Evaluation of ChatGPT-4 as an Online Outpatient Assistant in Puerperal Mastitis Management: Content Analysis of an Observational Study
Bibliographic record
Abstract
Background: The integration of artificial intelligence (AI) into clinical workflows holds promise for enhancing outpatient decision-making and patient education. ChatGPT, a large language model developed by OpenAI, has gained attention for its potential to support both clinicians and patients. However, its performance in the outpatient setting of general surgery remains underexplored. Objective: This study aimed to evaluate whether ChatGPT-4 can function as a virtual outpatient assistant in the management of puerperal mastitis by assessing the accuracy, clarity, and clinical safety of its responses to frequently asked patient questions in Turkish. Methods: Fifteen questions about puerperal mastitis were sourced from public health care websites and online forums. These questions were categorized into general information (n=2), symptoms and diagnosis (n=6), treatment (n=2), and prognosis (n=5). Each question was entered into ChatGPT-4 (September 3, 2024), and a single Turkish-language response was obtained. The responses were evaluated by a panel consisting of 3 board-certified general surgeons and 2 general surgery residents, using five criteria: sufficient length, patient-understandable language, accuracy, adherence to current guidelines, and patient safety. Quantitative metrics included the DISCERN score, Flesch-Kincaid readability score, and inter-rater reliability assessed using the intraclass correlation coefficient (ICC). Results: A total of 15 questions were evaluated. ChatGPT's responses were rated as "excellent" overall by the evaluators, with higher scores observed for treatment- and prognosis-related questions. A statistically significant difference was found in DISCERN scores across question types (P=.01), with treatment and prognosis questions receiving higher ratings. In contrast, no significant differences were detected in evaluator-based ratings (sufficient length, understandability, accuracy, guideline compliance, and patient safety), JAMA benchmark scores, or Flesch-Kincaid readability levels (P>.05 for all). Interrater agreement was good across all evaluation parameters (ICC=0.772); however, agreement varied when assessed by individual criteria. Correlation analyses revealed no significant overall associations between subjective ratings and objective quality measures, although a strong positive correlation between literature compliance and patient safety was identified for one question (r=0.968, P<.001). Conclusions: ChatGPT demonstrated adequate capability in providing information on puerperal mastitis, particularly for treatment and prognosis. However, evaluator variability and the subjective nature of assessments highlight the need for further optimization of AI tools. Future research should emphasize iterative questioning and dynamic updates to AI knowledge bases to enhance reliability and accessibility.
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 | 0.012 | 0.049 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".