Effect of COVID-19 vaccination on the menstrual cycle.

Numerous anecdotal accounts and qualitative research studies have reported on post-vaccination menstrual irregularities in women of reproductive age. However, none have quantified the impact. This is the first systematic review and meta-analysis to quantify and characterize the menstrual irregularities associated with vaccination for women of reproductive age. A search on July 20, 2022, retrieved articles published between December 1, 2019, and July 1, 2022, from MEDLINE, Embase, and Web of Science. The included articles were studies with full texts written in English that reported on menstrual irregularities for vaccinated vs. unvaccinated women of reproductive age. The quality of the studies was evaluated using the Study Quality Assessment Tool for Observation Cohort and Cross-Sectional Studies. Four observational studies were included. Review Manager was used to generating a forest plot with odds ratios (ORs) at the 95% confidence interval (CI), finding statistically significant associations between vaccination and menstrual irregularities for 25,054 women of reproductive age (OR = 1.91, CI: 1.76-2.07) with a significant overall effect of the mean (Z = 16.01, p < 0.0001). The studies were heterogeneous with significant dispersion of values (χ2 = 195.10 at df = 3, p < 0.00001, I 2 = 98%). The findings of this systematic review and meta-analysis are limited by the availability of quantitative data. The results have implications for treating women of reproductive age with menstrual irregularities and informing them about the potential side effects of vaccinations.

Menstrual cycles during COVID-19 lockdowns: A systematic review and meta-analysis.

Coronavirus disease 2019 lockdowns produced psychological and lifestyle consequences for women of reproductive age and changes in their menstrual cycles. To our knowledge, this is the first systematic review to characterize changes in menstrual cycle length associated with lockdowns compared to non-lockdown periods. A search on 5 May 2022 retrieved articles published between 1 December 2019, and 1 May 2022, from Medline, Embase, and Web of Science. The included articles were peer-reviewed observational studies with full texts in English, that reported menstrual cycle lengths during lockdowns and non-lockdowns. Cross-sectional and cohort studies were appraised using the Appraisal tool for Cross-Sectional Studies and the Cochrane Risk of Bias Tool for Cohort Studies, respectively. Review Manager was used to generate a forest plot with odds ratios (OR) at the 95% confidence interval (CI), finding a significant association between lockdown and menstrual cycle length changes for 21,729 women of reproductive age (OR = 9.14, CI: 3.16-26.50) with a significant overall effect of the mean (Z = 4.08, p < 0.0001). High heterogeneity with significant dispersion of values was observed (I 2 = 99%, τ = 1.40, χ2 = 583.78, p < 0.0001). This review was limited by the availability of published articles that favored high-income countries. The results have implications for adequately preparing women and assisting them with menstrual concerns during lockdown periods.

The Use of Audio Signals for Detecting COVID-19: A Systematic Review.

A systematic review on the topic of automatic detection of COVID-19 using audio signals was performed. A total of 48 papers were obtained after screening 659 records identified in the PubMed, IEEE Xplore, Embase, and Google Scholar databases. The reviewed studies employ a mixture of open-access and self-collected datasets. Because COVID-19 has only recently been investigated, there is a limited amount of available data. Most of the data are crowdsourced, which motivated a detailed study of the various pre-processing techniques used by the reviewed studies. Although 13 of the 48 identified papers show promising results, several have been performed with small-scale datasets (<200). Among those papers, convolutional neural networks and support vector machine algorithms were the best-performing methods. The analysis of the extracted features showed that Mel-frequency cepstral coefficients and zero-crossing rate continue to be the most popular choices. Less common alternatives, such as non-linear features, have also been proven to be effective. The reported values for sensitivity range from 65.0% to 99.8% and those for accuracy from 59.0% to 99.8%.

Challenges and Opportunities of Deep Learning for Cough-Based COVID-19 Diagnosis: A Scoping Review.

In the past two years, medical researchers and data scientists worldwide have focused their efforts on containing the pandemic of coronavirus disease 2019 (COVID-19). Deep learning models have been proven to be capable of efficient medical diagnosis and prognosis in cancer, common lung diseases, and COVID-19. On the other hand, artificial neural networks have demonstrated their potential in pattern recognition and classification in various domains, including healthcare. This literature review aims to report the state of research on developing neural network models to diagnose COVID-19 from cough sounds to create a cost-efficient and accessible testing tool in the fight against the pandemic. A total of 35 papers were included in this review following a screening of the 161 outputs of the literature search. We extracted information from articles on data resources, model structures, and evaluation metrics and then explored the scope of experimental studies and methodologies and analyzed their outcomes and limitations. We found that cough is a biomarker, and its associated information can determine an individual's health status. Convolutional neural networks were predominantly used, suggesting they are particularly suitable for feature extraction and classification. The reported accuracy values ranged from 73.1% to 98.5%. Moreover, the dataset sizes ranged from 16 to over 30,000 cough audio samples. Although deep learning is a promising prospect in identifying COVID-19, we identified a gap in the literature on research conducted over large and diversified data sets.

