Abstract Purpose Oligometastatic castration-sensitive prostate cancer (omCSPC) is a clinically and biologically heterogeneous disease. A multimodal artificial intelligence (MMAI) algorithm (ArteraAI Prostate Test), which incorporates digital histopathology and clinical information, is prognostic for outcomes in localized prostate cancer. We hypothesized MMAI algorithms are also prognostic in omCSPC and correlate with tumor biology. Thus, we aimed to evaluate the association between MMAI score vector features (VF) with outcomes and genomics of omCSPC. Materials/Methods We correlated somatic pathogenic mutations and ArteraAI MMAI scores from 168 omCSPC patients. RNAseq profiling was performed on a subset of 65 metachronous patients. Somatic nonsynonymous pathogenic mutations from panel DNAseq were identified using Mutect2 and ClinVAR database. Pair-end reads of RNAseq were aligned to Human reference (hg38) using HISAT2. To identify the differentially mutated genes associated with MMAI scores, samples were binned separately based on the median or quartile MMAI scores, and Fisher’s exact test were used to evaluate differentially mutated genes between bins. Differential expression of genes were evaluated using DEseq2 and gene set enrichment analysis. VFs from the MMAI scores and correlated with mutations using Wilcoxon test. Results Median follow-up was 34.7 months. Overall survival was shorter in patients with high MMAI scores (top quartile) compared to those with low MMAI scores (bottom three quartiles, p=0.017). MMAI scores were significantly higher in synchronous compared to metachronous omCSPC (p<0.05). DNAseq demonstrated high MMAI scores were associated with higher incidence of BRCA2/ATM (p=0.008) and WNT pathway (APC/CTNNB1) mutations (p=0.13). Conversely, high MMAI scores were associated with lower incidence of SPOP mutations (p=0.03). RNAseq revealed differential gene expression based on MMAI score, with higher scores being enriched for epithelial-mesenchymal transition (EMT) pathway expression (p<0.01). Of the 128 VFs that contribute to MMAI scores, 32 were associated with somatic mutations. Specifically, 15 VFs associated with mutations in DNA damage response (p<0.01); 8 VFs associated with mutated genes of PIK3 pathway(p<0.01); 4 VFs associated with mutated genes of TP53 pathway(p<0.01); and 1 VF associated with genomic alteration in WNT pathway genes. Conclusions We demonstrate digital histopathology features using MMAI algorithms are prognostic for outcomes in omCSPC. We directly correlated MMAI scores with DNA mutations and transcriptional programs involved in metastatic propagation with higher scores associated with aggressive alterations (WNT, BRCA2/ATM, EMT) and lower scores associated with more indolent alterations (SPOP). Furthermore, VF were able to be directly correlated with DNA mutations. This suggests digital histopathology-based MMAI algorithms identify phenotypic pathologic features correlated with underlying biological genomic and transcriptomic processes and can be leveraged to better understand the heterogeneity of omCSPC. Citation Format: Matthew P. Deek, Yang Song, Amol Shetty, Philip Sutera, Adrianna A. Mendes, Kim Van der Eecken, Emmalyn Chen, Timothy Showalter, Trevor J Royce, Tamara Todorovic, Huei-Chung Huang, Scott A. Houck, Rikiya Yamashita, Ana Ponce Kiess, Daniel Y. Song, Tamara Lotan, Andre Esteva, Felix Y. Feng, Piet Ost, Phuoc T. Tran.A digital pathology multimodal artificial intelligence algorithm is associated with pro-metastatic genomic pathways in oligometastatic prostate cancer.[abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Translating Targeted Therapies in Combination with Radiotherapy; 2025 Jan 26-29; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(2_Suppl):Abstract nr P007
Read full abstract