Yapay Zeka Destekli Gebelik Danışmanlığı Uygulanabilir mi? ChatGPT Yanıtlarının Kalitesinin Değerlendirilmesi

Öz

Giriş: Gebelik döneminde sıkça sorulan sorulara ChatGPT tarafından üretilen yanıtların kalitesini, uzman değerlendirmelerine dayalı olarak ve tanımlı kriterler (doğruluk, eksiksizlik ve güvenlik) üzerinden değerlendirmek. Yöntem: Toplam 20 kadın hastalıkları ve doğum uzmanı, gebelikle ilgili sık karşılaşılan 15 soruya ChatGPT tarafından verilen yanıtları değerlendirmiştir. Her yanıt, üç alanda 5 puanlık Likert ölçeği ile puanlanmıştır. Kriterler ve soru kategorileri arasındaki farkları değerlendirmek için istatistiksel karşılaştırmalar yapılmıştır. Bulgular: ChatGPT, tüm kriterler üzerinden ortalama 4,1 puan almıştır. En yüksek puan doğruluk kriterinden elde edilmiştir (ortalama 4,27 ± 0,31), ardından eksiksizlik (3,85 ± 0,30) ve güvenlik (3,78 ± 0,36) gelmektedir (P = 0,019). Genel bilgi sorularına verilen yanıtlar, semptomlar veya takip önerileriyle ilgili sorulara göre anlamlı düzeyde daha yüksek puanlanmıştır (P = 0,041). En yüksek puanlanan yanıt gebelikte uyku pozisyonları ile ilgili olurken (ortalama 4,5), en düşük puanı ağrı kesici güvenliği ile ilgili yanıt almıştır (ortalama 3,5). Sonuç: ChatGPT, gebelikle ilgili doğru ve anlaşılır bilgi sunma konusunda güçlü bir potansiyel göstermektedir. Ancak özellikle semptom odaklı konularda klinik güvenlik ve bilgi eksiksizliği açısından sınırlılıkları bulunmaktadır. Bu nedenle profesyonel tıbbi danışmanlığın yerine değil, tamamlayıcı bir bilgi kaynağı olarak kullanılmalıdır. Hastaya yönelik eğitimde güvenli entegrasyonu sağlamak için farklı klinik senaryolarda ve standartlaştırılmış değerlendirme araçlarıyla daha fazla doğrulama çalışması gereklidir.

Anahtar Kelimeler

• ChatGPT
• yapay zeka
• gebelik
• doğum
• hasta eğitimi
• tıbbi güvenlik
• uzman değerlendirmesi

Is Artificial Intelligence-Assisted Pregnancy Counseling Feasible? An Evaluation of the Quality of ChatGPT Responses

Abstract

Objective: To evaluate the quality of ChatGPT-generated responses to commonly asked questions during pregnancy, based on expert assessments using predefined criteria: accuracy, completeness, and safety. Methods: A total of 20 board-certified obstetricians evaluated 15 ChatGPT-generated responses to frequently encountered pregnancy-related questions. Each response was assessed using a 5-point Likert scale across three domains. Statistical comparisons were conducted to evaluate differences among criteria and question categories. Results: ChatGPT received an overall mean score of 4.1 across all criteria. Accuracy was the highest-rated criterion (mean 4.27 ± 0.31), followed by completeness (3.85 ± 0.30) and safety (3.78 ± 0.36) (P = 0.019). Responses to general knowledge questions scored significantly higher than those related to symptoms or follow-up guidance (P = 0.041). The most favorably rated response pertained to sleep positions during pregnancy (mean 4.5), while painkiller safety scored the lowest (mean 3.5). Conclusion: ChatGPT demonstrates strong potential in delivering accurate and comprehensible pregnancy-related information. However, its limitations in clinical safety and completeness—particularly in symptom-related topics—suggest that it should be used as an adjunct to, not a replacement for, professional medical guidance. Further validation across diverse clinical scenarios and standardized evaluation tools is necessary to ensure safe integration into patient education.

Keywords

• ChatGPT
• artificial intelligence
• pregnancy
• obstetrics
• patient education
• medical safety
• expert evaluation