A Ranking of the Most Common Maternal COVID-19 Symptoms: A Systematic Review.

As the coronavirus disease 2019 (COVID-19) continues to devastate health systems worldwide, there is particular concern over the health and safety of one high-risk group, pregnant women, due to their altered immune systems. Since health workers regularly rely on symptoms to inform clinical treatment, it became critical to maintain a ranked list of COVID-19 symptoms specific to pregnant women. This systematic review investigated the prevalence of common COVID-19 symptoms in pregnant women and compared the ranked list of symptoms to articles of various sizes. Articles were included if they discussed pregnant women diagnosed with COVID-19 using polymerase chain reaction testing, and women present symptoms of COVID-19 and were published between December 1, 2019, and December 1, 2021; while articles were excluded if they did not report on pregnant women with COVID-19 displaying symptoms of COVID-19. Articles were identified on OVID MedLine and Embase in January of 2022. The risk of bias and quality appraisal was assessed using a nine-item modified Scottish Intercollegiate Guidelines Network checklist for case-control studies. The search results included 78 articles that described 41,513 pregnant women with 42 unique COVID-19 symptoms. When ranked, the most common symptoms were found to be cough (10,843 cases, 16.02%), fever (7,653 cases, 11.31%), myalgia (6,505 cases, 9.61%), headache (5,264 cases, 7.78%), and dyspnea (5,184 cases, 7.66%). When compared to other articles in the literature with sample sizes of n = 23,434, n = 8,207, and n = 651, the ranking largely aligned with those in other articles with large sample sizes and did not align with the results of articles with small sample sizes. The symptom ranking may be used to inform testing for COVID-19 in the clinic. Research is rapidly evolving with the ongoing nature of the pandemic, challenging the generalizability of the results.

Virtual Arm Boot Camp (V-ABC): study protocol for a mixed-methods study to increase upper limb recovery after stroke with an intensive program coupled with a grasp count device.

BACKGROUND: Encouraging upper limb use and increasing intensity of practice in rehabilitation are two important goals for optimizing upper limb recovery post stroke. Feedback from novel wearable sensors may influence practice behaviour to promote achieving these goals. A wearable sensor can potentially be used in conjunction with a virtually monitored home program for greater patient convenience, or due to restrictions that preclude in-person visits, such as COVID-19. This trial aims to (1) determine the efficacy of a virtual behaviour change program that relies on feedback from a custom wearable sensor to increase use and function of the upper limb post stroke; and (2) explore the experiences and perceptions of using a program coupled with wearable sensors to increase arm use from the perspective of people with stroke. METHODS: This mixed-methods study will utilize a prospective controlled trial with random allocation to immediate or 3-week delayed entry to determine the efficacy of a 3-week behaviour change program with a nested qualitative description study. The intervention, the Virtual Arm Boot Camp (V-ABC) features feedback from a wearable device, which is intended to increase upper limb use post stroke, as well as 6 virtual sessions with a therapist. Sixty-four adults within 1-year post stroke onset will be recruited from seven rehabilitation centres. All outcomes will be collected virtually. The primary outcome measure is upper limb use measured by grasp counts over 3 days from the wearable sensor (TENZR) after the 3-week intervention. Secondary outcomes include upper limb function (Arm Capacity and Movement Test) and self-reported function (Hand Function and Strength subscale from the Stroke Impact Scale). Outcome data will be collected at baseline, post-intervention and at 2 months retention. The qualitative component will explore the experiences and acceptability of using a home program with a wearable sensor for increasing arm use from the point of view of individuals with stroke. Semi-structured interviews will be conducted with participants after they have experienced the intervention. Qualitative data will be analysed using content analysis. DISCUSSION: This study will provide novel information regarding the efficacy and acceptability of virtually delivered programs to improve upper extremity recovery, and the use of wearable sensors to assist with behaviour change. TRIAL REGISTRATION: ClinicalTrials.gov NCT04232163 . January 18, 2020.

