Assessment of ChatGPT-generated medical Arabic responses for patients with metabolic dysfunction–associated steatotic liver disease

• DOI: 10.1371/journal.pone.0317929
• Publication Date: 2025-02-03T18:25:43Z
• Authors: Saleh A. Alqahtani; Reem S. AlAhmed; Waleed S. AlOmaim; Saad Alghamdi; Waleed Al-Hamoudi; Khalid Ibrahim Bz...; Ali Albenmousa; Alessio Aghemo; Nicola Pugliese; Cesare Hassan; Faisal A. Abaalkhail
• Keywords: Concordance

Background and aim Artificial intelligence (AI)-powered chatbots, such as Chat Generative Pretrained Transformer (ChatGPT), have shown promising results in healthcare settings. These tools can help patients obtain real-time responses to queries, ensuring immediate access relevant information. The study aimed explore the potential use of ChatGPT-generated medical Arabic for with metabolic dysfunction–associated steatotic liver disease (MASLD). Methods An English patient questionnaire on MASLD was translated Arabic. questions were then entered into ChatGPT 3.5 November 12, 2023. evaluated accuracy, completeness, comprehensibility by 10 Saudi experts who native speakers. Likert scales used evaluate: 1) Accuracy, 2) Completeness, 3) Comprehensibility. grouped 3 domains: (1) Specialist referral, (2) Lifestyle, (3) Physical activity. Results Accuracy mean score 4.9 ± 0.94 a 6-point scale corresponding “Nearly all correct.” Kendall’s coefficient concordance (KCC) ranged from 0.025 0.649, 0.28, indicating moderate agreement between experts. Mean completeness 2.4 0.53 3-point “Comprehensive” (KCC: 0.03–0.553; mean: 0.22). Comprehensibility 2.74 0.52 scale, which indicates “Easy understand” 0.00–0.447; 0.25). Conclusion found that accurate, complete, comprehensible. support increasing trend leveraging power AI chatbots revolutionize dissemination information MASLD. However, many AI-powered require further enhancement scientific content avoid risks circulating misinformation.