AI-Enhanced Speech Recognition in Triage.
Bibliographic record
Abstract
Triage is used in emergency departments to ensure timely patient care according to urgency of treatment. However, triage accuracy and efficiency remain challenging due to time-constraints and high demand. This proof-of-concept study evaluates an AI-powered triage system that leverages speech recognition (STT) and large language models (LLMs) to process patient interactions in triage and to assign an Emergency Severity Index (ESI) triage level and a classification of the main presenting complaint according to the Canadian Emergency Department Information System (CEDIS). In Switzerland, different Swiss German dialects add to the complexity of the task. STT models achieved word error rates (WER) of 2.3% for High German and 17.66% for Swiss German. Despite the high WER, the AI's classification accuracy reached 90-100% for ESI levels and CEDIS codes. These results highlight the potential of integrating AI into triage workflows, enhancing consistency and reducing the documentation burden for clinical staff. Future research should address multi-language adaptation and data security to ensure seamless implementation in real-world settings.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.004 | 0.005 |
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".