Validity of Apgar Score as an Indicator of Neonatal SARS-CoV-2 Infection: A Scoping Review

The coronavirus disease 2019 (COVID-19) pandemic has had profound impacts on healthcare systems worldwide, particularly regarding the care of pregnant women and their neonates. The use of the Apgar score—a discrete numerical index used to evaluate neonatal condition immediately following delivery that has been used ubiquitously as a clinical indicator of neonatal condition and widely reported in the literature for decades—has continued during the pandemic. Although health systems adopted protocols that addressed pregnant women and their neonates during the pandemic, limited research has assessed the validity of Apgar scores for determining neonatal conditions in the context of COVID-19. Therefore, this scoping review was conducted on the first 2 years of the pandemic and included mothers with reverse transcription-polymerase chain reaction confirmed COVID-19 and their resulting positive or negative neonates. In total, 1,966 articles were assessed for eligibility, yielding 246 articles describing 663 neonates. Neonates who tested negative had median Apgar scores of 9 and 9 at 1 and 5 mins, respectively, while test-positive neonates had median Apgar scores of 8 and 9 at the same time points. The proportions of test-negative neonates with Apgar scores below 7 were 29 (4%) and 11 (2%) at 1 and 5 mins, which was not statistically significant (p = 0.327, χ2 = 0.961). These proportions were even lower for positive neonates: 22 (3%) and 11 (2%) at 1 and 5 mins, respectively, which was not statistically significant (p = 1, χ2 = 0). The low proportion of Apgar scores below 7 suggests that low Apgar scores are likely to be associated with severe maternal COVID-19 symptoms during delivery rather than neonatal COVID-19. Therefore, this study indicated that Apgar scores are poor indicators of neonatal COVID-19 status.

The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective.

Chest X-ray imaging technology used for the early detection and screening of COVID-19 pneumonia is both accessible worldwide and affordable compared to other non-invasive technologies. Additionally, deep learning methods have recently shown remarkable results in detecting COVID-19 on chest X-rays, making it a promising screening technology for COVID-19. Deep learning relies on a large amount of data to avoid overfitting. While overfitting can result in perfect modeling on the original training dataset, on a new testing dataset it can fail to achieve high accuracy. In the image processing field, an image augmentation step (i.e., adding more training data) is often used to reduce overfitting on the training dataset, and improve prediction accuracy on the testing dataset. In this paper, we examined the impact of geometric augmentations as implemented in several recent publications for detecting COVID-19. We compared the performance of 17 deep learning algorithms with and without different geometric augmentations. We empirically examined the influence of augmentation with respect to detection accuracy, dataset diversity, augmentation methodology, and network size. Contrary to expectation, our results show that the removal of recently used geometrical augmentation steps actually improved the Matthews correlation coefficient (MCC) of 17 models. The MCC without augmentation (MCC = 0.51) outperformed four recent geometrical augmentations (MCC = 0.47 for Data Augmentation 1, MCC = 0.44 for Data Augmentation 2, MCC = 0.48 for Data Augmentation 3, and MCC = 0.49 for Data Augmentation 4). When we retrained a recently published deep learning without augmentation on the same dataset, the detection accuracy significantly increased, with a χ McNema r ' s statistic 2 = 163 . 2 and a p-value of 2.23 × 10-37. This is an interesting finding that may improve current deep learning algorithms using geometrical augmentations for detecting COVID-19. We also provide clinical perspectives on geometric augmentation to consider regarding the development of a robust COVID-19 X-ray-based detector.

The Performance of Deep Neural Networks in Differentiating Chest X-Rays of COVID-19 Patients From Other Bacterial and Viral Pneumonias.

Chest radiography is a critical tool in the early detection, management planning, and follow-up evaluation of COVID-19 pneumonia; however, in smaller clinics around the world, there is a shortage of radiologists to analyze large number of examinations especially performed during a pandemic. Limited availability of high-resolution computed tomography and real-time polymerase chain reaction in developing countries and regions of high patient turnover also emphasizes the importance of chest radiography as both a screening and diagnostic tool. In this paper, we compare the performance of 17 available deep learning algorithms to help identify imaging features of COVID19 pneumonia. We utilize an existing diagnostic technology (chest radiography) and preexisting neural networks (DarkNet-19) to detect imaging features of COVID-19 pneumonia. Our approach eliminates the extra time and resources needed to develop new technology and associated algorithms, thus aiding the front-line healthcare workers in the race against the COVID-19 pandemic. Our results show that DarkNet-19 is the optimal pre-trained neural network for the detection of radiographic features of COVID-19 pneumonia, scoring an overall accuracy of 94.28% over 5,854 X-ray images. We also present a custom visualization of the results that can be used to highlight important visual biomarkers of the disease and disease progression.