Artificial Intelligence-Enabled Integration Suggests TP53 Pathway Alterations as Prognostic Biomarkers in Populations with Disproportionate Health Burdens.

The incidence of early-onset colorectal cancer (EOCRC; <50 years) continues to increase, with the most rapid rises occurring among Hispanic/Latino (H/L) populations who remain underrepresented in molecular research. Because the TP53 signaling pathway is a key driver of colorectal tumorigenesis, this study aimed to clarify its prognostic significance in FOLFOX-treated EOCRC across ancestry groups. We analyzed 2515 colorectal cancer (CRC) cases (266 H/L, 2249 non-Hispanic White [NHW]) stratified by ancestry, age at onset, and FOLFOX exposure. Fisher's exact, chi-square, and Kaplan-Meier's analyses were applied, and multi-dimensional data integration was performed using AI-HOPE and AI-HOPE-TP53, conversational artificial intelligence platforms enabling natural language-driven exploration of clinical, genomic, and therapeutic features. TP53 pathway alterations were common in both H/L (85%) and NHW (83%) FOLFOX-treated patients. Among late-onset NHW cases, FOLFOX treatment was associated with higher TP53 mutation frequencies and lower ATM and CDKN2A mutation rates compared with untreated counterparts, while CHEK2 alterations were significantly less frequent in late-onset H/L patients. Missense mutations were the predominant alteration type across groups. These findings suggest that TP53 pathway alterations may be associated with ancestry- and treatment-specific clinical patterns in EOCRC and illustrate how AI-enabled integrative analytic frameworks can facilitate hypothesis generation and prioritize candidate biomarkers for future validation in precision oncology.