A comprehensive screening method using machine learning and many factors (biological characteristics, Helicobacter pylori infection status, endoscopic findings and blood test results), accumulated daily as data in hospitals, could improve the accuracy of screening to classify patients at high or low risk of developing gastric cancer. We used XGBoost, a classification method known for achieving numerous winning solutions in data analysis competitions, to capture nonlinear relations among many input variables and outcomes using the boosting approach to machine learning. Longitudinal and comprehensive medical check-up data were collected from 25,942 participants who underwent multiple endoscopies from 2006 to 2017 at a single facility in Japan. The participants were classified into a case group (y = 1) or a control group (y = 0) if gastric cancer was or was not detected, respectively, during a 122-month period. Among 1,431 total participants (89 cases and 1,342 controls), 1,144 (80%) were randomly selected for use in training 10 classification models; the remaining 287 (20%) were used to evaluate the models. The results showed that XGBoost outperformed logistic regression and showed the highest area under the curve value (0.899). Accumulating more data in the facility and performing further analyses including other input variables may help expand the clinical utility.

Lifestyle factors including heavy alcohol consumption, heavy smoking, metabolic disorders, and hiatal hernia increased the risk of erosive esophagitis, but central obesity did not.

Objective To investigate the impact of metabolic and lifestyle factors on erosive esophagitis in young adults. Methods A total of 5,069 people under the age of 40 years old were enrolled in a medical survey at our institute. People with a previous history of upper gastrointestinal tract surgery were excluded, as were individuals taking medication for reflux symptoms, peptic ulcers, or malignancies. Independent and significant predictors affecting the presence of erosive esophagitis were determined by multivariate analysis. Results A total of 4,990 participants (male/female; 3,871/1,119, age; 33.9±3.9 years) were eligible. A total of 728 participants (14.6%) had erosive esophagitis. Male gender and increasing age were independent predictors for increased prevalence of erosive esophagitis (odds ratio=2.242 and 1.045. 95% confidence interval= 1.613-3.117 and 1.019-1.072; p<0.001 and 0.001, respectively). Moderate-to-heavy alcohol consumption, light-to-moderate-to-heavy smoking, hypertension, hyperglycemia, and hiatal hernia each significantly and independently increased the risk for erosive esophagitis (odds ratio=1.499, 1.398, 1.353, 1.570, 1.884, 1.297, 1.562, and 3.213. 95% confidence interval=1.181-1.903, 1.040-1.880, 1.094-1.675, 1.250-1.971, 1.307-2.716, 1.074-1.566, 1.063-2.295, and 2.712-3.807; p=0.001, 0.027, 0.005, <0.001, 0.001, <0.001, 0.007, 0.023, and <0.001 respectively). Helicobacter pylori infection decreased the risk for erosive esophagitis (odds ratio= 0.575, 95% confidence interval =0.436-0.759 p<0.001). Neither body mass index nor waist girth conferred increased risk of erosive esophagitis after adjusting for potential confounding factors. Conclusion Risk of erosive esophagitis in Japanese young adults was not increased by obesity, but it was increased by hiatal hernia and metabolic and lifestyle profiles including hypertension, hyperglycemia, alcohol consumption and smoking.

Aim:The aim was to investigate the respective associations between lifestyle and proteinuria and the estimated glomerular filtration rate (eGFR). Methods: The lifestyle habits of 25,493 middle-aged participants were investigated in a cross-sectional study to find habits that are associated with a low eGFR (＜60 mL/min/1.73 m 2 ) and/or the presence of proteinuria. The lifestyle habits of the participants were evaluated using a questionnaire. Unhealthy lifestyle habits were defined as follows: 1. obesity, 2. being a current/former smoker, 3. eating irregular meals, 4. having less than 5 hours sleep, 5. exercising less than once a week, and 6. drinking more than once a week. The associations among unhealthy habits, eGFR, and proteinuria were evaluated using multivariate analysis.

Soluble interleukin-2 receptor (sIL-2R) is produced by activated T and B cells, and the level of this receptor is elevated in patients with non-Hodgkin's lymphoma (NHL). The present study demonstrated that the sIL-2R level was high in the following groups of patients with aggressive NHL; those aged > or = 60 yr, those with a poor PS, those in Ann Arbor stage III or IV, and those in the high intermediate or high risk group according to the International Prognostic Index (IPI). Overall survival was significantly poorer when the sIL-2R level was 2000 U/ml or more. In addition, the overall survival of patients in the low (L) and low-intermediate (L-I) risk groups with an sIL-2R level of 3000 U/ml or more was significantly poorer, suggesting that the sIL-2R level could be particularly useful for identifying patients with a poor prognosis among the L and L-I risk groups. Univariate analysis identified some significant prognostic factors, and multivariate analysis of these factors plus the five IPI prognostic factors showed that the sIL-2R level was an independent prognostic indicator. In conclusion, the present findings established that the sIL-2R level is a significant independent prognostic factor in patients with aggressive NHL.