In this study we examined the associations of physical education class participation with physical activity among adolescents. We analysed the Global School-based Student Health Survey data from 65 ...countries (N = 206,417; 11-17 years; 49% girls) collected between 2007 and 2016. We defined sufficient physical activity as achieving physical activities ≥ 60 min/day, and grouped physical education classes as '0 day/week', '1-2 days/week', and ' ≥ 3 days/week' participation. We used multivariable logistic regression to obtain country-level estimates, and meta-analysis to obtain pooled estimates. Compared to those who did not take any physical education classes, those who took classes ≥ 3 days/week had double the odds of being sufficiently active (OR 2.05, 95% CI 1.84-2.28) with no apparent gender/age group differences. The association estimates decreased with higher levels of country's income with OR 2.37 (1.51-3.73) for low-income and OR 1.85 (1.52-2.37) for high-income countries. Adolescents who participated in physical education classes 1-2 days/week had 26% higher odds of being sufficiently active with relatively higher odds for boys (30%) than girls (15%). Attending physical education classes was positively associated with physical activity among adolescents regardless of sex or age group. Quality physical education should be encouraged to promote physical activity of children and adolescents.
Deep neural networks (DNNs) have been widely applied for detecting COVID-19 in medical images. Existing studies mainly apply transfer learning and other data representation strategies to generate ...accurate point estimates. The generalization power of these networks is always questionable due to being developed using small datasets and failing to report their predictive confidence. Quantifying uncertainties associated with DNN predictions is a prerequisite for their trusted deployment in medical settings. Here we apply and evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray (CXR) images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced. Through comprehensive experiments, it is shown that networks pertained on CXR images outperform networks pretrained on natural image datasets such as ImageNet. Qualitatively and quantitatively evaluations also reveal that the predictive uncertainty estimates are statistically higher for erroneous predictions than correct predictions. Accordingly, uncertainty quantification methods are capable of flagging risky predictions with high uncertainty estimates. We also observe that ensemble methods more reliably capture uncertainties during the inference. DNN-based solutions for COVID-19 detection have been mainly proposed without any principled mechanism for risk mitigation. Previous studies have mainly focused on on generating single-valued predictions using pretrained DNNs. In this paper, we comprehensively apply and comparatively evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced for the first time. Using these new uncertainty performance metrics, we quantitatively demonstrate when we could trust DNN predictions for COVID-19 detection from chest X-rays. It is important to note the proposed novel uncertainty evaluation metrics are generic and could be applied for evaluation of probabilistic forecasts in all classification problems.
COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on ...image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.
The COVID-19 pandemic disrupted the personal, professional and social life of Australians with some people more impacted than others.
This study aimed to identify factors associated with ...psychological distress, fear and coping strategies during the COVID-19 pandemic in Australia.
A cross-sectional online survey was conducted among residents in Australia, including patients, frontline health and other essential service workers, and community members during June 2020. Psychological distress was assessed using the Kessler Psychological Distress Scale (K10); level of fear was assessed using the Fear of COVID-19 Scale (FCV-19S); and coping strategies were assessed using the Brief Resilient Coping Scale (BRCS). Logistic regression was used to identify factors associated with the extent of psychological distress, level of fear and coping strategies while adjusting for potential confounders.
Among 587 participants, the majority (391, 73.2%) were 30-59 years old and female (363, 61.8%). More than half (349, 59.5%) were born outside Australia and two-third (418, 71.5%) completed at least a Bachelor's degree. The majority (401, 71.5%) had a source of income, 243 (42.3%) self-identified as a frontline worker, and 335 (58.9%) reported financial impact due to COVID-19. Comorbidities such as pre-existing mental health conditions (AOR 3.13, 95% CIs 1.12-8.75), increased smoking (8.66, 1.08-69.1) and alcohol drinking (2.39, 1.05-5.47) over the last four weeks, high levels of fear (2.93, 1.83-4.67) and being female (1.74, 1.15-2.65) were associated with higher levels of psychological distress. Perceived distress due to change of employment status (4.14, 1.39-12.4), alcohol drinking (3.64, 1.54-8.58), providing care to known or suspected cases (3.64, 1.54-8.58), being female (1.56, 1.00-2.45), being 30-59 years old (2.29, 1.21-4.35) and having medium to high levels of psychological distress (2.90, 1.82-5.62) were associated with a higher level of fear; while healthcare service use in the last four weeks was associated with medium to high resilience.
This study identified individuals who were at higher risk of distress and fear during the COVID-19 pandemic specifically in the State of Victoria, Australia. Specific interventions to support the mental wellbeing of these individuals should be considered in addition to the existing resources within primary healthcare settings.
Type 2 diabetes mellitus (T2DM) is among the most prevalent noncommunicable health conditions worldwide, affecting over 500 million people globally. Diet is a key aspect of T2DM management with ...dietary modification shown to elicit clinically meaningful outcomes such as improved glycemic control, and reductions in weight and cardiovascular disease risk factors. Web-based interventions provide a potentially convenient and accessible method for delivering dietary education, but its effects on dietary behavior in people with T2DM are unknown.
