Leveraging generative AI models to optimize image-based diagnostics in telehealth services in indonesia: a 2025 perspective

Abstract

The rapid advancement of telehealth services has transformed healthcare delivery, particularly in regions with limited access to medical specialists. Recent developments in generative artificial intelligence (AI) offer promising solutions to enhance diagnostic accuracy, especially in image-based medical assessments such as radiology, dermatology, and pathology. This study aims to investigate the integration of generative AI models within telehealth platforms to optimize diagnostic workflows in Indonesia. A mixed-method approach was employed, involving a simulated dataset of 10,000 annotated medical images and a usability assessment with 120 healthcare practitioners across primary healthcare centers. The generative AI model was trained to augment diagnostic images, improve feature visibility, and assist physicians in detecting early-stage diseases. Quantitative results showed a 23% improvement in diagnostic accuracy and a 30% reduction in analysis time compared to traditional telehealth systems. Additionally, qualitative findings highlighted enhanced user confidence and satisfaction with the AI-assisted platform. This research underscores the potential of generative AI to bridge diagnostic gaps in telehealth services, offering scalable and cost-effective solutions for Indonesia’s healthcare ecosystem. Recommendations for implementation and ethical considerations are also discussed.