Answering Hospital Caregivers’ Questions at Any Time: Proof-of-Concept Study of an Artificial Intelligence–Based Chatbot in a French Hospital
Bibliographic record
Abstract
BACKGROUND: Access to accurate information in health care is a key point for caregivers to avoid medication errors, especially with the reorganization of staff and drug circuits during health crises such as the COVID‑19 pandemic. It is, therefore, the role of the hospital pharmacy to answer caregivers' questions. Some may require the expertise of a pharmacist, some should be answered by pharmacy technicians, but others are simple and redundant, and automated responses may be provided. OBJECTIVE: We aimed at developing and implementing a chatbot to answer questions from hospital caregivers about drugs and pharmacy organization 24 hours a day and to evaluate this tool. METHODS: The ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model was used by a multiprofessional team composed of 3 hospital pharmacists, 2 members of the Innovation and Transformation Department, and the IT service provider. Based on an analysis of the caregivers' needs about drugs and pharmacy organization, we designed and developed a chatbot. The tool was then evaluated before its implementation into the hospital intranet. Its relevance and conversations with testers were monitored via the IT provider's back office. RESULTS: Needs analysis with 5 hospital pharmacists and 33 caregivers from 5 health services allowed us to identify 7 themes about drugs and pharmacy organization (such as opening hours and specific prescriptions). After a year of chatbot design and development, the test version obtained good evaluation scores: its speed was rated 8.2 out of 10, usability 8.1 out of 10, and appearance 7.5 out of 10. Testers were generally satisfied (70%) and were hoping for the content to be enhanced. CONCLUSIONS: The chatbot seems to be a relevant tool for hospital caregivers, helping them obtain reliable and verified information they need on drugs and pharmacy organization. In the context of significant mobility of nursing staff during the health crisis due to the COVID-19 pandemic, the chatbot could be a suitable tool for transmitting relevant information related to drug circuits or specific procedures. To our knowledge, this is the first time that such a tool has been designed for caregivers. Its development further continued by means of tests conducted with other users such as pharmacy technicians and via the integration of additional data before the implementation on the 2 hospital sites.
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 | 0.022 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.000 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".