Paediatricians' awareness of Canadian screen time guidelines, perception of screen time use, and counselling during the COVID-19 pandemic

Objectives Paediatricians are essential in guiding families on screen time use as digital media becomes increasingly prevalent. While this has been highlighted through the COVID-19 pandemic there is no literature on paediatricians' awareness of Canadian screen time guidelines, or perception of these guidelines during this time. The aim of this study was to assess pediatricians' knowledge, attitudes, and comfort with the Canadian Paediatric Society's (CPS) screen time guidelines, specifically during the COVID-19 pandemic. Methods Our survey was developed by a paediatric resident and paediatric endocrinologist, reviewed by local experts, and sent electronically to members of the CPS Community and Developmental Paediatrics sections. Results All 53 respondents were aware of current CPS screen time guidelines, and the majority self-reported fair to excellent knowledge of guidelines for both age groups (<5 years and school-aged children/adolescents). Over 80% noticed increased screen use during the pandemic, and 98% were somewhat or very concerned about screen use and their patients' health and well-being. Pediatricians reported concerns about associations between increased screen time with worsening behaviour, mental health concerns, obesity, and sedentary lifestyle. The greatest barrier to reducing screen time was perceived insufficient motivation or support from caregivers/families. Conclusions Responding Canadian paediatricians are knowledgeable and comfortable with current screen time guidelines in Canada. Despite this, there is increasing concern with health outcomes associated with screen use. These results highlight paediatricians' important role in counselling patients and may encourage further local advocacy and public education around screen use and associated health risks in children.

Transfer learning and data augmentation techniques to the COVID-19 identification tasks in ComParE 2021

In this work, we propose several techniques to address data scarceness in ComParE 2021 COVID-19 identification tasks for the application of deep models such as Convolutional Neural Networks. Data is initially preprocessed into spectrogram or MFCC-gram formats. After preprocessing, we combine three different data augmentation techniques to be applied in model training. Then we employ transfer learning techniques from pretrained audio neural networks. Those techniques are applied to several distinct neural architectures. For COVID-19 identification in speech segments, we obtained competitive results. On the other hand, in the identification task based on cough data, we succeeded in producing a noticeable improvement on existing baselines, reaching 75.9% unweighted average recall (UAR). Copyright © 2021 ISCA.