The objective of this review was to determine the effectiveness of web-based interventions on dietary behavior change and glycemic control in people with T2DM.
Per PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, systematic literature searches were performed using Medline, Embase, The Cochrane Library, and CINAHL to retrieve papers from January 2013 to May 2019. Randomized controlled trials of web-based interventions in adults with T2DM with reported dietary assessment were included. Population and intervention characteristics, dietary guidelines and assessments, and significant clinical outcomes were extracted. Differences between groups and within groups were assessed for dietary behavior and clinical outcomes.
There were 714 records screened, and five studies comprising 1056 adults were included. Studies measured dietary changes by assessing overall diet quality, changes in specific dietary components, or dietary knowledge scores. Significant improvements in dietary behavior were reported in four out of the five studies, representing healthier food choices, improvements in eating habits, reductions in carbohydrates, added sugar, sodium, saturated fat and overall fat intake, and/or increases in dietary knowledge. Three studies found significant mean reductions for hemoglobin A1c ranging from -0.3% to -0.8%, and/or weight ranging from -2.3 kg to -12.7 kg, fasting blood glucose (-1 mmol/L), waist circumference (-1 cm), and triglycerides (-60.1 mg/dL). These studies provided varied dietary recommendations from standard dietary guidelines, national health program guidelines, and a very low carbohydrate ketogenic diet.
This review provided evidence that web-based interventions may be an effective way to support dietary behavior change in people with T2DM, potentially leading to changes in glycemic control and other clinical outcomes. However, the evidence should be viewed as preliminary as there were only five studies included with considerable heterogeneity in terms of the diets recommended, the dietary assessment measures used, the complexity of the interventions, and the modes and methods of delivery.
The COVID-19 pandemic has enormously affected the psychological well-being, social and working life of millions of people across the world. This study aimed to investigate the psychological distress, ...fear and coping strategies as a result of the COVID-19 pandemic and its associated factors among Malaysian residents. The mean age (±SD) of the participants (N = 720) was 31.7 (±11.5) years, and most of them were females (67.1%). Half of the participants had an income source, while 216 (30%) identified themselves as frontline health or essential service workers. People whose financial situation was impacted due to COVID-19 (AOR 2.16, 95% CIs 1.54-3.03), people who drank alcohol in the last four weeks (3.43, 1.45-8.10), people who were a patient (2.02, 1.39-2.93), and had higher levels of fear of COVID-19 (2.55, 1.70-3.80) were more likely to have higher levels of psychological distress. Participants who self-isolated due to exposure to COVID-19 (3.12, 1.04-9.32) and who had moderate to very high levels of psychological distress (2.56, 1.71-3.83) had higher levels of fear. Participants who provided care to a family member/patient with a suspected case of COVID-19 were more likely to be moderately to highly resilient compared to those who did not. Vulnerable groups of individuals such as patients and those impacted financially during COVID-19 should be supported for their mental wellbeing. Behavioural interventions should be targeted to reduce the impact of alcohol drinking during such crisis period.
Brain tumors (BTs) are one of the deadliest diseases that can significantly shorten a person's life. In recent years, deep learning has become increasingly popular for detecting and classifying BTs. ...In this paper, we propose a deep neural network architecture called NeuroNet19. It utilizes VGG19 as its backbone and incorporates a novel module named the Inverted Pyramid Pooling Module (iPPM). The iPPM captures multi-scale feature maps, ensuring the extraction of both local and global image contexts. This enhances the feature maps produced by the backbone, regardless of the spatial positioning or size of the tumors. To ensure the model's transparency and accountability, we employ Explainable AI. Specifically, we use Local Interpretable Model-Agnostic Explanations (LIME), which highlights the features or areas focused on while predicting individual images. NeuroNet19 is trained on four classes of BTs: glioma, meningioma, no tumor, and pituitary tumors. It is tested on a public dataset containing 7023 images. Our research demonstrates that NeuroNet19 achieves the highest accuracy at 99.3%, with precision, recall, and F1 scores at 99.2% and a Cohen Kappa coefficient (CKC) of 99%.
