fairfolio
Saved Projects

OcuScan: Low-Cost Ml Biomarker Tool for Detection of Eye & Neurodegenerative Diseases

AJAS · 2026 Biomedical and Health Sciences (inferred)

Sakhyata Gurram · North Carolina Academy of Science

Overview

Ophthalmological diseases pose a significant public health challenge, with an estimated 93 million adults in the United States at high risk for serious vision loss. However, only half of them visited an eye doctor in the past year, and rising examination costs further limit access to essential eye care, a problem exacerbated by the COVID-19 pandemic. This research endeavors to address the pressing issue of limited access to affordable eye care by developing a risk-level self-assessment model. We aim to employ three machine learning methods, namely decision trees, logistic classification, and support vector machines (SVM), to create a cost-effective and accurate solution for the early detection of ophthalmological diseases. Quantitative and qualitative data were collected through surveys, with attributes interpreted within specific cultural and socio-technical contexts. Additionally, we accessed data from multiple eye databases containing standardized information on thousands of healthy and diseased human eyes. Machine learning models were trained to detect critical factors such as gaze estimation, saccade movement, smooth pursuits, and convergence. Machine learning models, employing Decision Tree, Logistic Regression, and SVM, were developed and evaluated. The dataset was randomly divided into training and testing groups, with 70% allocated to the training dataset and the remaining 30% assigned to the test dataset. Our approach yielded a low-cost, highly accurate, and non-invasive software solution for the detection of eye-related diseases. Statistical models achieved validation and training accuracies exceeding 95%. The research successfully addressed the urgent need for accessible and accurate eye disease detection by combining a low-cost biomarker (OcuScan) with machine learning-based risk assessment models. These findings hold significant potential for enhancing early disease detection and improving eye care accessibility, particularly for underserved populations.

Competition history

  • AJAS 2026 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: AAAS Annual Meeting (Confex) / American Junior Academy of Science

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google