can be difficult to distinguish from other causes of transient loss of consciousness (TLOC).
Observations
The cause of TLOC is often unclear, hospitalization criteria are ambiguous, diagnostic tests are frequently non-informative, and assessments are costly. Patients are left with unanswered questions and limited guidance. Artificial intelligence (AI) has the potential to optimize syncope evaluation by processing large datasets, detecting imperceptible patterns, and assisting clinicians. However, AI has limitations, including errors, lack of human empathy, and... (More) - Importance
Syncope remains a diagnostic challenge despite advancements in testing and treatment. Cardiac syncope is an independent predictor of mortality and can be difficult to distinguish from other causes of transient loss of consciousness (TLOC).
Observations
The cause of TLOC is often unclear, hospitalization criteria are ambiguous, diagnostic tests are frequently non-informative, and assessments are costly. Patients are left with unanswered questions and limited guidance. Artificial intelligence (AI) has the potential to optimize syncope evaluation by processing large datasets, detecting imperceptible patterns, and assisting clinicians. However, AI has limitations, including errors, lack of human empathy, and uncertain clinical utility. Liability issues further complicate its integration. We present three viewpoints: (1) AI is crucial for advancing syncope management; (2) AI can enhance the patient experience; and (3) AI in syncope care is inevitable.
Conclusions and Relevance
AI may improve syncope diagnosis and management, particularly through machine learning (ML)-based test interpretation and wearable device data. However, it has yet to surpass human clinical judgment in complex decision-making. Current challenges include gaps in understanding syncope mechanisms, AI interpretability, generalizability, and clinical integration. Standardized diagnostic approaches, real-world validation, and curated datasets are essential for progress. AI may enhance efficiency and communication but raises concerns regarding confidentiality, bias, inequities, and legal implications. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/44201ba3-26dc-43f8-9bc6-69ea881e1d9a
- author
- organization
- publishing date
- 2025-06
- type
- Contribution to journal
- publication status
- published
- subject
- in
- European Heart Journal - Digital Health
- publisher
- Oxford University Press
- ISSN
- 2634-3916
- DOI
- 10.1093/ehjdh/ztaf061
- language
- English
- LU publication?
- yes
- id
- 44201ba3-26dc-43f8-9bc6-69ea881e1d9a
- alternative location
- https://academic.oup.com/ehjdh/advance-article/doi/10.1093/ehjdh/ztaf061/8174732
- date added to LUP
- 2025-07-05 21:53:06
- date last changed
- 2025-07-07 10:42:48
@article{44201ba3-26dc-43f8-9bc6-69ea881e1d9a, abstract = {{Importance<br/>Syncope remains a diagnostic challenge despite advancements in testing and treatment. Cardiac syncope is an independent predictor of mortality and can be difficult to distinguish from other causes of transient loss of consciousness (TLOC).<br/><br/>Observations<br/>The cause of TLOC is often unclear, hospitalization criteria are ambiguous, diagnostic tests are frequently non-informative, and assessments are costly. Patients are left with unanswered questions and limited guidance. Artificial intelligence (AI) has the potential to optimize syncope evaluation by processing large datasets, detecting imperceptible patterns, and assisting clinicians. However, AI has limitations, including errors, lack of human empathy, and uncertain clinical utility. Liability issues further complicate its integration. We present three viewpoints: (1) AI is crucial for advancing syncope management; (2) AI can enhance the patient experience; and (3) AI in syncope care is inevitable.<br/><br/>Conclusions and Relevance<br/>AI may improve syncope diagnosis and management, particularly through machine learning (ML)-based test interpretation and wearable device data. However, it has yet to surpass human clinical judgment in complex decision-making. Current challenges include gaps in understanding syncope mechanisms, AI interpretability, generalizability, and clinical integration. Standardized diagnostic approaches, real-world validation, and curated datasets are essential for progress. AI may enhance efficiency and communication but raises concerns regarding confidentiality, bias, inequities, and legal implications.}}, author = {{Johnston, Samuel L and Barsotti, E John and Bakogiannis, Constantinos and Fedorowski, Artur and Ricci, Fabrizio and Heller, Eric G and Sheldon, Robert S and Sutton, Richard and Shen, Win-Kuang and Thiruganasambandamoorthy, Venkatesh and Adhaduk, Mehul and Parker, William H and Aburizik, Arwa and Haselton, Corey R and Cuskey, Alex J and Lee, Sangil and Johansson, Madeleine and Macfarlane, Donald and Dominic, Paari and Abe, Haruhiko and Rao, B Hygriv and Mudireddy, Avinash and Sonka, Milan and Sandhu, Roopinder K and Kenny, Rose Anne and Statz, Giselle M and Gopinathannair, Rakesh and Benditt, David and Dipaola, Franca and Gatti, Mauro and Menè, Roberto and Giaj Levra, Alessandro and Shiffer, Dana and Costantino, Giorgio and Furlan, Raffaello and Ruwald, Martin H and Vassilikos, Vassilios and Gebska, Milena A and Olshansky, Brian}}, issn = {{2634-3916}}, language = {{eng}}, publisher = {{Oxford University Press}}, series = {{European Heart Journal - Digital Health}}, title = {{The Hope and the Hype of Artificial Intelligence for Syncope Management}}, url = {{http://dx.doi.org/10.1093/ehjdh/ztaf061}}, doi = {{10.1093/ehjdh/ztaf061}}, year = {{2025}}, }