Evaluation of ChatGPT as a Counselling Tool for Italian-Speaking MASLD Patients: Assessment of Accuracy, Completeness and Comprehensibility
Bibliographic record
Abstract
BACKGROUND: Artificial intelligence (AI)-based chatbots have shown promise in providing counseling to patients with metabolic dysfunction-associated steatotic liver disease (MASLD). While ChatGPT3.5 has demonstrated the ability to comprehensively answer MASLD-related questions in English, its accuracy remains suboptimal. Whether language influences these results is unclear. This study aims to assess ChatGPT's performance as a counseling tool for Italian MASLD patients. METHODS: Thirteen Italian experts rated the accuracy, completeness and comprehensibility of ChatGPT3.5 in answering 15 MASLD-related questions in Italian using a six-point accuracy, three-point completeness and three-point comprehensibility Likert's scale. RESULTS: Mean scores for accuracy, completeness and comprehensibility were 4.57 ± 0.42, 2.14 ± 0.31 and 2.91 ± 0.07, respectively. The physical activity domain achieved the highest mean scores for accuracy and completeness, whereas the specialist referral domain achieved the lowest. Overall, Fleiss's coefficient of concordance for accuracy, completeness and comprehensibility across all 15 questions was 0.016, 0.075 and -0.010, respectively. Age and academic role of the evaluators did not influence the scores. The results were not significantly different from our previous study focusing on English. CONCLUSION: Language does not appear to affect ChatGPT's ability to provide comprehensible and complete counseling to MASLD patients, but accuracy remains suboptimal in certain domains.
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 | 0.014 | 0.043 |
| Meta-epidemiology (narrow) | 0.001 | 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) | 0.004 | 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".