Atrial Fibrillation Detection With an Analog Smartwatch: Prospective Clinical Study and Algorithm Validation
Bibliographic record
Abstract
BACKGROUND: Atrial fibrillation affects approximately 4% of the world's population and is one of the major causes of stroke, heart failure, sudden death, and cardiovascular morbidity. It can be difficult to diagnose when asymptomatic or in the paroxysmal stage, and its natural history is not well understood. New wearables and connected devices offer an opportunity to improve on this situation. OBJECTIVE: We aimed to validate an algorithm for the automatic detection of atrial fibrillation from a single-lead electrocardiogram taken with a smartwatch. METHODS: Eligible patients were recruited from 4 sites in Paris, France. Electrocardiograms (12-lead reference and single lead) were captured simultaneously. The electrocardiograms were reviewed by independent, blinded board-certified cardiologists. The sensitivity and specificity of the algorithm to detect atrial fibrillation and normal sinus rhythm were calculated. The quality of single-lead electrocardiograms (visibility and polarity of waves, interval durations, heart rate) was assessed in comparison with the gold standard (12-lead electrocardiogram). RESULTS: A total of 262 patients (atrial fibrillation: n=100, age: mean 74.3 years, SD 12.3; normal sinus rhythm: n=113, age: 61.8 years, SD 14.3; other arrhythmia: n=45, 66.9 years, SD 15.2; unreadable electrocardiograms: n=4) were included in the final analysis; 6.9% (18/262) were classified as Noise by the algorithm. Excluding other arrhythmias and Noise, the sensitivity for atrial fibrillation detection was 0.963 (95% CI lower bound 0.894), and the specificity was 1.000 (95% CI lower bound 0.967). Visibility and polarity accuracies were similar (1-lead electrocardiogram: P waves: 96.9%, QRS complexes: 99.2%, T waves: 91.2%; 12-lead electrocardiogram: P waves: 100%, QRS complexes: 98.8%, T waves: 99.5%). P-wave visibility accuracy was 99% (99/100) for patients with atrial fibrillation and 95.7% (155/162) for patients with normal sinus rhythm, other arrhythmias, and unreadable electrocardiograms. The absolute values of the mean differences in PR duration and QRS width were <3 ms, and more than 97% were <40 ms. The mean difference between the heart rates from the 1-lead electrocardiogram calculated by the algorithm and those calculated by cardiologists was 0.55 bpm. CONCLUSIONS: The algorithm demonstrated great diagnostic performance for atrial fibrillation detection. The smartwatch's single-lead electrocardiogram also demonstrated good quality for physician use in daily routine care. TRIAL REGISTRATION: ClinicalTrials.gov NCT04351386; http://clinicaltrials.gov/ct2/show/NCT04351386.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".