Francisco Sanchez-Vega, PhD

Developing artificial intelligence tools with more accurate predictive and prognostic capabilities for breast cancer in patients from underrepresented groups.

Impact

Modern artificial intelligence (AI) offers a unique opportunity to improve therapeutic outcomes for cancer patients. Whereas traditional clinical models for outcome prediction have focused on a narrow set of interpretable biomarkers such as tumor size, grade, hormone receptor status, gene mutations, or overexpression of a small number of genes, modern AI-based approaches can integrate millions of data points from multiple data modalities including radiology images, pathology slides, comprehensive genomic sequencing and clinical variables for improved prediction and prognostication. Unfortunately, most of these new tools continue to be developed in a race-agnostic manner and do not account for race-specific differences in tumor biology. AI tools trained and validated using racially homogeneous cohorts exacerbate existing racial disparities in clinical outcomes, where age-adjusted breast-cancer mortality is about 40 percent higher among Black women than among non-Hispanic White women.

What’s next

With his AACR award supported by BCRF, Dr. Sanchez-Vega aims to create a comprehensive, racially diverse database of 1,600 patients with early-stage breast cancer treated with neoadjuvant chemotherapy. The database will include detailed therapeutic outcomes with corresponding clinical, imaging, pathology, genomic and molecular data. To account for non-biological factors, Dr. Sanchez-Vega will also include information about the type of health insurance and address-based indices of socioeconomic status for each patient and compare the prevalence of specific multimodal features across races. He and his team will build algorithms to predict response to neoadjuvant therapy and analyze the predictive value of individual data modalities (clinical, pathology, radiology, and genomic) across different racial backgrounds to identify the most informative features for each race. Then, the team will design novel, race-aware AI-based multimodal predictors that have enhanced accuracy for underrepresented minority patients. All the data generated as part of Dr. Sanchez-Vega’s project will be made public and widely accessible to facilitate long-term development of tools that further improve predictive and prognostic capabilities for all patients with breast cancer.