
Eye diseases such as cataracts, glaucoma, and diabetic retinopathy are major global health issues, affecting millions of people and leading to vision impairment or blindness if not detected and treated promptly. According to the World Health Organization (WHO), 2.2 billion people suffer from vision impairment, with at least 1 billion cases being preventable. In Indonesia, these eye diseases significantly contribute to vision problems, exacerbated by limited awareness and accessibility to early detection. Additionally, inefficiencies and lack of integration in medical records hinder effective diagnosis and treatment.
To address these challenges, we developed SCANOCULAR, an application leveraging artificial intelligence (AI) and blockchain technology to facilitate early detection of eye diseases through smartphone-based eye scans. The blockchain component ensures the security and immutability of patient data, supporting the implementation of electronic medical records (EMR) and integration with Indonesia's SATUSEHAT system. This development aims to enhance overall eye care quality in Indonesia, aligning with the Sustainable Development Goals (SDGs) for "Good Health and Well-Being."
The initial phase involved identifying the needs and expectations of patients, healthcare providers, administrators, and public health officials through surveys and interviews. This provided insights into functional and non-functional requirements, guiding subsequent phases.
A comprehensive project plan was developed post-requirement gathering, outlining timelines and milestones. Design focused on creating a scalable architecture and intuitive user interface, incorporating stakeholder feedback.
Front-end development used robust frameworks to ensure responsiveness and accessibility. Concurrent back-end development supported data flow and real-time updates, with blockchain integration for data security.
Rigorous testing included unit, integration, and user acceptance testing (UAT) phases to validate functionality, performance, and user experience. Load testing ensured scalability under high usage.
Production environment setup ensured configurations were optimized for performance and security. Final checks and user validation preceded the official launch.
Post-launch monitoring tracked performance metrics and user engagement. Feedback mechanisms facilitated ongoing improvements to meet user needs and healthcare objectives.