We aimed to use deep learning to detect tuberculosis in chest radiographs in annual workers’ health examination data and compare the performances of convolutional neural networks (CNNs) based on images only (I-CNN) and CNNs including demographic variables (D-CNN). The I-CNN and D-CNN models were trained on 1000 chest X-ray images, both positive and negative, for tuberculosis. Feature extraction was conducted using VGG19, InceptionV3, ResNet50, DenseNet121, and InceptionResNetV2. Age, weight, height, and gender were recorded as demographic variables. The area under the receiver operating characteristic (ROC) curve (AUC) was calculated for model comparison. The AUC values of the D-CNN models were greater than that of I-CNN. The AUC values for VGG19 increased by 0.0144 (0.957 to 0.9714) in the training set, and by 0.0138 (0.9075 to 0.9213) in the test set (both p < 0.05). The D-CNN models show greater sensitivity than I-CNN models (0.815 vs. 0.775, respectively) at the same cut-off point for the same specificity of 0.962. The sensitivity of D-CNN does not attenuate as much as that of I-CNN, even when specificity is increased by cut-off points. Conclusion: Our results indicate that machine learning can facilitate the detection of tuberculosis in chest X-rays, and demographic factors can improve this process.

No abstract

Background The burden of rare diseases on society and patients’ families has increased in Korea. However, because of the infrequency of rare diseases, there is a lack of resources and information to address these cases and inadequate funding for the management of these patients. We investigated the average annual cumulative incidence of rare diseases and the trends in annual cumulative incidence from 2011 to 2015 in Korea by using nationwide administrative data from the Korean National Health Insurance Service (NHIS) database for patients registered with the co-payment assistance policy for rare and incurable diseases. Annual cumulative incidence per 10,000,000 was calculated as the total number of newly enrolled patients with the Korean Standard Classification of Diseases (KCD)-7 code in the register, divided by the number of residents with health insurance coverage during each year. We employed simple linear regression analysis to evaluate the trends in annual cumulative incidence/10,000,000 population per year for each rare disease. Results Overall, national support was provided for patients with 415 KCD codes listed among the targeted rare diseases. The total number of newly enrolled patients with rare diseases was 53,831 in 2011, 52,658 in 2012, 52,955 in 2013, 71,530 in 2014, and 70,559 in 2015. The number of rare diseases with an average annual cumulative incidence of 100/10,000,000 and above was 22 (5.30%), while there were 227 (54.70%) and 148 (35.66%) with an average cumulative incidence between 1/10,000,000 and 100/10,000,000 and less than 1/10,000,000, respectively. The trends in the annual cumulative incidence for 43 rare diseases were statistically significant ( p -value < 0.05). The rare diseases for which the incremental trend per year was statistically significant were sarcoidosis (D86, D86.0, D86.1, D86.2, D86.3, D86.8, D86.9), Parkinson’s disease (G20), Guillain-Barré syndrome (G61.0), primary biliary cirrhosis (K74.3) and Sjogren’s syndrome (M35.0). Conclusions The number of rare diseases showing an increasing trend in annual cumulative incidence was higher than the number of diseases showing a decreasing trend in annual cumulative incidence. Given that the definition and diagnosis vary based on country and that there is difficulty in identifying valid cases, further detection strategies are needed to establish the incidence of each rare disease considering the importance of establishing a health policy based on the actual incidence of the targeted diseases. Electronic supplementary material The online version of this article (10.1186/s13023-019-1032-6) contains supplementary material, which is available to authorized users.

