The effects of a combination of 3D virtual reality and hands-on horticultural activities on mastery, achievement motives, self-esteem, isolation and depression: a quasi-experimental study.

BACKGROUND: Aging societies are a public health concern worldwide. It is critical to develop strategies that harness technology to enhance older adults' mastery, achievement motives, self-esteem, isolation and depression effectively. METHODS: This study aimed to explore the effects of a combination of three-dimensional virtual reality (VR) and hands-on horticultural activities on the psychological well-being of community-dwelling older adults. We used a quasi-experimental design. A total of 62 community-dwelling older adults were recruited and assigned to the experimental (n = 32) and comparison groups (n = 30). The members of the experimental group participated in an 8-week intervention program. Participants of both groups completed before-and-after intervention measurements for outcome variables that included perceived self-esteem, depression, isolation, and mastery and achievement motives, which were analyzed using the generalized estimating equation (GEE). A baseline score of depression was used as an adjustment for the GEE analyses to eliminate the effects of depression on outcomes. RESULTS: After controlling age and gender as confounders, GEE analyses indicated that the experimental group showed significant post-intervention improvements in scores for self-esteem (ß = 2.18, P = .005) and mastery (ß = 1.23, P = .039), compared to the control group. CONCLUSIONS: This study supported a combination of three-dimensional VR and hands-on horticultural activities on community-dwelling older adults to improve self-esteem and mastery. The findings suggest that the future implementation of a similar program would be feasible and beneficial to community-dwelling older adults. TRIAL REGISTRATION: The study was posted on www. CLINICALTRIALS: gov (NCT05087654) on 21/10/2021. It was approved by the Institutional Review Board of En Chu Kong Hospital and performed in accordance with the Declaration of Helsinki.

General deep learning model for detecting diabetic retinopathy.

BACKGROUND: Doctors can detect symptoms of diabetic retinopathy (DR) early by using retinal ophthalmoscopy, and they can improve diagnostic efficiency with the assistance of deep learning to select treatments and support personnel workflow. Conventionally, most deep learning methods for DR diagnosis categorize retinal ophthalmoscopy images into training and validation data sets according to the 80/20 rule, and they use the synthetic minority oversampling technique (SMOTE) in data processing (e.g., rotating, scaling, and translating training images) to increase the number of training samples. Oversampling training may lead to overfitting of the training model. Therefore, untrained or unverified images can yield erroneous predictions. Although the accuracy of prediction results is 90%-99%, this overfitting of training data may distort training module variables. RESULTS: This study uses a 2-stage training method to solve the overfitting problem. In the training phase, to build the model, the Learning module 1 used to identify the DR and no-DR. The Learning module 2 on SMOTE synthetic datasets to identify the mild-NPDR, moderate NPDR, severe NPDR and proliferative DR classification. These two modules also used early stopping and data dividing methods to reduce overfitting by oversampling. In the test phase, we use the DIARETDB0, DIARETDB1, eOphtha, MESSIDOR, and DRIVE datasets to evaluate the performance of the training network. The prediction accuracy achieved to 85.38%, 84.27%, 85.75%, 86.73%, and 92.5%. CONCLUSIONS: Based on the experiment, a general deep learning model for detecting DR was developed, and it could be used with all DR databases. We provided a simple method of addressing the imbalance of DR databases, and this method can be used with other medical images.