Evaluating ChatGPT-3.5 in allergology: performance in the Polish Specialist Examination
Bibliographic record
Abstract
Introduction:The development of Artificial Intelligence (AI) and attempts to use it in medicine are increasingly becoming the subject of more scientific research.Aim: The aim of this article is to present the effectiveness of the advanced language model, ChatGPT-3.5 in the context of the pass rate of the Polish National Specialist Examination (PES) in allergology.Additionally, it seeks to comprehend the potential applications of artificial intelligence in the field of medicine, particularly within allergology. Material and methods:The study used the latest available PES exam prepared by the Medical Research Centre in Lodz.118 questions were asked using the openai.complatform, which allows free access to the ChatGPT-3.5model.All questions were classified according to Bloom's taxonomy to assess their complexity and difficulty, with additional three categorisations.Each question was asked five times.Results: ChatGPT-3.5 did not pass the allergology PES, achieving a score of 52.54%.It was observed that the model performed better in answering memory questions (60%) compared to those requiring comprehension and critical thinking, where the results were slightly lower (45%).Moreover, within the categories of 'treatment' , 'immune system' and 'symptoms' , the model exceeded the passing threshold.Questions to which ChatGPT provided the correct answer significantly exhibited higher difficulty compared to those to which it provided an incorrect response. Conclusions:The results indicate that ChatGPT's pass rate in the allergology PES is considerably lower than that of resident doctors specializing in this field.The potential applications of AI in medicine require further research to effectively support clinical practice among physicians.
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 | 0.010 | 0.028 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".