Development and validation of a machine learning-based 18F-fluorodeoxyglucose PET/CT radiomics signature for predicting gastric cancer survival.

BACKGROUND: Survival prognosis of patients with gastric cancer (GC) often influences physicians' choice of their follow-up treatment. This study aimed to develop a positron emission tomography (PET)-based radiomics model combined with clinical tumor-node-metastasis (TNM) staging to predict overall survival (OS) in patients with GC. METHODS: We reviewed the clinical information of a total of 327 patients with pathological confirmation of GC undergoing 18 F-fluorodeoxyglucose (18 F-FDG) PET scans. The patients were randomly classified into training (n = 229) and validation (n = 98) cohorts. We extracted 171 PET radiomics features from the PET images and determined the PET radiomics scores (RS) using the least absolute shrinkage and selection operator (LASSO) and random survival forest (RSF). A radiomics model, including PET RS and clinical TNM staging, was constructed to predict the OS of patients with GC. This model was evaluated for discrimination, calibration, and clinical usefulness. RESULTS: On multivariate COX regression analysis, the difference between age, carcinoembryonic antigen (CEA), clinical TNM, and PET RS in GC patients was statistically significant (p < 0.05). A radiomics model was developed based on the results of COX regression. The model had the Harrell's concordance index (C-index) of 0.817 in the training cohort and 0.707 in the validation cohort and performed better than a single clinical model and a model with clinical features combined with clinical TNM staging. Further analyses showed higher PET RS in patients who were older (p < 0.001) and those who had elevated CEA (p < 0.001) and higher clinical TNM (p < 0.001). At different clinical TNM stages, a higher PET RS was associated with a worse survival prognosis. CONCLUSIONS: Radiomics models based on PET RS, clinical TNM, and clinical features may provide new tools for predicting OS in patients with GC.

Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model.

Deep vein thrombosis (DVT) represents a critical health concern due to its potential to lead to pulmonary embolism, a life-threatening complication. Early identification and prediction of DVT are crucial to prevent thromboembolic events and implement timely prophylactic measures in high-risk individuals. This study aims to examine the risk determinants associated with acute lower extremity DVT in hospitalized individuals. Additionally, it introduces an innovative approach by integrating Q-learning augmented colony predation search ant colony optimizer (QL-CPSACO) into the analysis. This algorithm, then combined with support vector machines (SVM), forms a bQL-CPSACO-SVM feature selection model dedicated to crafting a clinical risk prognostication model for DVT. The effectiveness of the proposed algorithm's optimization and the model's accuracy are assessed through experiments utilizing the CEC 2017 benchmark functions and predictive analyses on the DVT dataset. The experimental results reveal that the proposed model achieves an outstanding accuracy of 95.90% in predicting DVT. Key parameters such as D-dimer, normal plasma prothrombin time, prothrombin percentage activity, age, previously documented DVT, leukocyte count, and thrombocyte count demonstrate significant value in the prognostication of DVT. The proposed method provides a basis for risk assessment at the time of patient admission and offers substantial guidance to physicians in making therapeutic decisions.

Prognostic value and association of the age-adjusted Charlson Comorbidity Index with sarcopenia within patients with gastric cancer after radical resection.

PURPOSE: The association between the age-adjusted Charlson Comorbidity Index (ACCI) and sarcopenia in patients with gastric cancer (GC) remains ambiguous. This study aimed to investigate the association between the ACCI and sarcopenia and the prognostic value in patients with GC after radical resection. In addition, this study aimed to develop a novel prognostic scoring system based on these factors. METHODS: Univariate and multivariate Cox regression analyses were used to determine prognostic factors in patients undergoing radical GC resection. Based on the ACCI and sarcopenia, a new prognostic score (age-adjusted Charlson Comorbidity Index and Sarcopenia [ACCIS]) was established, and its prognostic value was assessed. RESULTS: This study included 1068 patients with GC. Multivariate analysis revealed that the ACCI and sarcopenia were independent risk factors during the prognosis of GC (P = 0.001 and P < 0.001, respectively). A higher ACCI score independently predicted sarcopenia (P = 0.014). A high ACCIS score was associated with a greater American Society of Anesthesiologists score, higher pathologic TNM (pTNM) stage, and larger tumor size (all P < 0.05). Multivariate analysis demonstrated that the ACCIS independently predicted the prognosis for patients with GC (P < 0.001). By incorporating the ACCIS score into a prognostic model with sex, pTNM stage, tumor size, and tumor differentiation, we constructed a nomogram to predict the prognosis accurately (concordance index of 0.741). CONCLUSION: The ACCI score and sarcopenia are significantly correlated in patients with GC. The integration of the ACCI score and sarcopenia markedly enhances the accuracy of prognostic predictions in patients with GC.