Healthcare professionals' perspectives on artificial intelligence (AI)-based mobile applications (apps) for diabetes education and behavioural management

BACKGROUND: The global prevalence of diabetes mellitus is escalating rapidly. Similarly in Malaysia, diabetes prevalence among adults rose exponentially. Artificial intelligence (AI) integrated into mobile health applications (apps) presents a promising avenue for enhancing diabetes management through personalized patient education and behaviour modification. However, adoption rates remain low, primarily due to limited awareness and technological challenges, especially among older adults.

OBJECTIVE: This study aimed to explore Malaysian healthcare professionals' (HCPs') perspectives on the use of AI in mobile apps for diabetes education and behavioural management.

METHODS: Qualitative study using semi-structured interviews with 19 HCPs across Malaysia. Interviews were conducted via video conferencing, recorded, transcribed, and analysed using thematic analysis with NVivo 14 software.

RESULTS: Seven key themes emerged: (1) acceptance and trust, (2) impact on patient behaviour, (3) skills and abilities required, (4) problems and obstacles, (5) key features and functions, (6) HCPs' and patients' information needs, and (7) strategies for increasing patient adoption. HCPs expressed positive sentiments towards AI-based apps, highlighting their potential for continuous, personalized education and real-time feedback. However, significant concerns were raised about accessibility for older adults, data privacy, and the apps' ability to modify entrenched behaviours without human intervention.

CONCLUSION: AI-based mobile apps show potential for improving diabetes management, but successful implementation requires addressing challenges. Strategies should focus on developing user-friendly interfaces, providing comprehensive education for patients and providers, and ensuring robust data protection. Future research should quantify the impact on patient outcomes and explore effective integration of human support with AI capabilities.