Kaynakça

1. 1. Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023;11(6):887. [Crossref]
2. 2. Ayers JW, Poliak A, Dredze M, et al. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med. 2023;183(6):589–96. [Crossref]
3. 3. Ługowski F, Babińska J, Ludwin A, Stanirowski PJ. Comparative analysis of ChatGPT 3.5 and ChatGPT 4 obstetric and gynecological knowledge. Sci Rep. 2025;15(1):21133. [Crossref]
4. 4. Yeşilçinar İ, Güvenç G, Kinci MF, Bektaş Pardes B, Kök G, Sivaslioğlu AA. Knowledge, fear, and anxiety levels among pregnant women during the COVID-19 pandemic: a cross-sectional study. Clin Nurs Res. 2022;31(4):758–65. [Crossref]
5. 5. Yeşilçinar İ, Kinci MF, Ünver HC, Sivaslioğlu AA. Pregnancy-related anxiety and prenatal attachment in pregnant women with preeclampsia and/or gestational diabetes mellitus: a cross-sectional study. J Clin Obstet Gynecol. 2023;33(1):27–35. [Crossref]
6. 6. Soma-Pillay P, Nelson-Piercy C, Tolppanen H, Mebazaa A. Physiological changes in pregnancy. Cardiovasc J Afr. 2016;27(2):89–94. [Crossref]
7. 7. Peled T, Sela HY, Weiss A, Grisaru-Granovsky S, Agrawal S, Rottenstreich M. Evaluating the validity of ChatGPT responses on common obstetric issues: potential clinical applications and implications. Int J Gynecol Obstet. 2024;166(3):1127–33. [Crossref]
8. 8. Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit Health. 2023;2(2):e0000198. [Crossref]

9. 9. Gilson A, Safranek CW, Huang T, et al. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9:e45312. [Crossref]
10. 10. Jeblick K, Schachtner B, Dexl J, et al. ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur Radiol. 2024;34(5):2817–25. [Crossref]
11. 11. Sinha RK, Deb Roy A, Kumar N, Mondal H. Applicability of ChatGPT in assisting to solve higher order problems in pathology. Cureus. 2023;15(2):e35237. [Crossref]
12. 12. Yan D, Li H. Can ChatGPT provide comparable answers to common questions about cervical cancer to doctors in Chinese? Int J Gynecol Cancer. 2024;34(2):307–10. [Crossref]
13. 13. Sallam M, Salim NA, Barakat M, Al-Tammemi AB. ChatGPT applications in medical, health sciences, scientific, and research education: ChatGPT in higher education. A Jordanian medley. Adv Med Educ Pract. 2023;14:61–77. [Crossref]
14. 14. Sallam M, Salim NA, Al-Tammemi AB, et al. ChatGPT output regarding compulsory vaccination and COVID-19 vaccine conspiracy: a descriptive study at the outset of a paradigm shift in online search for information. Cureus. 2023;15(2):e35029. [Crossref]
15. 15. De Angelis L, Baglivo F, Arzilli G, et al. ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health. Front Public Health. 2023;11:1166120. [Crossref]
16. 16. Rahsepar AA, Tavakoli N, Kim GHJ, Hassani C, Abtin F, Bedayat A. How AI responds to common lung cancer questions: ChatGPT vs Google Bard. Radiology. 2023;307(5):e230922. [Crossref]
17. 17. Dave T, Athaluri SA, Singh S. ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell. 2023;6:1169595. [Crossref]
18. 18. Flanagin A, Bibbins-Domingo K, Berkwits M, Christiansen SL. Nonhuman “authors” and implications for the integrity of scientific publication and medical knowledge. JAMA. 2023;329(8):637–9. [Crossref]
19. 19. da Silva JAT. Is ChatGPT a valid author? Nurse Educ Pract. 2023;68:103600. [Crossref]
20. 20. Hill-Yardin EL, Hutchinson MR, Laycock R, Spencer SJ. A chat(GPT) about the future of scientific publishing. Brain Behav Immun. 2023;110:152–4. [Crossref]
21. 21. Elenskaia K, Haidvogel K, Heidinger C, Doerfler D, Umek W, Hanzal E. The greatest taboo: urinary incontinence as a source of shame and embarrassment. Wien Klin Wochenschr. 2011;123(19-20):607–10. [Crossref]
22. 22. Horrocks S, Somerset M, Stoddart H, Peters TJ. What prevents older people from seeking treatment for urinary incontinence? A qualitative exploration of barriers to the use of community continence services. Fam Pract. 2004;21(6):689–96. [Crossref]
23. 23. Koch LH. Help-seeking behaviors of women with urinary incontinence: an integrative literature review. J Midwifery Womens Health. 2006;51(6):e39–44. [Crossref]
24. 24. Thirunavukarasu AJ, Hassan R, Mahmood S, et al. Trialling a large language model (ChatGPT) in general practice with the applied knowledge test: observational study demonstrating opportunities and limitations in primary care. JMIR Med Educ. 2023;9:e46599. [Crossref]
25. 25. Lazzerini M, Barbi E, Apicella A, Marchetti F, Cardinale F, Trobia G. Delayed access or provision of care in Italy resulting from fear of COVID-19. Lancet Child Adolesc Health. 2020;4(5):e10–1. [Crossref]
26. 26. Oh S, Kim JH, Choi SW, Lee HJ, Hong J, Kwon SH. Physician confidence in artificial intelligence: an online mobile survey. J Med Internet Res. 2019;21(3):e12422. [Crossref]
27. 27. Ahuja AS. The impact of artificial intelligence in medicine on the future role of the physician. PeerJ. 2019;7:e7702. [Crossref]