The Potential of GPT-4 as a Support Tool for Pharmacists: Analytical Study Using the Japanese National Examination for Pharmacists
Bibliographic record
Abstract
BACKGROUND: The advancement of artificial intelligence (AI), as well as machine learning, has led to its application in various industries, including health care. AI chatbots, such as GPT-4, developed by OpenAI, have demonstrated potential in supporting health care professionals by providing medical information, answering examination questions, and assisting in medical education. However, the applicability of GPT-4 in the field of pharmacy remains unexplored. OBJECTIVE: This study aimed to evaluate GPT-4's ability to answer questions from the Japanese National Examination for Pharmacists (JNEP) and assess its potential as a support tool for pharmacists in their daily practice. METHODS: The question texts and answer choices from the 107th and 108th JNEP, held in February 2022 and February 2023, were input into GPT-4. As GPT-4 cannot process diagrams, questions that included diagram interpretation were not analyzed and were initially given a score of 0. The correct answer rates were calculated and compared with the passing criteria of each examination to evaluate GPT-4's performance. RESULTS: For the 107th and 108th JNEP, GPT-4 achieved an accuracy rate of 64.5% (222/344) and 62.9% (217/345), respectively, for all questions. When considering only the questions that GPT-4 could answer, the accuracy rates increased to 78.2% (222/284) and 75.3% (217/287), respectively. The accuracy rates tended to be lower for physics, chemistry, and calculation questions. CONCLUSIONS: Although GPT-4 demonstrated the potential to answer questions from the JNEP and support pharmacists' capabilities, it also showed limitations in handling highly specialized questions, calculation questions, and questions requiring diagram recognition. Further evaluation is necessary to explore its applicability in real-world clinical settings, considering the complexities of patient scenarios and collaboration with health care professionals. By addressing these limitations, GPT-4 could become a more reliable tool for pharmacists in their daily practice.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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".