A predictive model and rapid multi-dynamic algorithm developed based on tumor-stroma percentage in gastric cancer: a retrospective, observational study.

Background: Tumor-stroma percentage (TSP) is a prognostic risk factor in numerous solid tumors. Despite this, the prognostic significance of TSP in gastric cancer (GC) remains underexplored. Through the development of a personalized predictive model and a semi-automatic identification system, our study aimed to fully unlock the predictive potential of TSP in GC.

Methods: We screened GC patients from Shanghai General Hospital (SGH) between 2012 and 2019 to develop and validate a nomogram. Univariate and multivariate Cox proportional hazards regression analyses were employed to identify independent prognostic factors influencing the prognosis for GC patients. The nomogram was further validated externally by using a cohort from Bengbu Medical College (BMC). All patients underwent radical gastrectomy, with those diagnosed with locally advanced GC receiving adjuvant chemotherapy. The primary outcome measured was overall survival (OS). The semi-automatic identification of the TSP was achieved through a computer-aided detection (CAD) system, denoted as TSP-cad, while TSP identified by pathologists was labeled as TSP-visual.

Results: A total of 813 GC patients from SGH and 59 from BMC were enrolled in our study. TSP-visual was identified as an adverse prognostic factor for OS in GC and was found to be associated with pathological Tumor Node Metastasis staging system (pTNM) stage, T stage, N stage, perineural invasion (PNI), lymphovascular invasion (LVI), TSP-visual, tumor size, and other factors. Multivariate Cox regression using the training cohort revealed that TSP-visual (hazard ratio [HR], 2.042; 95% confidential interval [CI], 1.485-2.806; <0.001), N stage (HR, 2.136; 95% CI, 1.343-3.397; =0.010), PNI (HR , 1.791; 95% CI, 1.270-2.526; =0.001), and LVI (HR, 1.482; 95% CI, 1.021-2.152; =0.039) were independent predictors. These factors were incorporated into a novel nomogram, which exhibited strong predictive accuracy for 5-year OS in the training, internal validation, and external validation cohorts (area under the curve = 0.744, 0.759, and 0.854, respectively). The decision curve analysis of the nomogram and concordance indexes across the three cohorts outperformed the traditional pTNM (<0.05). Additionally, TSP-cad assessment using a rapid multi-dynamic algorithm demonstrated good agreement with TSP-visual.

Conclusions: The novel nomogram based on TSP could effectively identify individuals at risk of a poor prognosis among patients with GC. TSP-cad is anticipated to enhance the evaluation process of TSP.