# Study of Biological and Radiographic Biomarkers and Association with Ancestry and Survival Disparities in Oral Cavity Squamous Cell Carcinoma Using AI Approaches > **NIH NIH R01** · UNIVERSITY OF MARYLAND BALTIMORE · 2024 · $659,936 ## Abstract ABSTRACT Oral cavity squamous cell carcinoma (OSCC) is a complex and aggressive disease that requires multidisciplinary care and has a poor prognosis at advanced stages. Moreover, OSCC is the only site of head and neck cancer that exhibits significant racial disparities, with African ancestry (AA) patients having worse survival than European ancestry (EA) patients. However, the causes of these survival disparities are poorly understood due to the scarcity of AA-OSCC patient data, which hinders the development of better treatments to address the disparities. To fill this knowledge gap, we propose to conduct a comprehensive and novel study on AA-OSCC patients, using our unique dataset from the University of Maryland Medical Center/Greenebaum Comprehensive Cancer Center, which has a high head and neck cancer patient volume and has built one of the most comprehensive, annotated, racially diverse clinical databases. We will also use additional samples and data from the Yale Head and Neck Biorepository from Yale Cancer Center to enhance patient representation. We will analyze 163 AA-OSCC and 836 EA-OCSS cases in this project. We will perform multi- scale analyses of AA-OSCC samples/patients to evaluate their unique clinical, biological, pathology, imaging, and socioeconomic characteristics relative to EA-OSCC samples/patients. Our central hypothesis is that differential biological, physiological, and socioeconomic factors drive race-based survival disparities in OSCC, leading to pathway abnormalities, differential responses to the therapeutic intervention, and overall poorer survival. To test our hypothesis, we have designed the following specific aims: Specific Aim 1: Compare biological differences between AA-OSCC and EA-OSCC patients and assess the role of biological factors in patients’ survival. Specific Aim 2: Determine imaging biomarkers for survival prediction among AA- OSCC and EA-OSCC patients. Specific Aim 3: Identify socioeconomic factors related to overall, disease- specific, and recurrence-free survival among AA-OSCC and EA-OSCC. By integrating the results from these three aims using artificial intelligence methods, we will produce the first comprehensive study on the AA-OSCC population. This study will reveal the unique characteristics of AA-OSCC and functionally examine the potential therapeutic targets and pathways that are activated in AA-OSCC. We will thoroughly investigate different aspects of the patient data, including biology, imaging, and socioeconomic/clinical data, and synergize the findings to develop a systematic approach to address disparities. Our research will help identify key prognostic and/or predictive biomarkers that will be leveraged to advance clinical studies of novel therapeutics or alternative treatment strategies to improve outcomes of AA-OSCC to reduce disparities. This project will also advance the field of precision medicine for OSCC by incorporating ancestry information into personalized diagnosis and treatm... ## Key facts - **NIH application ID:** 10977744 - **Project number:** 1R01DE033426-01A1 - **Recipient organization:** UNIVERSITY OF MARYLAND BALTIMORE - **Principal Investigator:** Daria A Gaykalova - **Activity code:** R01 (R01, R21, SBIR, etc.) - **Funding institute:** NIH - **Fiscal year:** 2024 - **Award amount:** $659,936 - **Award type:** 1 - **Project period:** 2024-08-15 → 2029-05-31 ## Primary source NIH RePORTER: https://reporter.nih.gov/project-details/10977744 ## Citation > US National Institutes of Health, RePORTER application 10977744, Study of Biological and Radiographic Biomarkers and Association with Ancestry and Survival Disparities in Oral Cavity Squamous Cell Carcinoma Using AI Approaches (1R01DE033426-01A1). Retrieved via AI Analytics 2026-06-12 from https://api.ai-analytics.org/grant/nih/10977744. Licensed CC0. --- *[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*