Detecting atrial fibrillation by artificial intelligence enabled neuroimaging examination.
Our machine learning algorithm has reasonable classification power in categorizing stroke patients into those with and without underlying AF. Testing in external validation datasets is critical to confirm these results.
Authors
- Angelos Sharobeam (ORCID: https://orcid.org/0000-0001-5833-7632)
- Bernard Yan (ORCID: https://orcid.org/0000-0001-8802-9606)
- Nandakishor Desai (ORCID: https://orcid.org/0000-0001-6491-6171)
- Stephen M. Davis (ORCID: https://orcid.org/0000-0003-0962-2300)
- Yohanna Kusuma (ORCID: https://orcid.org/0000-0002-0946-3066)
- Aravinda S. Rao (ORCID: https://orcid.org/0000-0003-2319-6539)
- Marimuthu Palaniswami (ORCID: https://orcid.org/0000-0002-3635-4252)
- Mohammad Javad Shokri (ORCID: https://orcid.org/0000-0002-2928-716X)
Institutions
- The Royal Melbourne Hospital (AU)
- The University of Melbourne (AU)
Publication Details
- Journal
- Cerebrovascular Diseases
- Published
- 2025-02-13
- DOI
- https://doi.org/10.1159/000543042
- Primary Topic
- Atrial Fibrillation Management and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Medical Research Council
- National Health and Medical Research Council