Background Population-based studies have linked measures of sleep disordered breathing to nocturnally occurring atrial fibrillation (AF) episodes. Whether measures of sleep disordered breathing and sleep quality are associated with prevalent AF has not been studied in an unselected population. We investigated the cross-sectional association with prevalent AF of objectively collected prespecified measures of overnight sleep breathing disturbances, sleep stage distributions, arousal and sleep duration. Methods AF prevalence, defined by diagnosis codes, study electrocardiography and sleep study were examined among Multi-Ethnic Study of Atherosclerosis (MESA) participants who underwent polysomnography in the MESA Sleep Study (n=2048). Measurements and main results Higher apnoea hypopnoea index (AHI) was associated with increased odds of AF, although the significance was attenuated after full adjustment for covariates including prevalent cardiovascular disease (OR: 1.22 (0.99 to 1.49) per SD (17/h), p=0.06). Analyses of sleep architecture measures and AF revealed significantly lower odds of AF associated with longer duration of slow wave sleep (OR: 0.66 (0.5 to 0.89) per SD (34 min), p=0.01) which persisted after additionally adjusting for AHI (OR: 0.68 (0.51 to 0.92), p=0.01). Higher sleep efficiency was significantly associated with lower likelihood of AF but the significance was lost when adjusted for AHI. No significant association was present between sleep duration and AF. In a model including AHI and arousal index, the association between AHI and AF was strengthened (AHI: OR 1.49 (1.15 to 1.91) per SD, p=0.002) and a significant inverse association between arousal index and AF was observed (OR 0.65 (0.50 to 0.86) per SD (12/h), p=0.005). Conclusions In a study of a large multiethnic population, AF was associated with AHI severity, and was more common in individuals with poor sleep quality as measured by reduced slow wave sleep time, a finding that was independent of AHI.

Deep learning of fundus photograph has emerged as a practical and cost-effective technique for automatic screening and diagnosis of severer diabetic retinopathy (DR). The entropy image of luminance of fundus photograph has been demonstrated to increase the detection performance for referable DR using a convolutional neural network- (CNN-) based system. In this paper, the entropy image computed by using the green component of fundus photograph is proposed. In addition, image enhancement by unsharp masking (UM) is utilized for preprocessing before calculating the entropy images. The bichannel CNN incorporating the features of both the entropy images of the gray level and the green component preprocessed by UM is also proposed to improve the detection performance of referable DR by deep learning.

Background: Both genetic and environmental factors have been reasoned for cancer development in schizophrenia patients. However, the influence of age of onset and duration of schizophrenia on cancer incidence has rarely been emphasized. Besides, bipolar disorder tends to resemble schizophrenia from the perspective of multiple rare mutations. Comparing pattern and risk of cancers between schizophrenia and bipolar patients is illuminating. Methods: This study used the Taiwan National Health Insurance Database. A total of 71 317 schizophrenia and 20 567 bipolar disorder patients from 1997 to 2009 were enrolled. Both cohorts were followed up for cancer during the same period by record linkage with the cancer certification in Taiwan. Age and gender standardized incidence ratios (SIRs) of overall and site-specific cancers were calculated. Results: The SIR for all cancers was 1.17 for the schizophrenia cohort. Increased cancer risk (SIR: 1.31, 95% CI: 1.17–1.48) was observed in females but not males. For the bipolar disorder cohort, the SIR for all cancers was 1.29, but the excess risk was found in males (SIR: 1.42, 95% CI: 1.14–1.77) and not females. Cancer risk decreases as the duration and age of onset of schizophrenia increases. If schizophrenia is diagnosed before 50, the SIRs for colorectal, breast, cervical, and uterine cancers increase but if diagnosed after 50, the SIRs for all cancers decrease except for breast cancer. In bipolar disorder, the SIRs for all site-specific cancers were insignificant. Conclusions: Among schizophrenia patients, overall cancer risk varies inversely with age at diagnosis and disease duration. Besides, gender-specific cancer risks differ between schizophrenia and bipolar disorder.

Entropy images, representing the complexity of original fundus photographs, may strengthen the contrast between diabetic retinopathy (DR) lesions and unaffected areas. The aim of this study is to compare the detection performance for severe DR between original fundus photographs and entropy images by deep learning. A sample of 21,123 interpretable fundus photographs obtained from a publicly available data set was expanded to 33,000 images by rotating and flipping. All photographs were transformed into entropy images using block size 9 and downsized to a standard resolution of 100 × 100 pixels. The stages of DR are classified into 5 grades based on the International Clinical Diabetic Retinopathy Disease Severity Scale: Grade 0 (no DR), Grade 1 (mild nonproliferative DR), Grade 2 (moderate nonproliferative DR), Grade 3 (severe nonproliferative DR), and Grade 4 (proliferative DR). Of these 33,000 photographs, 30,000 images were randomly selected as the training set, and the remaining 3,000 images were used as the testing set. Both the original fundus photographs and the entropy images were used as the inputs of convolutional neural network (CNN), and the results of detecting referable DR (Grades 2–4) as the outputs from the two data sets were compared. The detection accuracy, sensitivity, and specificity of using the original fundus photographs data set were 81.80%, 68.36%, 89.87%, respectively, for the entropy images data set, and the figures significantly increased to 86.10%, 73.24%, and 93.81%, respectively (all p values <0.001). The entropy image quantifies the amount of information in the fundus photograph and efficiently accelerates the generating of feature maps in the CNN. The research results draw the conclusion that transformed entropy imaging of fundus photographs can increase the machinery detection accuracy, sensitivity, and specificity of referable DR for the deep learning-based system.

Rationale and design of the cardiorespiratory fitness and hospitalization events in armed forces study in Eastern Taiwan

Military personnel have greater psychological stress and are at higher suicide attempt risk compared with the general population. High mental stress may cause suicidal ideations which are crucially driving suicide attempts. However, traditional statistical methods could only find a moderate degree of correlation between psychological stress and suicidal ideation in non-psychiatric individuals. This paper utilizes machine learning techniques including logistic regression, decision tree, random forest, gradient boosting regression tree, support vector machine, and multilayer perceptron to predict the presence of suicidal ideation by six important psychological stress domains of the military males and females. The accuracies of all the six machine learning methods are over 98%. Among them, the multilayer perceptron and support vector machine provide the best predictions of suicide ideation approximately to 100%. As compared with the BSRS-5 score ≥ 7, a conventional criterion, for the presence of suicidal ideation ≥ 1, the proposed algorithms can improve the performances of accuracy, sensitivity, specificity, precision, the AUC of ROC curve and the AUC of PR curve up to 5.7%, 35.9%, 4.6%, 65.2%, 4.3% and 53.2%, respectively; and for the presence of more severely intense suicidal ideation ≥ 2, the improvements are 6.1%, 26.2%, 5.8%, 83.5%, 2.8% and 64.7%, respectively.