Patients Ask, AI Answers: An Evaluation of ChatGPT-4o Responses to the Most Frequently Googled Questions on Laparoscopic Hysterectomy Hasta Eğitiminde Yapay Zeka: Laparoskopik Histerektomi Hakkında Google’da En Sık Aranan Sorulara ChatGPT-4o Yanıtlarının Değerlendirilmesi
Anatolian Journal of General Medical Research, cilt.36, sa.1, ss.84-89, 2026 (Scopus, TRDizin)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 36 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.4274/anatoljmed.2026.97759
- Dergi Adı: Anatolian Journal of General Medical Research
- Derginin Tarandığı İndeksler: Scopus, TR DİZİN (ULAKBİM)
- Sayfa Sayıları: ss.84-89
- Anahtar Kelimeler: artificial intelligence, ChatGPT, Laparoscopic hysterectomy, minimally invasive surgical procedures, patient education
- Sağlık Bilimleri Üniversitesi Adresli: Evet
Özet
Objective: Patients increasingly use search engines and artificial intelligence-based tools to obtain medical information prior to surgical consultations. This study aimed to evaluate the quality of ChatGPT-4o’s responses to the patient questions most frequently searched on Google regarding laparoscopic hysterectomy. Methods: This expert-based evaluation identified the most frequently searched patient questions on Google regarding laparoscopic hysterectomy using a newly created Google account with no prior search history. After eliminating duplicates, 24 unique questions were included. Each question was independently presented to ChatGPT-4o using a new account with no prior conversation history. Ten experienced gynecologic surgeons evaluated each response across four domains: accuracy, clarity, completeness, and relevance, using a five-point Likert scale. Descriptive statistics were calculated, and interrater reliability was assessed using intraclass correlation coefficients. Results: Mean scores across all questions were 4.36 for accuracy, 4.55 for clarity, 4.21 for completeness, and 4.59 for relevance. No responses received a score below 3 in any domain. Interrater reliability varied across evaluation domains. Overall, ChatGPT-4o responses were perceived as highly relevant and easy to understand, with comparatively lower scores for completeness. Conclusion: ChatGPT-4o provides responses to common online queries about laparoscopic hysterectomy that are generally accurate, relevant, and clearly presented. However, limitations in completeness highlight the need for clinician-led counseling. Artificial intelligence-generated information may serve as a supplementary resource for patient education but should not replace professional medical guidance.