Patient-Centred Gestational Diabetes Care: Preference Elicitation Methods and Machine Learning Innovations

Gestational Diabetes Mellitus (GDM) requires long-term management, frequent visits, and additional financial costs compared to normal pregnancies. Patients often express preferences for services that save time, reduce expenses, and simplify screening. Virtual and telehealth services are valued as they shorten travel and waiting times, lower costs, and improve satisfaction. Screening preferences emphasize accuracy, affordability, and convenience, while recent machine learning (ML) models have enhanced prediction and early detection, supporting more personalized strategies. Patients' preferences have been explored through qualitative, quantitative, and mixed methods, which capture lived experiences, quantify trade-offs, and contextualize results. This review aims to examine GDM patients' experiences with time, costs, and screening, highlight the role of machine learning in screening, and synthesize evidence from preference-elicitation methods to inform patient-centred care. By linking patient preferences with technological advances in ML, this review provides a broader and more integrated perspective than previous reviews, helping to guide future GDM research and service design.