ARTIFICIAL INTELLIGENCE AND DIGITAL HEALTH IN DIAGNOSTIC SCIENCES: A COMPREHENSIVE REVIEW OF APPLICATIONS IN RADIOLOGY, MEDICAL LABORATORY TECHNOLOGY AND OPTOMETRY
Keywords:
Artificial intelligence; digital health; machine learning; deep learning; radiology; medical laboratory technology; optometry; diagnostic sciences; medical imaging; clinical decision support.Abstract
Artificial intelligence (AI) and digital health are rapidly transforming diagnostic sciences by enabling automated image interpretation, intelligent laboratory analytics, predictive modelling, clinical decision support, remote diagnostics, and personalized healthcare. Diagnostic disciplines generate large volumes of structured and unstructured data, making them particularly suitable for machine learning (ML), deep learning (DL), computer vision, natural language processing, and multimodal artificial intelligence. Radiology has emerged as one of the most advanced areas of clinical AI implementation, with applications spanning image reconstruction, segmentation, lesion detection, classification, workflow optimization, reporting, and prognostic assessment. In medical laboratory technology, AI is being explored across the pre-analytical, analytical, and post-analytical phases, including specimen processing, quality control, automated microscopy, hematology, clinical chemistry, microbiology, laboratory utilization, and result interpretation. Optometry and ophthalmic diagnostics are similarly benefiting from AI-based analysis of fundus photography, optical coherence tomography (OCT), visual fields, corneal imaging, and other digital eye-care data, particularly for diabetic retinopathy, glaucoma, age-related macular degeneration, and other ocular disorders. Digital health infrastructure, including electronic health records, picture archiving and communication systems, laboratory information systems, telemedicine, cloud computing, mobile health, and connected diagnostic devices, provides the ecosystem required for AI deployment. Despite considerable potential, challenges involving data quality, algorithmic bias, explainability, cybersecurity, interoperability, regulatory approval, workforce readiness, and clinical validation remain. The future of diagnostic sciences is likely to involve human-AI collaboration rather than complete automation, with multimodal systems integrating imaging, laboratory, clinical, genomic, and patient-generated data. This review summarizes the current applications, opportunities, challenges, and future directions of AI and digital health across radiology, medical laboratory technology, and optometry.