Purpose: To describe the characteristics and effectiveness of pediatric telerehabilitation interventions offered to children 0–12 years old or to their families. Methods: A systematic review was conducted on randomized control trials published between 2007 and 2018 involving at least one rehabilitation professional who provided services remotely. Information was extracted about key study, participants and intervention characteristics. The percentage of outcomes that improved were computed per study, and per intervention characteristic. Results: Out of 4472 screened articles, 23 were included. Most studies were published after 2016 and evaluated outcomes related to the child’s behavior (n = 12, 52.2%) or to the parent (n = 10, 43.5%), such as parental skills or stress. Overall, 56.1% (SD: 38.5%) of evaluated outcomes improved following telerehabilitation. A great diversity of population and teleintervention characteristics was observed. Effective interventions tended to target parents, centered around an exercise program, used a coaching approach, focused on improving children’s behavioral functioning, lasted >8 weeks and were offered at least once a week. Conclusions: Intervention characteristics that appear to yield better outcomes should inform the development of future telerehabilitation studies, especially in populations for whom telerehabilitation is currently understudied (e.g., children’s with physical functioning difficulties). Future trials should compare telerehabilitation interventions to well-described evidence-based face-to-face interventions, and document their cost-effectiveness.

Background. Now that early identification of toddlers with autism spectrum disorder (ASD) is possible, efforts are being made to develop interventions for children under three years of age. Most studies on early intervention have focused on intensive and individual interventions. However, parent training interventions that help parents interact and communicate with their toddlers with ASD might be a good alternative to promote the development of their child’s sociocommunicative skills.Objective. This review aims to systematically examine (1) the use of parent training interventions for children with ASD under three years of age and (2) their effects on children’s development, parents’ well-being and parent-child interactions.Methods. Systematic searches were conducted to retrieve studies in which at least one parent was trained to implement ASD-specific techniques with their toddlers (0–36 months old) with a diagnosis of or suspected ASD.Results. Fifteen studies, involving 484 children (mean age: 23.26 months), were included in this review. Only two of them met criteria for conclusive evidence. Results show that parents were able to implement newly learned strategies and were generally very satisfied with parent training programs. However, findings pertaining to the children’s communication and socioemotional skills, parent-child interactions, and parental well-being were inconclusive.

Objective To explore leisure participation by people with traumatic brain injury (TBI) and reasons underlying changes after the trauma. Participants Twenty-six individuals with mild to severe TBI. Main Measure Leisure Profile, a semi-structured questionnaire measuring involvement in leisure activities before and after TBI (frequency of activities, degree of interest, and desire to modify one's leisure activities), attitudes toward leisure, and difficulties that might influence leisure activities (impairments and environmental obstacles). Results Leisure participation was greatly disrupted after TBI, with 92% of the participants reporting a reduction posttrauma. Less severe injuries, more time since the injury, and the presence of social obstacles in the environment were positively correlated with leisure participation. Motor impairments had a negative impact on leisure participation. Conclusion TBI has a significant negative effect on leisure participation. Leisure activities should be evaluated and included in a therapy program designed to promote reintegration into society and work.

Deep learning models have gained prominence in human activity recognition using ambient sensors, particularly for telemonitoring older adults’ daily activities in real-world scenarios. However, collecting large volumes of annotated sensor data presents a formidable challenge, given the time-consuming and costly nature of traditional manual annotation methods, especially for extensive projects. In response to this challenge, we propose a novel AttCLHAR model rooted in the self-supervised learning framework SimCLR and augmented with a self-attention mechanism. This model is designed for human activity recognition utilizing ambient sensor data, tailored explicitly for scenarios with limited or no annotations. AttCLHAR encompasses unsupervised pre-training and fine-tuning phases, sharing a common encoder module with two convolutional layers and a long short-term memory (LSTM) layer. The output is further connected to a self-attention layer, allowing the model to selectively focus on different input sequence segments. The incorporation of sharpness-aware minimization (SAM) aims to enhance model generalization by penalizing loss sharpness. The pre-training phase focuses on learning representative features from abundant unlabeled data, capturing both spatial and temporal dependencies in the sensor data. It facilitates the extraction of informative features for subsequent fine-tuning tasks. We extensively evaluated the AttCLHAR model using three CASAS smart home datasets (Aruba-1, Aruba-2, and Milan). We compared its performance against the SimCLR framework, SimCLR with SAM, and SimCLR with the self-attention layer. The experimental results demonstrate the superior performance of our approach, especially in semi-supervised and transfer learning scenarios. It outperforms existing models, marking a significant advancement in using self-supervised learning to extract valuable insights from unlabeled ambient sensor data in real-world environments.