Path-enhanced graph convolutional networks for node classification without features.

Most current graph neural networks (GNNs) are designed from the view of methodology and rarely consider the inherent characters of graph. Although the inherent characters may impact the performance of GNNs, very few methods are proposed to resolve the issue. In this work, we mainly focus on improving the performance of graph convolutional networks (GCNs) on the graphs without node features.

Subjective Perception of Work and the Home Care Workers' Depression.

The care crisis has become a global trend, and the demand for child and elderly care is increasing worldwide. The increasing number of home care workers plays a significant role in meeting this demand in developing countries. The mental health of these workers is associated with the quality of care they provide, which has rarely been studied.

[Compliance of antihypertensive drug use in patients with hypertension].

Unlabelled: >

Objective: To understand the compliance of antihypertensive drug use in patients with hypertension.

Methods: A retrospective analysis was conducted among 218 patients with hypertension to understand their drug use compliancy and influencing factors, including side effect of the drugs, drug type, educational level, economic status and drug use length.

Results: The factors including disease course, drug type, drug use length and drug side effects, the economy status, educational level, awareness of hypertension related knowledge and psychological reaction could significantly influence the compliance of antihypertensive drug use.