We analysed cancer risk in road transportation workers (RTWs) exposed to traffic air pollution and motor vehicle engine exhaust using the Korean National Health Insurance Service database. RTWs were defined as individuals in the transportation workers group doing road transportation. First admission history of cancer within a 3-year wash-out period was defined as an incident case. The crude incidence, standardised incidence ratio (SIR), and 95% confidence interval (CI) of all cancer risk of RTWs were compared with those of government employees or the whole working population. In total, 3,074 cancer cases were found among RTWs. The respective SIRs and 95% CIs for cancers in RTWs compared with those in the whole population were as follows: liver and intrahepatic bile duct cancers, 1.15 and 1.04-1.27; other digestive organ cancers, 1.28 and 1.04-1.57; trachea, bronchus, and lung cancers, 1.28 and 1.15-1.43; and bladder cancer, 1.26 and 1.03-1.52, respectively. The corresponding SIRs and 95% CIs were also higher in RTWs than in government employees. RTWs have a high risk of developing cancer, including cancer in the liver, intrahepatic bile ducts, other digestive organs, trachea, bronchus, lung, and bladder. Our results can assist in establishing prevention strategies for various cancers in RTWs. Road transport workers (RTWs) such as truck, bus, and taxi drivers account for approximately 3% of the working-age population in Korea 1. RTWs face accident risks and injury by motor vehicles and are exposed to various chemicals, including motor engine exhaust 2. Motor engine exhaust is a complex mixture of particulates and gases 2. Various hydrocarbons and derivatives (such as benzene, formaldehyde, toluene, and sulphur dioxide); inorganic sulphates and nitrates; metals, including lead and platinum; and polycyclic aromatic hydrocarbons (PAHs) make up the mixture of particulates and gases from vehicle engine exhaust 3. The International Agency for Research on Cancer (IARC) reviewed the literature and categorised diesel engine exhaust (DEE) as a Group 1 carcinogen, indicating 'carcinogenic to humans' , in 2012. They confirmed its carcinogenicity for lung cancer and reported a positive association with bladder cancer. The IARC 2012 report showed that engine exhaust increased risk of cancers, such as brain tumours 4 , colorectal cancer 5 , and breast cancer 6. Furthermore, animal studies and cellular experiments have shown that a significant relationship exists between engine exhaust and various cancer risks other than lung cancer 7. One recent cohort study that assessed traffic air pollution exposure for 20 years showed an increased odds of lung, bladder, kidney, and prostate cancer 8. Studies have shown when inhaled, fine particles can go through the systemic circulation and consequently cause DNA damage, which is linked to carcinogenesis 9-11. However, there is a lack of studies about the association between traffic exhaust and gastrointestinal tract cancers. A well designed pooling analysis of four cohorts showed that the h...

We aimed to investigate the association between long working hours and periodontitis, and whether such an association constitutes an exposure-response relationship. Data for this study were collected from the Korea National Health and Nutrition Examination Surveys conducted from 2007 to 2014; 17,533 workers (9,483 of men and 8,050 of women) were included. The odds ratios (OR) and 95% confidence intervals (CI) for the analysis of periodontitis defined as positive of Community Periodontal Index in relation to working hours were calculated using multiple logistic regression models with various stratifications. Compared to participants who worked ≤40 hours per week, the prevalence ratio (95% CI) for the periodontitis was 1.19 (1.14–1.24) and full adjusted OR (95% CI) was 1.09 (1.02–1.18) in participants who worked over 40 hours per week. The OR (95% CI) for periodontitis were 1.09 (0.99–1.19) in working group of 40< and ≥52 and 1.10 (1.01–1.20) in working group of >52 hours per week with a significant trend (p = 0.0233) even after adjusting for age, socioeconomic status, healthy behaviour, chronic disease, and dental care status. Long working hours are associated with periodontitis among Korean workers in an exposure-response manner.

