Detection of Atrial Fibrillation in Compressively Sensed Electrocardiogram for Remote Monitoring
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The objective of this paper is to develop an optimized system to detect Atrial Fibrillation (AF) in compressively sensed electrocardiogram (ECG) for long-term remote patient monitoring. A three-stage system was developed to 1) reject ECG of poor signal quality, 2) detect AF in compressively sensed ECG, and 3) detect AF in selectively reconstructed ECG. The Long-Term AF Database (LTAFDB), sampled at 128 Hz using a 12-bit ADC with a range of 20 mV, was used to validate the system. The LTAFDB had 83,315 normal and 82,435 AF rhythm 30 s ECG segments. Clean ECG from the LTAFDB was artificially contaminated with motion artifact to achieve −12 to 12 dB Signal-to-Noise Ratio (SNR) in steps of 3 dB. The contaminated ECG was compressively sensed at 50% and 75% compression ratio (CR). The system was evaluated using average precision (AP), the area under the curve (AUC) of the receiver operator characteristic curve, and the F1 score. The system was optimized to maximize the AP and minimize ECG rejection and reconstruction ratios. The optimized system for 50% CR had 0.72 AP, 0.63 AUC, and 0.58 F1 score, 0.38 rejection ratio, and 0.38 reconstruction ratio. The optimized system for 75% CR had 0.72 AP, 0.63 AUC, and 0.59 F1 score, 0.40 rejection ratio, and 0.35 reconstruction ratio. Challenges for long-term AF monitoring are the short battery life of monitors and the high false alarm rate due to artifacts. The proposed system improves the short battery life through compressive sensing while reducing false alarms (high AP) and ECG reconstruction (low reconstruction ratio).
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.
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 | 0.000 | 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 | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| 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 it