No abstract

No abstract

Cognitive behavioral therapy (CBT) is the first choice of treatment of obsessive–compulsive disorder (OCD) in children and adolescents. However, there is often a lack of access to appropriate treatment close to the home of the patients. An internet-based CBT via videoconferencing could facilitate access to state-of-the-art treatment even in remote areas. The aim of this study was to investigate feasibility and acceptability of this telemedical approach. A total of nine children received 14 sessions of CBT. The first session took place face-to-face, the remaining 13 sessions via videoconference. OCD symptoms were recorded with a smartphone app and therapy materials were made accessible in a data cloud. We assessed diagnostic data before and after treatment and obtained measures to feasibility, treatment satisfaction and acceptability. Outcomes showed high acceptance and satisfaction on the part of patients with online treatment (89%) and that face-to-face therapy was not preferred over an internet-based approach (67%). The majority of patients and their parents classified the quality of treatment as high. They emphasized the usefulness of exposures with response prevention (E/RP) in triggering situations at home. The app itself was rated as easy to operate and useful. In addition to feasibility, a significant decrease in obsessive–compulsive symptoms was also achieved. Internet-based CBT for pediatric OCD is feasible and well received by the patients and their parents. Furthermore, obsessive–compulsive symptomatology decreased in all patients. The results of this study are encouraging and suggest the significance of further research regarding this technology-supported approach, with a specific focus on efficacy.Trial registration number: Clinical trials AZ53-5400.1-004/44.

This paper describes technology developed to automatically grade Italian students (ages 9-16) on their English and German spoken language proficiency. The students' spoken answers are first transcribed by an automatic speech recognition (ASR) system and then scored using a feedforward neural network (NN) that processes features extracted from the automatic transcriptions. In-domain acoustic models, employing deep neural networks (DNNs), are derived by adapting the parameters of an original out of domain DNN. Automatic scores are computed for low level proficiency indicators -such as: lexical richness, syntax correctness, quality of pronunciation, discourse fluency, semantic relevance to the prompt, etc -defined by human experts in language proficiency. A set of experiments was carried out on a large set of data collected during proficiency evaluation campaigns involving thousands of students, manually scored by human experts. Obtained results are presented and discussed.

No abstract