A Two-Way Street? Reciprocal Associations Between Parental Warmth and Hostility with Substance Use Among Justice-Involved Adolescents.

Transactional developmental theories propose that poor parenting behaviors contribute to youth substance use, and youth substance use contributes to poor parenting behaviors. However, research aimed at testing these theories has not distinguished: (1) between- and within-person sources of variance; (2) maternal and paternal parenting behaviors; and (3) alcohol, marijuana, and other illicit drug use. This study addressed these limitations by investigating the reciprocal associations between maternal and paternal warmth and hostility with alcohol, marijuana, and other illicit drug use among justice-involved adolescents, an at-risk population for substance use. 1354 justice-involved adolescents (86.4% male; Mage = 16.04 [SD = 0.14], range = 14-17; 41.4% Black, 33.5% Hispanic, 20.2% White, 4.8% other race/ethnicity) completed self-reports assessing parental warmth, parental hostility, and substance use every six months for 36 months. Random-intercept structural equation models disaggregated between- and within-person associations. At the between-person level, maternal and paternal warmth were negatively associated with alcohol, marijuana, and other illicit drug use, whereas maternal and paternal hostility were positively associated with alcohol, marijuana, and other illicit drug use. At the within-person level, maternal and paternal warmth predicted decreases in marijuana and other illicit drug use, and paternal warmth predicted decreases in alcohol use six months later. Maternal hostility predicted increases in subsequent marijuana and other illicit drug use. Marijuana and other illicit drug use predicted decreases in subsequent paternal hostility. The results are partially consistent with transactional developmental models proposing recursive influences between parenting behaviors and youth substance use. Evocative effects were in the opposite direction than expected and specific to fathers, such that youth drug use was related to improvements in the father-youth relationship. The results support the potential utility of family-based interventions for substance use among justice-involved adolescents.

IoT-Enabled Classification of Echocardiogram Images for Cardiovascular Disease Risk Prediction with Pre-Trained Recurrent Convolutional Neural Networks.

Cardiovascular diseases currently present a key health concern, contributing to an increase in death rates worldwide. In this phase of increasing mortality rates, healthcare represents a major field of research, and the knowledge acquired from this analysis of health information will assist in the early identification of disease. The retrieval of medical information is becoming increasingly important to make an early diagnosis and provide timely treatment. Medical image segmentation and classification is an emerging field of research in medical image processing. In this research, the data collected from an Internet of Things (IoT)-based device, the health records of patients, and echocardiogram images are considered. The images are pre-processed and segmented, and then further processed using deep learning techniques for classification as well as forecasting the risk of heart disease. Segmentation is attained via fuzzy C-means clustering (FCM) and classification using a pretrained recurrent neural network (PRCNN). Based on the findings, the proposed approach achieves 99.5% accuracy, which is higher than the current state-of-the-art techniques.