Electrocardiogram Signal Quality Analysis to Reduce False Alarms in Myocardial Ischemia Monitoring
Bibliographic record
Abstract
The probability of myocardial ischemia, reduction in blood flow to the heart muscle, is increased following a non-cardiac surgery, which can lead to an increase in the incidence of post-operative heart attacks, cardiac death, and increase in hospital length of stay among patients.β-Blockers can be administered to reduce the probability of experiencing a cardiac event post a non-cardiac surgery; however, they have side effects including stroke, bradycardia, hypotension, morbidity, and mortality.Myocardial ischemia causes a deviation of ST segment in the electrocardiogram (ECG), which can enable targeted administration of β-Blockers rather than prophylactic administration; however, attempts to utilize ECG as a diagnostic tool in real-time were hindered by a large number of false alarms due to noise and error in the quantification of ST segment deviation.The objective of this thesis is to develop a system to gate false alarms using the signal quality of the ECG and quality of the ST segment deviation estimate.The system was tested using ECG records from Physionet's Long-Term ST Database (LTSTDB) that were contaminated with motion artifact noise from Physionet's MIT-BIH Noise Stress Test Database (NSTDB).The system based on signal quality and ST segment trend estimation gated 100% of noiseinduced alarms (86% of all false alarms) attaining a recall and precision of 0.72 and 0.73, respectively, marking an increase of 0.42 in precision and a decrease of 0.05 in recall from the commercial bedside monitor baseline performance (precision -0.31, recall -0.78).The signal quality analysis approach to gate contaminated data was extended to an ECG biometrics system.The signal quality analysis led to the rejection of 193 (57.8%) out of 334 false identifications at the loss of 25 (8.14%) out of 307 true identifications.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".