Artificial intelligence-assisted chatbot: impact on breastfeeding outcomes and maternal anxiety


KERİMOĞLU YILDIZ G., Delibalta R. T., Coktay Z.

BMC PREGNANCY AND CHILDBIRTH, cilt.25, sa.1, 2025 (SCI-Expanded, Scopus) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 25 Sayı: 1
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1186/s12884-025-07753-3
  • Dergi Adı: BMC PREGNANCY AND CHILDBIRTH
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, CINAHL, EMBASE, MEDLINE, Veterinary Science Database, Directory of Open Access Journals
  • Hatay Mustafa Kemal Üniversitesi Adresli: Evet

Özet

Background Artificial intelligence (AI) is increasingly used in healthcare interventions to provide accessible, continuous, and personalized patient support. This study investigates the impact of a mobile breastfeeding counseling application developed with artificial AI on mothers' breastfeeding self-efficacy, success, and anxiety levels. Methods A quasi-experimental design was employed, involving 60 mothers. Participants were divided into two groups: 30 mothers received AI-based counseling, and 30 mothers were provided a booklet. Data collection tools included a personal information form, Breastfeeding Charting System and Assessment Tool (LATCH), Postnatal Breastfeeding Self-Efficacy Scale, and Beck Anxiety Inventory. Data were collected from mothers who delivered at a state hospital's obstetrics and gynecology department and were followed for ten days postpartum (postpartum days 1, 3, 7, and 10). Results No significant differences were found in the demographic characteristics of the two groups (p > 0.05). Statistically significant improvements were observed in breastfeeding self-efficacy over time for both groups (AI group: f = 36.356, p = 0.000; booklet group: f = 43.349, p = 0.000). At day 10, the AI group scored significantly higher than the booklet group (Z=-2.216, p = 0.027). For breastfeeding success, as measured by the LATCH tool, significant differences were also noted over time for both groups (AI group: f = 68.466, p = 0.000; booklet group: f = 68.088, p = 0.000). At day seven, the AI group outperformed the booklet group (Z=-2.995, p = 0.003). Anxiety levels showed no significant differences between groups. Conclusions AI-based breastfeeding counseling positively impacts breastfeeding self-efficacy and success. The findings highlight the potential of AI applications in healthcare. AI-based chatbots can serve as effective tools for breastfeeding education, offering accessible, personalized, and continuous support. The significant improvements in breastfeeding outcomes indicate that innovative AI-assisted interventions can effectively support mothers during the critical early postpartum period. This research demonstrates the feasibility of integrating AI technology into maternal care and serves as a foundation for future studies.