Appropriateness and Comprehensiveness of Using ChatGPT for Perioperative Patient Education in Thoracic Surgery in Different Language Contexts: Survey Study
Bibliographic record
Abstract
BACKGROUND: ChatGPT, a dialogue-based artificial intelligence language model, has shown promise in assisting clinical workflows and patient-clinician communication. However, there is a lack of feasibility assessments regarding its use for perioperative patient education in thoracic surgery. OBJECTIVE: This study aimed to assess the appropriateness and comprehensiveness of using ChatGPT for perioperative patient education in thoracic surgery in both English and Chinese contexts. METHODS: This pilot study was conducted in February 2023. A total of 37 questions focused on perioperative patient education in thoracic surgery were created based on guidelines and clinical experience. Two sets of inquiries were made to ChatGPT for each question, one in English and the other in Chinese. The responses generated by ChatGPT were evaluated separately by experienced thoracic surgical clinicians for appropriateness and comprehensiveness based on a hypothetical draft response to a patient's question on the electronic information platform. For a response to be qualified, it required at least 80% of reviewers to deem it appropriate and 50% to deem it comprehensive. Statistical analyses were performed using the unpaired chi-square test or Fisher exact test, with a significance level set at P<.05. RESULTS: The set of 37 commonly asked questions covered topics such as disease information, diagnostic procedures, perioperative complications, treatment measures, disease prevention, and perioperative care considerations. In both the English and Chinese contexts, 34 (92%) out of 37 responses were qualified in terms of both appropriateness and comprehensiveness. The remaining 3 (8%) responses were unqualified in these 2 contexts. The unqualified responses primarily involved the diagnosis of disease symptoms and surgical-related complications symptoms. The reasons for determining the responses as unqualified were similar in both contexts. There was no statistically significant difference (34/37, 92% vs 34/37, 92%; P=.99) in the qualification rate between the 2 language sets. CONCLUSIONS: This pilot study demonstrates the potential feasibility of using ChatGPT for perioperative patient education in thoracic surgery in both English and Chinese contexts. ChatGPT is expected to enhance patient satisfaction, reduce anxiety, and improve compliance during the perioperative period. In the future, there will be remarkable potential application for using artificial intelligence, in conjunction with human review, for patient education and health consultation after patients have provided their informed consent.
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 | 0.017 | 0.052 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".