This study aimed to investigate the effect of facing complaining customer and suppressed emotion at worksite on sleep disturbance among working population. We enrolled 13,066 paid workers (male = 6,839, female = 6,227, age < 65 years) in the 3rd Korean Working Condition Survey (2011). The odds ratio (OR) and 95% confidence intervals (CI) for sleep disturbance occurrence were calculated using multiple logistic regression models. Among workers in working environments where they always engage complaining customers had a significantly higher risk for sleep disturbance than rarely group (The OR [95% CI]; 5.46 [3.43–8.68] in male, 5.59 [3.30–9.46] in female workers). The OR (95% CI) for sleep disturbance was 1.78 (1.16–2.73) and 1.63 (1.02–2.63), for the male and female groups always suppressing their emotions at the workplace compared with those rarely group. Compared to those who both rarely engaged complaining customers and rarely suppressed their emotions at work, the OR (CI) for sleep disturbance was 9.66 (4.34–20.80) and 10.17 (4.46–22.07), for men and women always exposed to both factors. Sleep disturbance was affected by interactions of both emotional demands (engaging complaining customers and suppressing emotions at the workplace). The level of emotional demand, including engaging complaining customers and suppressing emotions at the workplace is significantly associated with sleep disturbance among Korean working population.

BackgroundThere is a lack of statistical analysis investigating the relationship between sleep problems and commute time in Korea. We aimed to analyze the association between representative health symptoms, sleep disturbances, and commute time according to working hours in Korea.MethodsThe 4th Korean Working Conditions Survey data were used for analysis, and unpaid family workers and workers who work fewer than three days in a week were excluded. Commute time, working hours, and sleep hours were assessed using self-reported questionnaires. Odds ratios (ORs) with 95% confidence intervals (CIs) for sleep problems were calculated using a multivariate logistic regression model with ≤10 min commute time as the reference group.ResultsAmong a total of 28,804 workers (men = 14,945, women = 13,859), 2.6% of men and 3.2% of women experienced sleep problems. In both sexes, long commute time (51–60 minutes and >60 minutes) showed an increased OR [men, 2.03 (CI = 1.32–3.13) and 2.05 (CI = 1.33–3.17); women, 1.58 (CI = 1.05–2.39) and 1.63 (CI = 1.06–2.50), respectively]. In stratification analysis of working hours, long commute time (51–60 and > 60 minutes) showed an increased OR in men working >40 hours/week [2.08 (CI = 1.16–3.71) and 1.92 (CI = 1.08–3.41), respectively]. Furthermore, long commute time (41–50, 51–60, and >60 minutes) showed an increased OR in women working >40 hours/week [2.40 (CI = 1.27–4.55), 2.28 (CI = 1.25–4.16), and 2.19 (CI = 1.17–4.16), respectively]. Moreover, commute time >60 minutes showed an increased OR in women working ≤40 hours/week [1.96 (CI = 1.06–3.62)].ConclusionThis large cross-sectional study highlights that long commute time is related to sleep problems in both sexes. Shorter commute times and decreased working hours are needed to prevent sleep problems in workers.

BackgroundWe aim to discuss the overall effect of customer service manual (CSM) on service industry workers using Korean Working Condition Survey.MethodsOut of 50,007 total survey participants, 11,946 customer service workers were included in the current study (5613 men, 6333 women). Answers to survey questions were used to define the use of CSM, emotional burden, emotional dissonance, engaging angry customers and other covariates. Emotional burden included either depressive event or stress level. Odds ratio (OR) with 95% confidence interval (95% CI) of experiencing emotional burden was calculated by logistic regression model. Interaction effect between CSM and engaging angry customer on emotional burden was also estimated.ResultsOut of 11,946 subjects, total of 3279 (27.4%) have experienced emotional burden. OR (95% CI) of experiencing emotional burden was 1.40 (1.19–1.64) in men and 1.25 (1.09–1.44) in women. There was gender difference in interaction effect between the use of CSM and engaging angry customers. In men, OR (95% CI) was 3.16 (1.38–7.23) with additive effect when always engaging angry customers with CSM compared to rarely engaging without CSM, while in women OR (95% CI) was 8.85 (3.96–19.75) with synergistic effect. Moreover, the risk of depressive event increased only in women with OR (95% CI) 2.22 (1.42–3.48).ConclusionsOur current study highlighted association between emotional burden and CSM in both men and women service workers. Furthermore, women were affected more severely by CSM. The results from current study suggest that CSM should be changed appropriately to benefit workers.