Ai Chatbots In Emergency Medicine: Analyzing Agreement with Expert Physician Triage Decisions
Bibliographic record
Abstract
Introduction In emergency medicine, accurate triage is vital for patient outcomes and resource management. The Canadian Triage and Acuity Scale (CTAS) has been essential in training healthcare providers to make prompt and precise triage decisions.1 With the rise of artificial intelligence (AI), chatbots are being considered for their potential to support or even replace human decision-making in various medical situations. This study aims to assess the agreement between AI chatbot triage decisions and those made by experienced emergency physicians using CTAS. Methods This study involved a comparative analysis between an AI chatbot and two expert emergency physicians, each with over ten years of experience. We used a dataset of 60 emergency case scenarios, which have been utilized for over 8-10 years to train medical personnel at the start of their careers.1 The AI chatbot received training materials on CTAS and triage before being tasked with assigning appropriate triage levels for each scenario. Meanwhile, the expert physicians independently triaged the same cases. Scenarios where the two experts disagreed on the triage level were excluded, leaving 35 case scenarios for the final analysis. To evaluate the agreement between the AI chatbot and the expert physicians, we used the Cohen's Kappa coefficient. This included determining the Cohen's Kappa coefficient value, the p-value, and the 95% confidence interval (CI) to assess the statistical significance and reliability of the agreement. Results The Cohen's Kappa coefficient value between the AI chatbot and the expert physicians was 0.721, indicating a substintial level of agreement. The p-value was
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 | 0.045 | 0.224 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".