Caesarean delivery (C-section) has been increasing worldwide; however, many women from developing countries in Sub-Saharan Africa are deprived of these lifesaving services. This study aimed to ...explore the impact of certain socioeconomic factors, including respondent's education, husband's education, place of residence, and wealth index, on C-section delivery for women in Sub-Saharan Africa. We used pooled data from 36 demographic and health surveys (DHS) in Sub-Saharan Africa. Married women aged 15-49 years who have at least one child in the last five years were considered in this survey. After inclusion and excluding criteria, 234,660 participants were eligible for final analysis. Binary logistic regression was executed to determine the effects of selected socioeconomic factors. The countries were assembled into four sub-regions (Southern Africa, West Africa, East Africa, and Central Africa), and a meta-analysis was conducted. We performed random-effects model estimation for meta-analysis to assess the overall effects and consistency between covariates and utilization of C-section delivery as substantial heterogeneity was identified (I
> 50%). Furthermore, the meta-regression was carried out to explain the additional amount of heterogeneity by country levels. We performed a sensitivity analysis to examine the effects of outliers in this study. Findings suggest that less than 15% of women in many Sub-Saharan African countries had C-section delivery. Maternal education (OR 4.12; CI 3.75, 4.51), wealth index (OR 2.05; CI 1.94, 2.17), paternal education (OR 1.71; CI 1.57, 1.86), and place of residence (OR 1.51; CI 1.44, 1.58) were significantly associated with the utilization of C-section delivery. These results were also consistent in sub-regional meta-analyses. The meta-regression suggests that the total percentage of births attended by skilled health staff (TPBASHS) has a significant inverse association with C-section utilization regarding educational attainment (respondent & husband), place of residence, and wealth index. The data structure was restricted to define the distinction between elective and emergency c-sections. It is essential to provide an appropriate lifesaving mechanism, such as C-section delivery opportunities, through proper facilities for rural, uneducated, impoverished Sub-Saharan African women to minimize both maternal and infant mortality.
Traditional psychological theories are inadequate to fully leverage the potential of smartphones and improve the effectiveness of physical activity (PA) and sedentary behavior (SB) change ...interventions. Future interventions need to consider dynamic models taken from other disciplines, such as engineering (eg, control systems). The extent to which such dynamic models have been incorporated in the development of interventions for PA and SB remains unclear.
This review aims to quantify the number of studies that have used dynamic models to develop smartphone-based interventions to promote PA and reduce SB, describe their features, and evaluate their effectiveness where possible.
Databases including PubMed, PsycINFO, IEEE Xplore, Cochrane, and Scopus were searched from inception to May 15, 2019, using terms related to mobile health, dynamic models, SB, and PA. The included studies involved the following: PA or SB interventions involving human adults; either developed or evaluated integrated psychological theory with dynamic theories; used smartphones for the intervention delivery; the interventions were adaptive or just-in-time adaptive; included randomized controlled trials (RCTs), pilot RCTs, quasi-experimental, and pre-post study designs; and were published from 2000 onward. Outcomes included general characteristics, dynamic models, theory or construct integration, and measured SB and PA behaviors. Data were synthesized narratively. There was limited scope for meta-analysis because of the variability in the study results.
A total of 1087 publications were screened, with 11 publications describing 8 studies included in the review. All studies targeted PA; 4 also included SB. Social cognitive theory was the major psychological theory upon which the studies were based. Behavioral intervention technology, control systems, computational agent model, exploit-explore strategy, behavioral analytic algorithm, and dynamic decision network were the dynamic models used in the included studies. The effectiveness of quasi-experimental studies involved reduced SB (1 study; P=.08), increased light PA (1 study; P=.002), walking steps (2 studies; P=.06 and P<.001), walking time (1 study; P=.02), moderate-to-vigorous PA (2 studies; P=.08 and P=.81), and nonwalking exercise time (1 study; P=.31). RCT studies showed increased walking steps (1 study; P=.003) and walking time (1 study; P=.06). To measure activity, 5 studies used built-in smartphone sensors (ie, accelerometers), 3 of which used the phone's GPS, and 3 studies used wearable activity trackers.
To our knowledge, this is the first systematic review to report on smartphone-based studies to reduce SB and promote PA with a focus on integrated dynamic models. These findings highlight the scarcity of dynamic model-based smartphone studies to reduce SB or promote PA. The limited number of studies that incorporate these models shows promising findings. Future research is required to assess the effectiveness of dynamic models in promoting PA and reducing SB.
International Prospective Register of Systematic Reviews (PROSPERO) CRD42020139350; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=139350.
Preventing communicable diseases requires understanding the spread, epidemiology, clinical features, progression, and prognosis of the disease. Early identification of risk factors and clinical ...outcomes might help in identifying critically ill patients, providing appropriate treatment, and preventing mortality. We conducted a prospective study in patients with flu‐like symptoms referred to the imaging department of a tertiary hospital in Iran between March 3, 2020, and April 8, 2020. Patients with COVID‐19 were followed up after two months to check their health condition. The categorical data between groups were analyzed by Fisher's exact test and continuous data by Wilcoxon rank‐sum test. Three hundred and nineteen patients (mean age 45.48 ± 18.50 years, 177 women) were enrolled. Fever, dyspnea, weakness, shivering, C‐reactive protein, fatigue, dry cough, anorexia, anosmia, ageusia, dizziness, sweating, and age were the most important symptoms of COVID‐19 infection. Traveling in the past 3 months, asthma, taking corticosteroids, liver disease, rheumatological disease, cough with sputum, eczema, conjunctivitis, tobacco use, and chest pain did not show any relationship with COVID‐19. To the best of our knowledge, a number of factors associated with mortality due to COVID‐19 have been investigated for the first time in this study. Our results might be helpful in early prediction and risk reduction of mortality in patients infected with COVID‐19.