Ibrahim Arif
Grade 10, Oral Presenter
Age-related macular degeneration (AMD) is a progressive neurodegenerative eye disorder characterized by eventual degeneration of the retinal pigment epithelium (RPE) leading to permanent vision loss. Artificial intelligence (AI) and machine learning (ML) have revolutionized healthcare by advancing clinical diagnosis leveraging its ability to analyze vast amounts of patient data and accurately predict future outcomes. With no definitive treatment for AMD, this experiment located novel genetic biomarkers, utilizing Hygieia, an open-source AI/ML pipeline to more comprehensively understand AMD’s etiology for potential treatments and assess the performance of this model in diagnosing AMD. A gene expression dataset was downloaded from the Gene Expression Omnibus (GEO) database. Differential gene expression analysis was performed to identify significant differentially expressed genes (DEGs) between case and control retinal samples. AI/ML analysis was performed using Hygieia to identify statistically significant genes. Gene ontology analysis was performed and a classifier was constructed to analyze the prediction performance of the genes in diagnosing AMD. Results were compared with current literature.
The data from this experiment supported earlier findings linking RPE dysfunction and concurrent inflammatory mechanisms in AMD’s pathogenesis. Low p-values were obtained from the Chi-Square test for SLC1A4 (p<0.001), BCS1L (p<0.001), and SNHG17 (p<0.001) which were proposed as novel biomarkers that, with further research, may contribute to a more complete understanding of AMD’s etiology for treatment, and lead to earlier diagnosis of AMD. This experiment elucidated that AI/ML technologies can contribute significantly to identifying biomarkers and predicting disease.
Mentors:
- Mrs. Allison Hennings- IMSA/RISE Instructor
- Mr. Will DeGroat (B.S.) – Rutgers Institute of Health
- Mr. Safdar Zaman (B.S.) – Microsoft
- Dr. Linsey Mao (Ph.D.) – Benedictine University
