Background: The rapid advancement of radiomics and artificial intelligence (AI) technology has provided novel tools for the diagnosis of esophageal cancer. This study innovatively combines muscle imaging features with conventional esophageal imaging features to construct deep learning diagnostic models. Methods: This retrospective study included 1066 patients undergoing radical esophagectomy. Preoperative computed tomography (CT) images covering esophageal, stomach, and muscle (bilateral iliopsoas and erector spinae) regions were segmented automatically with manual adjustments. Diagnostic models were developed using deep learning (2D and 3D neural networks) and traditional machine learning (11 algorithms with PyRadiomics-derived features). Multimodal features underwent Principal Component Analysis (PCA) for dimension reduction and were fused for final analysis. Results: Comparative analysis of 1066 patients’ CT imaging revealed the muscle-based model outperformed the esophageal plus stomach model in predicting N2 staging (0.63 ± 0.11 vs. 0.52 ± 0.11, p = 0.03). Subsequently, multimodal fusion models were established for predicting pathological subtypes, T staging, and N staging. The logistic regression (LR) fusion model showed optimal performance in predicting pathological subtypes, achieving accuracy (ACC) of 0.919 in the training set and 0.884 in the validation set. For predicting T staging, the support vector machine (SVM) model demonstrated the highest accuracy, with training and validation accuracies of 0.909 and 0.907, respectively. The multilayer perceptron (MLP) fusion model achieved the best performance among all models tested for N staging prediction, although the accuracy remained moderate (ACC = 0.704 in the training set and 0.685 in the validation set), indicating potential for further optimization. Fusion models significantly outperformed single-modality models. Conclusions: Based on CT imaging data from 1066 patients, this study systematically constructed predictive models for pathological subtypes, T staging, and N staging of esophageal cancer. Comparative analysis of models using esophageal, esophageal plus stomach, and muscle modalities demonstrated that muscle imaging features contribute to diagnostic accuracy. Multimodal fusion models consistently showed superior performance.

Heavy metals are widespread environmental contaminants that have attracted considerable attention because of the potential human health risks. Heavy metals can lead to cardiovascular disease and chest pain is the most common precursor symptom. The study aimed to investigate the association between metal exposure and chest pain. This cross-sectional study used data obtained from the 2003 to 2012 National Health and Nutrition Examination Survey. Three metals: lead (Pb), cadmium (Cd), mercury (Hg) in the blood and ten metals: barium (Ba), Cd, cobalt (Co), cesium (Cs), molybdenum (Mo), Pb, antimony (Sb), thallium (Tl), tungsten (Tu), uranium (Ur) in the urine were studied. Using weighted logistic regression models, the relationship between the metal exposure and chest pain was investigated. The hazard ratios (HR) and 95% confidence intervals (95% CI) for all-cause mortality were calculated by weighted Cox proportional hazards models. By applying restricted cubic spline (RCS) analysis, we confirmed linear or nonlinear relationships between metal exposure and all-cause mortality. After adjusting for potential confounding factors, our study found a significant positive association between urinary Sb concentration and chest pain (quartile 4 vs quartile 1, odds ratio [OR] 1.55, 95% CI: 1.02–2.35, P = .042). Additionally, each 1-unit increase in blood Cd concentration was associated with a 22% increased risk of all-cause mortality (HR: 1.22, 95% CI: 1.01–1.48). Additionally, RCS analysis showed a nonlinear relationship between the urine Sb concentration and chest pain (P for nonlinear = .0009). A linear relationship was revealed between the urine Cd concentration and all-cause mortality in participants without chest pain (P for nonlinear = .0858). We observed higher odds of chest pain in participants with elevated urinary Sb concentrations, with those in the highest quartile of Sb concentration showing 55% increased odds of chest pain compared to the lowest quartile (OR: 1.55, 95% CI: 1.02–2.35, P = .042). Besides, urinary Sb concentration levels were significantly associated with chest pain. Cd concentration levels in the blood and urine were associated with all-cause mortality. This study explored the associations between metal exposure and chest pain incidence, as well as all-cause mortality. However, due to the cross-sectional design, causality cannot be established.