Application of a machine learning algorithm for detection of atrial fibrillation in secondary care
| Autor: | Sadia Khan, Kevin G.J. Pollock, Fu Siong Ng, Ellie Johnston, Ayman Nassar, Sara Sekelj, Belinda Sandler, Nathan R. Hill, Usman Farooqui |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial intelligence
lcsh:Diseases of the circulatory (Cardiovascular) system 030204 cardiovascular system & hematology Machine learning computer.software_genre Secondary care 03 medical and health sciences 0302 clinical medicine Heart arrhythmia Diagnosis Medicine In patient 030212 general & internal medicine Risk threshold Stroke Original Paper business.industry fungi food and beverages Atrial fibrillation medicine.disease Data extraction lcsh:RC666-701 Cohort Cardiology and Cardiovascular Medicine business computer Algorithm |
| Zdroj: | International Journal of Cardiology: Heart & Vasculature, Vol 31, Iss, Pp 100674-(2020) International Journal of Cardiology. Heart & Vasculature |
| ISSN: | 2352-9067 |
| DOI: | 10.1016/j.ijcha.2020.100674 |
| Popis: | Highlights • Machine learning algorithms can accurately identify undiagnosed atrial fibrillation in patients. • Algorithms developed in primary care can be used in secondary care with reasonable performance. • An appreciable proportion of patients with undiagnosed AF could be detected in secondary care. Atrial fibrillation (AF) is the most common sustained heart arrhythmia and significantly increases risk of stroke. Opportunistic AF testing in high-risk patients typically requires frequent electrocardiogram tests to capture the arrhythmia. Risk-prediction algorithms may help to more accurately identify people with undiagnosed AF and machine learning (ML) may aid in the diagnosis of AF. Here, we applied an AF-risk prediction algorithm to secondary care data linked to primary care data in the DISCOVER database in order to evaluate changes in model performance, and identify patients not previously detected in primary care. We identified an additional 5,444 patients who had an AF diagnosis only in secondary care during the data extraction period. 2,696 (49.5%) were accepted by the algorithm and the algorithm correctly assigned 2,637 (97.8%) patients to the AF cohort. Using a risk threshold of 7.4% in patients aged ≥ 30 years, algorithm sensitivity and specificity was 38% and 95%, respectively. Approximately 15% of AF patients assigned to the AF cohort by the algorithm had a secondary care diagnosis with no record of AF in primary care. These additional patients did not substantially alter algorithm performance. The additional detection of previously undiagnosed AF patients in secondary care highlights unexpected potential utility of this ML algorithm. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|