OptoForge
Clinical learning
A separate eye-care learning environment for practising clinical reasoning, cases and reflective learning. Educational performance is not proof of clinical competence.
Explore OptoForgeAI awareness · Eye care · Brain health
SightedAI connects clinical curiosity with practical learning about artificial intelligence in eye and brain care—and the healthcare systems of the future.
An educational initiative in development. This website does not analyse patient images or provide clinical assessments.
Why SightedAI exists
Founded by Dr Justin Ogheneruemu Eghaghara, an optometrist with professional experience in Nigeria and the UK, SightedAI aims to make developments in healthcare AI easier to understand and discuss.
The vision starts with awareness and education in eye and brain care, alongside a longer-term ambition to help build efficient, accessible healthcare systems.
Explore the learning prompts below, examine areas of research interest, or start a conversation about a practical question.
Retinal imaging, OCT, visual fields, and corneal imaging are active areas of AI research. SightedAI explores how these technologies may support education, research, screening, and carefully governed clinical workflows — while recognising that performance depends on data, validation, population, device, and intended use.
Research on optic nerve, RNFL and visual-field data for screening, interpretation support, and risk modelling.
Computer-vision research for retinal lesion detection and scalable screening workflows.
Exploration of AI-assisted OCT and fundus interpretation for AMD-related features and progression research.
Pattern-analysis research using corneal topography and tomography for detection and classification questions.
Emerging research is examining whether retinal structure, vasculature, and imaging patterns can contribute to understanding neurological disease. AI may help identify patterns within these data, but clinical usefulness depends on careful validation, reproducibility, and appropriate populations.
Research is investigating whether retinal imaging features may be associated with neurological disease. These signals are not established as stand-alone diagnostic tests.
The retina is neural tissue and can be imaged non-invasively, making it an important research window for studying neurovascular and neurological change.
Machine-learning methods can help explore retinal patterns and candidate biomarkers, but associations require robust validation before clinical use.
Alzheimer's
Research signals
Parkinson's
Candidate biomarkers
MS
Retinal research
Learning explorer
Choose a theme and collect questions for your next paper, presentation or discussion. These are learning prompts, not a clinical approval checklist.
Start by making the claim specific.
0 questions selected
Courses, workshops and a larger resource library remain planned.
Where these ideas lead
SightedAI explores questions about emerging technology. The related initiatives below have distinct audiences and safeguards; they are not interconnected patient systems.
Clinical learning
A separate eye-care learning environment for practising clinical reasoning, cases and reflective learning. Educational performance is not proof of clinical competence.
Explore OptoForgeEye-health collaboration
An eye-health, mentorship and collaboration initiative. Programmes still in development are identified as such; an enquiry is not an appointment or service booking.
Explore SeeingBetterPrototype · synthetic data only
A separate exploratory workspace for possible future clinical-record, referral and research workflows. Not a functioning clinical EHR or a tool for entering real patient information.
AI discussions and demonstration software must not be treated as clinical recommendations, validated diagnostic tools or evidence of effectiveness.
These are areas of research interest for SightedAI, rather than claims of completed studies or available services. The aim is to understand what works, for whom, under what conditions, and what evidence is needed before translation into practice.
Tracking emerging methods such as vision transformers, multimodal models, federated learning, and explainable AI with a focus on healthcare evidence and limitations.
Open to collaboration with universities, hospitals, researchers, and technical teams on clinically relevant and responsibly governed questions.
Exploring prototypes and research concepts for imaging, clinical learning, workflow support, and other carefully scoped healthcare AI use cases.
Treating validation, external testing, calibration, subgroup performance, safety, and intended use as core requirements before clinical claims.
Outline a collaboration idea. This prepares an email for you to review and send; nothing is submitted here.
Enter your name and idea to prepare your enquiry.
Prefer to write directly? hello@sightedai.com
Explore areas of interest in eye and brain care, collect questions in the learning explorer, follow primary-source reading links, and prepare a collaboration enquiry.
No. This website offers educational content and discussion prompts. The illustrations are conceptual; they do not run a clinical model or analyse patient data.
Formal courses, workshops and research services are not offered through this website at present. Research sections describe areas of interest, not completed studies or validated products.
OptoForge is the founder’s separate eye-care learning platform. SightedAI focuses on awareness, education and discussion about AI and healthcare systems.
No. The enquiry tool prepares an email. You review and send it through your email application.