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

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.