Abstract 13937: Electrocardiography-Derived Respiratory Rate Detects Clinical Deterioration in Acute Care Patients With Cardiovascular Disease
Bibliographic record
Abstract
Introduction: Clinical deterioration resulting in ICU transfer occurs in 4 to 5 of every 100 acute care admissions. Early Warning Scores (EWS) identify high risk patients, but rely on intermittent assessments. Continuous ECG not only provides heart rate (HR) and rhythm, but can also estimate respiratory rate (RR). Hypothesis: Continuous ECG data improves the predictive validity of EWS prior to acute deterioration leading to ICU transfer or unanticipated death. Methods: Among floor patients admitted with continuous ECG, we identified those with deterioration resulting in ICU transfer or unanticipated death. We analyzed 60 patient-years of ECG data and applied previously validated methodologies for detection of atrial fibrillation (AF) and estimation of RR. We evaluated the predictive validity of common EWS and compared them to models that incorporate ECG data. We excluded observations after DNR/DNI orders or transitions to comfort care. We calculated the fold change in mortality, and the predictive validity (C-statistic). Results: From 8,033 consecutive admissions, we identified 544 instances of clinical deterioration in 508 admissions. Admissions with events had a 50-fold increase in mortality (19.8% vs 0.4%) despite unexpected deaths accounting for only 6% of all events. We analyzed the 274 deteriorations that had ECG data in the 24-hours leading up to events. EWS had C-statistics ranging from 0.63 to 0.70. A model using only ECG-derived measurements had a C-statistic of 0.67 and the strongest predictors included RR, HR, and AF. Addition of the ECG-only model to the best EWS improved its C-statistic to 0.72. Conclusions: Continuous ECG data improves the ability of intermittent EWS to identify the highest risk patients up to 24-hours in advance of acute clinical deterioration.
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 | 0.005 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".