Smartphone-Based Portable Slit Lamp in Anterior Segment Diseases: A Narrative Review of Clinical Assessment and Integration with Artificial Intelligence

Smartphone-based portable slit lamps are rapidly evolving from simple add-ons into practical, low-cost front-line tools for anterior segment care beyond traditional clinical settings. By integrating high-performance smartphone cameras with compact optical attachments (e.g., slit-light converters, macro lenses, blue filters) and dedicated applications, these devices deliver slit-lamp-style imaging and video capture to environments where conventional biomicroscopes are inaccessible. Accumulating clinical evidence-most notably for the Smart Eye Camera (SEC) and iSpector MINI HE 010-21-confirms that smartphone slit lamps reliably support assessments across major anterior segment disorders. SEC-based recordings enable evaluation of tear film-related signs in dry eye disease; smartphone-acquired slit-lamp images show strong agreement with standard slit lamps for corneal ulcers, scars, and other ocular surface pathologies; slit-beam acquisition facilitates preliminary screening of shallow anterior chambers and narrow angles relevant to primary angle-closure glaucoma; and cataract screening and grading via smartphone systems align closely with conventional slit-lamp evaluations. Notably, recent advancements have transcended mere image capture to embrace artificial intelligence (AI)-enabled analysis, positioning smartphone slit lamps as scalable screening and triage solutions. Across the studies reviewed, AI models trained on smartphone slit-lamp images or videos demonstrate robust feasibility for automated dry eye diagnosis, corneal opacity detection, keratitis screening, cataract grading, pterygium detection/grading, and narrow-angle identification, typically through pipelines integrating image quality control, region-of-interest localization/segmentation, and disease-specific prediction. Despite these advances, however, key barriers remain, including incomplete replication of full slit-lamp functionality, lack of standardized acquisition protocols, and limited multicenter external validation for most AI systems. Future progress should prioritize hardware stabilization, optical design improvements, disease-specific standardized imaging workflows, and large-scale prospective validation to unlock the full potential of AI-assisted smartphone slit lamps for community screening, teleophthalmology, and care in underserved regions.