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

Area of Science:

• Maternal Health
• Health Services Research
• Medical Informatics

Background:

• Gestational Diabetes Mellitus (GDM) presents significant management challenges, including frequent visits and financial burdens.
• Patients with GDM prioritize services that minimize time, reduce costs, and simplify screening processes.
• Virtual and telehealth services are increasingly recognized for their potential to improve patient satisfaction by reducing travel and waiting times.

Purpose of the Study:

• To review patient experiences regarding time, costs, and screening for Gestational Diabetes Mellitus.
• To highlight the application of machine learning (ML) in enhancing GDM screening and early detection.
• To synthesize evidence from preference-elicitation methods to guide patient-centered GDM care.

Main Methods:

• Qualitative, quantitative, and mixed-methods approaches were used to explore patient preferences.
• Literature review focusing on patient experiences, telehealth, and machine learning in GDM.
• Synthesis of evidence linking patient preferences with technological advancements in GDM management.

Main Results:

• Patients value convenience, accuracy, and affordability in GDM screening methods.
• Telehealth and virtual services are preferred for their time-saving and cost-reducing benefits.
• Machine learning models show potential for improving the prediction and personalization of GDM screening strategies.

Conclusions:

• Integrating patient preferences with technological innovations like machine learning is crucial for developing effective, patient-centered GDM care models.
• Future research and service design should prioritize convenience, cost-effectiveness, and accuracy in GDM screening.
• Telehealth and ML-driven approaches can significantly enhance the management and patient experience of Gestational Diabetes Mellitus.