STAR (stroma-tumor AI risk) assessment: association of AI-derived tumor-stroma proportion with patient survival provides added prognostic value beyond KELIM in epithelial ovarian cancer

Abstract Background There remains a critical need for prognostic biomarkers of treatment response in epithelial ovarian cancer (EOC). The KELIM score, derived from the rate of CA-125 elimination during the first 100 days of treatment, is a clinically available biomarker of treatment response to platinum-based chemotherapy, its utility is limited by the need for post-treatment data. Tumor–stroma proportion (TSP) has emerged as a prognostic biomarker across several malignancies. Studies from our group have shown that high TSP (≥50% stroma content assessed by pathologist evaluation, TSP manual ) is associated with platinum resistance and poor survival in EOC at diagnosis and before treatment. Methods We compared the prognostic value of TSP and KELIM by analyzing manual pathologist (TSP manual ) and artificial intelligence–derived assessments (TSP auto ) on digitized images from a cohort of EOC specimens. Results In this cohort, we showed the prognostic significance of TSP manual , confirming prior findings. Furthermore, TSP auto and TSP manual assessments were highly concordant (94% agreement, Cohen’s Kappa 0.89, p