The Utility and Limitations of Artificial Intelligence-Powered Chatbots in Healthcare
Bibliographic record
Abstract
At the intersection of artificial intelligence (AI) and healthcare, it is essential that clinicians grasp the ability of chatbots. AI-powered chatbots such as ChatGPT are being explored for their potential benefits by both individuals and institutions. The utility of ChatGPT (OpenAI) in various scenarios was explored through a series of recorded prompts and responses. In the clinical aspects, the chatbot facilitated tasks such as triage, patient consultation, diagnosis, and administrative responsibilities. Their capacity to translate and simplify intricate medical topics was also evaluated. For research purposes, the chatbots' abilities to suggest ideas, prepare protocols, assist in manuscript writing, guide statistical analyses, and recommend suitable journals were assessed. In the educational domain, chatbots were tested for simplifying complex subjects, reviewing procedural steps, generating clinical scenarios, and formulating multiple-choice questions. A comprehensive literature review was also conducted across Medline, Embase, and Web of Science. Chatbots, when optimally employed, can serve as invaluable resources in healthcare, spanning clinical, research, and educational domains. Their potential lies in enhancing efficiency, guiding decision-making, and facilitating patient care and education. However, their application requires a nuanced understanding and caution regarding their limitations.
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 | 0.165 | 0.392 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.006 | 0.004 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.011 | 0.013 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".