The effectiveness and efficiency of using ChatGPT for writing health care simulations
Bibliographic record
Abstract
Simulation is a crucial part of health professions education that provides essential experiential learning. Simulation training is also a solution to logistical constraints around clinical placement time and is likely to expand in the future. Large language models, most specifically ChatGPT, are stirring debate about the nature of work, knowledge and human relationships with technology. For simulation, ChatGPT may present a solution to help expand the use of simulation by saving time and costs for simulation development. To understand if ChatGPT can be used to write health care simulations effectively and efficiently, simulations written by a subject matter expert (SME) not using ChatGPT and a non-SME writer using ChatGPT were compared. Simulations generated by each group were submitted to a blinded Expert Review. Simulations were evaluated holistically for preference, overall quality, flaws and time to produce. The SME simulations were selected more frequently for implementation and were of higher quality, though the quality for multiple simulations was comparable. Preferences and flaws were identified for each set of simulations. The SME simulations tended to be preferred based on technical accuracy while the structure and flow of the ChatGPT simulations were preferred. Using ChatGPT, it was possible to write simulations substantially faster. Health Profession Educators can make use of ChatGPT to write simulations faster and potentially create better simulations. More high-quality simulations produced in a shorter amount of time can lead to time and cost savings while expanding the use of simulation.
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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".