Upregulation of SLC2A genes that encode glucose transporter (GLUT) protein is associated with poor prognosis in many cancers. In colorectal cancer, studies reporting the association between overexpression of GLUT and poor clinical outcomes were flawed by small sample sizes or subjective interpretation of immunohistochemical staining. Here, we analyzed mRNA expressions in all 14 SLC2A genes and evaluated the association with prognosis in colorectal cancer using data from the Cancer Genome Atlas (TCGA) database. In the present study, we analyzed the expression of SLC2A genes in colorectal cancer and their association with prognosis using data obtained from the TCGA for the discovery sample, and a dataset from the Gene Expression Omnibus for the validation sample. SLC2A3 was significantly associated with overall survival (OS) and disease-free survival (DFS) in both the discovery sample (345 patients) and validation sample (501 patients). High SLC2A3 expression resulted in shorter OS and DFS. In multivariate analyses, high SLC2A3 levels predicted unfavorable OS (adjusted HR 1.95, 95% CI 1.22–3.11; P = 0.005) and were associated with poor DFS (adjusted HR 1.85, 95% CI 1.10–3.12; P = 0.02). Similar results were found in the discovery set. Upregulation of the SLC2A3 genes is associated with decreased OS and DFS in colorectal cancer patients. Therefore, assessment of SLC2A3 gene expression may useful for predicting prognosis in these patients.

The prevalence of metabolic syndrome (MS) in the nonobese population is not low. However, the identification and risk mitigation of MS are not easy in this population. We aimed to develop an MS prediction model using genetic and clinical factors of nonobese Koreans through machine learning methods. A prediction model for MS was designed for a nonobese population using clinical and genetic polymorphism information with five machine learning algorithms, including naïve Bayes classification (NB). The analysis was performed in two stages (training and test sets). Model A was designed with only clinical information (age, sex, body mass index, smoking status, alcohol consumption status, and exercise status), and for model B, genetic information (for 10 polymorphisms) was added to model A. Of the 7,502 nonobese participants, 647 (8.6%) had MS. In the test set analysis, for the maximum sensitivity criterion, NB showed the highest sensitivity: 0.38 for model A and 0.42 for model B. The specificity of NB was 0.79 for model A and 0.80 for model B. In a comparison of the performances of models A and B by NB, model B (area under the receiver operating characteristic curve [AUC] = 0.69, clinical and genetic information input) showed better performance than model A (AUC = 0.65, clinical information only input). We designed a prediction model for MS in a nonobese population using clinical and genetic information. With this model, we might convince nonobese MS individuals to undergo health checks and adopt behaviors associated with a preventive lifestyle.

A relationship between nonalcoholic fatty liver disease (NAFLD) and sarcopenia has been suggested. The aim of this study was to evaluate the association between NAFLD and skeletal muscle mass measured by computed tomography (CT). The clinical records of individuals visiting our center for a routine health check-up who underwent abdominal ultrasonography and abdominal CT scanning were retrospectively reviewed. Sarcopenia was diagnosed according to body mass index (BMI)-adjusted skeletal muscle mass, which was measured by CT (CT-measured skeletal muscle index (SMI_CT)). Of the 1828 subjects (1121 males; mean age 54.9 ± 9.5 years), 487 (26.6%) were obese (BMI ≥ 25 kg/m²), and 454 (24.8%) had low muscle mass. Sarcopenic subjects had a significantly higher prevalence of NAFLD than nonsarcopenic subjects, regardless of obesity (35.9% vs. 26.8%, p = 0.004 in the nonobese group; 76.6% vs. 63.0%, p = 0.003 in the obese group). Sarcopenia was significantly associated with the risk of NAFLD (adjusted odds ratio (OR) (95% confidence interval (CI)), 1.51 (1.15–1.99)), and the risk of NAFLD increased with increasing severity of sarcopenia (adjusted OR (95% CI), 1.45 (1.09–1.92) vs. 2.51 (1.16–5.56), mild vs. severe sarcopenia, respectively). When the risk of NAFLD was analyzed according to the SMI_CT quartiles, the adjusted OR and 95% CI for the lowest muscle mass quartile compared to the highest were 1.78 (1.17–2.72) in males and 2.39 (1.13–5.37) in females. Low skeletal muscle mass, which was precisely measured by CT, is independently associated with NAFLD, suggesting that sarcopenia is a risk factor for NAFLD.

Background: Machine learning (ML) is a promising methodology for classification and prediction applications in healthcare. However, this method has not been practically established for clinical data. Hyperuricemia is a biomarker of various chronic diseases. We aimed to predict uric acid status from basic healthcare checkup test results using several ML algorithms and to evaluate the performance. Methods: We designed a prediction model for hyperuricemia using a comprehensive health checkup database designed by the classification of ML algorithms, such as discrimination analysis, K-nearest neighbor, naïve Bayes (NBC), support vector machine, decision tree, and random forest classification (RFC). The performance of each algorithm was evaluated and compared with the performance of a conventional logistic regression (CLR) algorithm by receiver operating characteristic curve analysis. Results: Of the 38,001 participants, 7705 were hyperuricemic. For the maximum sensitivity criterion, NBC showed the highest sensitivity (0.73), and RFC showed the second highest (0.66); for the maximum balanced classification rate (BCR) criterion, RFC showed the highest BCR (0.68), and NBC showed the second highest (0.66) among the various ML algorithms for predicting uric acid status. In a comparison to the performance of NBC (area under the curve (AUC) = 0.669, 95% confidence intervals (CI) = 0.669–0.675) and RFC (AUC = 0.775, 95% CI 0.770–0.780) with a CLR algorithm (AUC = 0.568, 95% CI = 0.563–0.571), NBC and RFC showed significantly better performance (p < 0.001). Conclusions: The ML model was superior to the CLR model for the prediction of hyperuricemia. Future studies are needed to determine the best-performing ML algorithms based on data set characteristics. We believe that this study will be informative for studies using ML tools in clinical research.