Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer.

Gastric cancer (GC) represents a significant burden of cancer-related mortality worldwide, underscoring an urgent need for the development of early detection strategies and precise postoperative interventions. However, the identification of non-invasive biomarkers for early diagnosis and patient risk stratification remains underexplored. Here, we conduct a targeted metabolomics analysis of 702 plasma samples from multi-center participants to elucidate the GC metabolic reprogramming. Our machine learning analysis reveals a 10-metabolite GC diagnostic model, which is validated in an external test set with a sensitivity of 0.905, outperforming conventional methods leveraging cancer protein markers (sensitivity < 0.40). Additionally, our machine learning-derived prognostic model demonstrates superior performance to traditional models utilizing clinical parameters and effectively stratifies patients into different risk groups to guide precision interventions. Collectively, our findings reveal the metabolic landscape of GC and identify two distinct biomarker panels that enable early detection and prognosis prediction respectively, thus facilitating precision medicine in GC.

Nutritional Risk Index as a Prognostic Factor Predicts the Clinical Outcomes in Patients With Stage III Gastric Cancer.

Objective: This study is aimed to determine the potential prognostic significance of nutritional risk index (NRI) in patients with stage III gastric cancer. Methods: A total of 202 patients with stage III gastric cancer were enrolled in this study. NRI was an index based on ideal body weight, present body weight, and serum albumin levels. All patients were divided into two groups by receiver operating characteristic curve: low NRI group (NRI<99) and high NRI group (NRI≥99). The relationship between NRI and clinicopathologic characteristics was evaluated by Chi-square test. The clinical survival outcome was analyzed by Kaplan-Meier method and compared using log-rank test. The univariate and multivariate analyses were used to detect the potential prognostic factors. A nomogram for individualized assessment of disease-free survival (DFS) and overall survival (OS). The calibration curve was used to evaluate the performance of the nomogram for predicted and the actual probability of survival time. The decision curve analysis was performed to assess the clinical utility of the nomogram by quantifying the net benefits at different threshold probabilities. Results: The results indicated that NRI had prognostic significance by optimal cutoff value of 99. With regard to clinicopathologic characteristics, NRI showed significant relationship with age, weight, body mass index, total protein, albumin, albumin/globulin, prealbumin, glucose, white blood cell, neutrophils, lymphocyte, hemoglobin, red blood cell, hematocrit, total lymph nodes, and human epidermal growth factor receptor 2 (P<0.05). Through the univariate and multivariate analyses, NRI, total lymph nodes, and tumor size were identified as the independent factor to predict the DFS and OS. The nomogram was used to predict the 1-, 3-, and 5-year survival probabilities, and the calibration curve showed that the prediction line matched the reference line well for 1-, 3-, and 5-year DFS and OS. Furthermore, the decision curve analysis also showed that the nomogram model yielded the best net benefit across the range of threshold probability for 1-, 3-, 5-year DFS and OS. Conclusions: NRI is described as the potential prognostic factor for patients with stage III gastric cancer and is used to predict the survival and prognosis.