AI/ML-Assisted Detection of HMGA2 RNA Isoforms in Prostate Cancer Patient Tissue

RNA In Situ Hybridization (RISH) is a powerful tool for spatial gene expression analysis, yet its quantitative use remains limited by the high cost and inaccessibility of commercial software, particularly in under-resourced settings. This study developed an Artificial Intelligence/Machine Learning (AI/ML)-assisted RISH quantification pipeline to evaluate expression patterns of High Mobility Group AT Hook-2 (<i>HMGA2</i>) in prostate cancer (PCa), focusing on racial disparities. We created a machine learning model capable of analyzing RISH images. Expressions of full-length (wild-type) and truncated <i>HMGA2</i> isoforms were assessed in tissues from 85 men of African descent, European American, and Asian descent. A training dataset was generated for supervised learning analysis of the full cohort. RISH findings revealed that the wild-type <i>HMGA2</i> isoform was significantly more abundant in tumors from men of African descent and positively correlated with increasing Gleason grade. The truncated isoform was less abundant and did not display a consistent expression pattern across racial groups. These results demonstrate the feasibility of AI/ML-based RISH quantification and suggest that elevated wild-type <i>HMGA2</i> expression may represent a biomarker linked to prostate cancer aggressiveness and racial disparities. These findings highlight the importance of interdisciplinary collaboration and equitable computational tools in advancing biomarker discovery and addressing cancer health inequities.