Artificial Intelligence in cardiopulmonary resuscitation training – A scoping review
Bibliographic record
Abstract
Objectives: This scoping review aimed to identify Artificial Intelligence methods used in cardiopulmonary resuscitation (CPR) training. Methods: Members of the writing group 'Education for Resuscitation' of the European Resuscitation Council 2025 guidelines used the PICOST format for this scoping review, which included only published randomized and non-randomized studies. Medline, Embase, Cochrane, Education Resources Information Center, Web of Science, and PubMed were searched from inception to July 2025. Title and abstract screening, full-text review, and data extraction were performed by two researchers in pairs. PRISMA reporting standards were followed. The review was registered at PROSPERO. Because the evidence was insufficient for a systematic review, we changed our initial plan and performed a scoping review. Results: The search identified 6977 citations. After removing 2521 duplicates, reviewing titles and abstracts yielded 43 articles for full-text review. Of these, 15 studies were included in the final analysis. Our findings reveal that Artificial Intelligence is being explored across key areas of CPR training, including its accuracy in detecting CPR quality parameters, providing real-time feedback, creating personalized training experiences, detecting and analyzing dialog segments during and after simulation, generating medical teaching illustrations, its capacity for interactive simulations, and answering laypersons' medical questions. Conclusion: Artificial Intelligence shows potential for transforming CPR training via enhancing real-time feedback, enabling personalized learning, improving dialog analysis, facilitating content creation, and serving as an information source. The current evidence is dominated by proof-of-concept studies. Future research needs to establish the efficacy of Artificial Intelligence-supported CPR training compared to traditional methods.
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 | 0.028 | 0.090 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.006 | 0.006 |
| Bibliometrics | 0.025 | 0.021 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.005 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 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".