Abstract 17679: Automating Cardiopulmonary Resuscitation Quality Data Abstraction for Entire Episodes of Cardiac Arrest Resuscitation
Bibliographic record
Abstract
Introduction: Research and quality assessment of cardiopulmonary resuscitation (CPR) quality has traditionally been limited to the first five minutes of resuscitation due to significant costs in both time and personnel from manual data abstraction. Manual CPR quality data abstraction of entire episodes of resuscitation may be too resource-intensive for many emergency medical service (EMS) agencies and hospitals. Moreover, the first five minutes of CPR are also different in many aspects compared to later time periods during cardiac arrest resuscitation, which represents significant knowledge gaps since the majority of resuscitations go beyond five minutes. Methods: We developed a software program to facilitate and help automate data abstraction from electronic defibrillator files for entire resuscitation episodes. Internal validation of the software program was performed on 50 randomly selected out-of-hospital cardiac arrest cases with resuscitation durations up to 60 minutes. CPR quality data variables were abstracted as minute averages, which included ventilation rate, CPR compression rate, depth, fraction, and end-tidal CO2. CPR quality data variables were manually abstracted independently by two trained data abstractors and automatically by the software program. Error rates and the time needed for data abstraction were measured. Results: A total of 9826 data points were abstracted. Manual data abstraction resulted in a total of six errors (0.06%) compared to zero errors by the software program. The mean time ± SD needed for data abstraction was 20.3 ± 2.7 minutes manually and 5.3 ± 1.4 minutes using the software program (p=0.003). Conclusion: Our data abstraction software was 100% accurate in abstracting CPR quality data for complete cardiac arrest resuscitation episodes. It significantly reduced the time and resources required to abstract CPR quality data, and will allow EMS agencies and hospitals to evaluate their CPR quality in a cost-effective manner. The development of this software will enable future studies to efficiently evaluate CPR quality during entire resuscitation episodes, including its impact on patient outcomes during prolonged cardiac arrests.
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 | 0.023 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".