Evaluation of lifestyle behaviors, anxiety and depression in patients with hematologic disorders.

Patients with hematologic disorders may experience anxiety and depression due to their immunocompromised status and potential side effects of therapies. Healthy lifestyle behaviors might enhance the mental health. To evaluate the association of both separate and clustering pattern lifestyle behaviors with anxiety and depression in hematological patients, healthcare providers can develop future initiatives that respond to the specific needs of this population. A total of 185 patients with hematologic disorders were enrolled in this cross-sectional study. Linear regression analysis was performed to measure the association of separate lifestyles with anxiety and depression. Latent class analysis was further conducted to identify homogeneous and mutually exclusive lifestyle classes, and the logistic regression was then used to assess the relationship between class memberships and symptoms of anxiety and depression. The study found sleep quality was correlated with anxiety and depression. Nevertheless, no association of anxious and depressive symptoms with sitting and exercise, dietary habits, toxicant exposure, drinking, and smoking, in either the overall patient population or patients classified by hematologic neoplasms. Two latent classes of lifestyle behaviors were further identified, but the class memberships were independent of anxiety and depression. The study suggested that promoting sleep quality was a viable intervention for patients with hematologic disorders. However, the clustering pattern of lifestyles may not be a reliable indicator of psychological issues.

Association of lifestyle behaviors with health-related quality of life among patients with hematologic diseases.

PURPOSE: Health-related quality of life (HRQoL) is a multi-dimensional construct used to assess the impact of health status on quality of life, and it is known to be affected by lifestyle behaviors. This study focused on multiple lifestyle behaviors among patients with hematologic diseases, including physical activity, dietary intake, sleep quality, occupational exposure, alcohol consumption and smoking. The main objective was to investigate the association of both individual and clustering of health behaviors with HRQoL among the population with hematologic diseases based on a comprehensive lifestyle survey. METHODS: A total of 539 patients with hematologic diseases aged over 18 years were enrolled in this cross-sectional study. Latent class analysis was used to identify homogeneous, mutually exclusive lifestyle classes, and multinomial logistic regression was then performed to explore the association of lifestyle classes membership with HRQoL. Meanwhile, multiple linear regression and quantile regression were used to identify the relationship between individual lifestyle behaviors and HRQoL. RESULTS: A three-class model was selected based on conceptual interpretation and model fit. We found no association between multiple lifestyle behaviors and HRQoL in the 3-class model, either in the whole patients or in subgroups stratified by hematological malignancies. Further research on each lifestyle found that physical activity, dietary intake, occupational exposure, alcohol consumption or smoking were independent of HRQoL. Sleep quality was positively associated with HRQoL. CONCLUSION: Our findings suggested that clustering of lifestyle behaviors may not be an indicator to reflect the health quality of patients with hematologic diseases. Sleep represents a viable intervention target that can confer health benefits on the hematologic patients.

Acne detection and severity evaluation with interpretable convolutional neural network models.

BACKGROUND: Acne vulgaris is one of the most prevalent skin conditions, which harms not only the patients' physiological conditions, but also their mental health. Early diagnosis and accurate continuous self-monitoring could help control and alleviate their discomfort. OBJECTIVE: We focus on the development and comparison of deep learning models for locating acne lesions on facial images, thus making estimations on the acne severity on faces via medical criterion. METHODS: Different from most existing literature on facial acne analysis, the considered models in this study are object detection models with convolutional neural network (CNN) as backbone and has better interpretability. Thus, they produce more credible results of acne detection and facial acne severity evaluation. RESULTS: Experiments with real data validate the effectiveness of these models. The highest mean average precision (mAP) is 0.536 on an open source dataset. Corresponding error of acne lesion counting can be as low as 0.43 ± 6.65 on this dataset. CONCLUSIONS: The presented models have been released to public via deployed as a freely accessible WeChat applet service, which provides continuous out-of-hospital self-monitoring to patients. This also aids the dermatologists to track the progress of this disease and to assess the effectiveness of treatment.