Introduction: Real-time evaluations of the severity of depressive symptoms are of great significance for the diagnosis and treatment of patients with major depressive disorder (MDD). In clinical practice, the evaluation approaches are mainly based on psychological scales and doctor-patient interviews, which are time-consuming and labor-intensive. Also, the accuracy of results mainly depends on the subjective judgment of the clinician. With the development of artificial intelligence (AI) technology, more and more machine learning methods are used to diagnose depression by appearance characteristics. Most of the previous research focused on the study of single-modal data; however, in recent years, many studies have shown that multi-modal data has better prediction performance than single-modal data. This study aimed to develop a measurement of depression severity from expression and action features and to assess its validity among the patients with MDD.Methods: We proposed a multi-modal deep convolutional neural network (CNN) to evaluate the severity of depressive symptoms in real-time, which was based on the detection of patients’ facial expression and body movement from videos captured by ordinary cameras. We established behavioral depression degree (BDD) metrics, which combines expression entropy and action entropy to measure the depression severity of MDD patients.Results: We found that the information extracted from different modes, when integrated in appropriate proportions, can significantly improve the accuracy of the evaluation, which has not been reported in previous studies. This method presented an over 74% Pearson similarity between BDD and self-rating depression scale (SDS), self-rating anxiety scale (SAS), and Hamilton depression scale (HAMD). In addition, we tracked and evaluated the changes of BDD in patients at different stages of a course of treatment and the results obtained were in agreement with the evaluation from the scales.Discussion: The BDD can effectively measure the current state of patients’ depression and its changing trend according to the patient’s expression and action features. Our model may provide an automatic auxiliary tool for the diagnosis and treatment of MDD.

This study examines the institutional and attitudinal changes in elder care homes in Tianjin, China. Based on a survey conducted in 2001 with 61 elder home managers and 265 elder residents, this study examines 1) factors that influence elder home managers' views about elder home development and 2) elders' evaluation of elder home quality and their levels of willingness to stay in such homes. Findings show that elder home managers view their autonomy in financing and administration as a very important factor for future development of an elder home industry. Elders' overall evaluation of elder home quality was high. Elders' willingness to stay in elder homes was related to two factors: their living arrangements prior to elder home placement and their assessment of the cost involved for such care. This suggests that the limited level of autonomy in private elder home administration and financing is hindering the development of elder homes. As adult children become increasingly unavailable due to the one-child policy and geographic mobility, institutional care for aging parents is likely to become a major option for familial care in China. The government should grant greater autonomy to private elder homes in order to encourage elder home development.

Studies show that caregiving can have negative consequences on the psychological and physical health of its providers. However, few studies have examined the immediate and long-term impact of caregiving on health and none have considered these longitudinal associations among women in a predominately family-care society such as China. Six waves of data from the Ever-Married Women Survey component of the China Health and Nutrition Survey (n = 6,178) are used for analysis. Multivariate latent growth models are used to examine trajectories of self-rated health associated with providing care to parents (parental caregiving) among young-adult and middle-aged women in China. Results show that women who are caregivers to their parents have consistently worse self-reported health than women who do not have caregiving responsibilities. We find that caregivers--especially those who provide high-intensity care--exhibit initially low levels of health, followed by a period of health improvement that is comparable to noncaregivers. However, this pattern of role adaptation in women is followed by a precipitous decline in self-rated health in later years. The findings demonstrate the subjective health consequences of caregiving for women in China and provide new evidence to support the life course processes of wear-and-tear and role adaptation.

This paper introduces the theory of genetic algorithm. The specific operation flow of genetic algorithm is described. The application of genetic algorithm in function optimization has been achieved by the using of matlab programming language. The process of programming shows that it is very easy, flexible and efficient to optimize and compute with matlab language, and the effectiveness of genetic algorithm in function optimization has been demonstrated by the matlab simulation results.