Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient

The Covid-19 pandemic is one of the most significant global health concerns that have emerged in this decade. Intelligent healthcare technology and techniques based on speech signal and artificial intelligence make it feasible to provide a faster and more efficient timely detection of Covid-19. The main objective of our study is to design speech signal-based noninvasive, low-cost, remote diagnosis of Covid-19. In this study, we have developed system to detect Covid-19 from speech signal using Mel frequency magnitude coefficients (MFMC) and machine learning techniques. In order to capture higher-order spectral features, the spectrum is divided into a larger number of subbands with narrower bandwidths as MFMC, which leads to better frequency resolution and less overall noise. As a consequence of an improvement in frequency resolution as well as a decrease in the quantity of noise that is included with the extraction of MFMC, the higher-order MFMCs are able to identify Covid-19 from speech signals with an increased level of accuracy. The procedures for machine learning are often less complicated than those for deep learning, and they may commonly be carried out on regular computers. However, deep learning systems need extensive computing power and data storage. Twelve, twenty-four, thirty, and forty spectral coefficients are obtained using MFMC in our study, and from these coefficients, performance is accessed using machine learning classifiers, such as random forests and K-nearest neighbor (KNN);however, KNN has performed better than the other model with having AUC score of 0.80.

Machine learning approach for detecting Covid-19 from speech signal using Mel frequency magnitude coefficient.

The Covid-19 pandemic is one of the most significant global health concerns that have emerged in this decade. Intelligent healthcare technology and techniques based on speech signal and artificial intelligence make it feasible to provide a faster and more efficient timely detection of Covid-19. The main objective of our study is to design speech signal-based noninvasive, low-cost, remote diagnosis of Covid-19. In this study, we have developed system to detect Covid-19 from speech signal using Mel frequency magnitude coefficients (MFMC) and machine learning techniques. In order to capture higher-order spectral features, the spectrum is divided into a larger number of subbands with narrower bandwidths as MFMC, which leads to better frequency resolution and less overall noise. As a consequence of an improvement in frequency resolution as well as a decrease in the quantity of noise that is included with the extraction of MFMC, the higher-order MFMCs are able to identify Covid-19 from speech signals with an increased level of accuracy. The procedures for machine learning are often less complicated than those for deep learning, and they may commonly be carried out on regular computers. However, deep learning systems need extensive computing power and data storage. Twelve, twenty-four, thirty, and forty spectral coefficients are obtained using MFMC in our study, and from these coefficients, performance is accessed using machine learning classifiers, such as random forests and K-nearest neighbor (KNN); however, KNN has performed better than the other model with having AUC score of 0.80.

An observational multi-centric COVID-19 sequelae study among health care workers.

Background: India has seen more than 43 million confirmed cases of COVID-19 as of April 2022, with a recovery rate of 98.8%, resulting in a large section of the population including the healthcare workers (HCWs), susceptible to develop post COVID sequelae. This study was carried out to assess the nature and prevalence of medical sequelae following COVID-19 infection, and risk factors, if any. Methods: This was an observational, multicenter cross-sectional study conducted at eight tertiary care centers. The consenting participants were HCWs between 12 and 52 weeks post discharge after COVID-19 infection. Data on demographics, medical history, clinical features of COVID-19 and various symptoms of COVID sequelae was collected through specific questionnaire. Finding: Mean age of the 679 eligible participants was 31.49 ± 9.54 years. The overall prevalence of COVID sequelae was 30.34%, with fatigue (11.5%) being the most common followed by insomnia (8.5%), difficulty in breathing during activity (6%) and pain in joints (5%). The odds of having any sequelae were significantly higher among participants who had moderate to severe COVID-19 (OR 6.51; 95% CI 3.46-12.23) and lower among males (OR 0.55; 95% CI 0.39-0.76). Besides these, other predictors for having sequelae were age (≥45 years), presence of any comorbidity (especially hypertension and asthma), category of HCW (non-doctors vs doctors) and hospitalisation due to COVID-19. Interpretation: Approximately one-third of the participants experienced COVID sequelae. Severity of COVID illness, female gender, advanced age, co-morbidity were significant risk factors for COVID sequelae. Funding: This work is a part of Indian Council for Medical Research (ICMR)- Rational Use of Medicines network. No additional financial support was received from ICMR to carry out the work, for study materials, medical writing, and APC.

Impact of COVID-19 pandemic on pediatric cardiac services in India.

BACKGROUND: COVID-19 pandemic has disrupted pediatric cardiac services across the globe. Limited data are available on the impact of COVID.19 on pediatric cardiac care in India. AIMS: The aims are to study the impact of COVID-19 pandemic on the care of children with heart disease in India in terms of number of outpatient visits, hospitalizations, catheter-based interventions, and cardiac surgeries. SETTINGS AND DESIGN: This is a retrospective, multicentric, observational study. METHODS: We collected monthly data on the number and characteristics of outpatient visits, hospitalizations, catheter-based interventions, and cardiac surgeries and major hospital statistics, over a period of 5 months (April to August 2020), which coincided with the first wave of COVID-19 pandemic in India and compared it with data from the corresponding months in 2019. RESULTS: The outpatient visits across the 24 participating pediatric cardiac centers decreased by 74.5% in 2020 (n = 13,878) as compared to the corresponding period in 2019 (n = 54,213). The reduction in the number of hospitalizations, cardiac surgeries, and catheterization procedures was 66.8%, 73.0%, and 74.3%, respectively. The reduction in hospitalization was relatively less pronounced among neonates as compared to infants/children (47.6% vs. 70.1% reduction) and for emergency surgeries as compared to elective indications (27.8% vs. 79.2%). The overall in-hospital mortality was higher in 2020 (8.1%) as compared to 2019 (4.8%), with a higher postoperative mortality (9.1% vs. 4.3%). CONCLUSIONS: The current COVID-19 pandemic significantly impacted the delivery of pediatric cardiac care across India with two-third reduction in hospitalizations and cardiac surgeries. In an already resource-constrained environment, the impact of such a massive reduction in the number of surgeries could be significant over the coming years. These findings may prove useful in formulating strategy to manage subsequent waves of ongoing COVID-19 pandemic.

Perception of understanding COVID-19 among doctors at Patan Hospital, Nepal

Introduction: Coronavirus disease 2019 (COVID-19) is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and presents with fever, dry cough, fatigue, myalgia, and dyspnea. This study aims to is find out the understanding of COVID-19 among doctors at Patan Hospital. Method: A cross sectional was conducted among doctors at Patan Hospital, Patan Academy of Health Sciences, Nepal. The questionnaire in Google form consisted, part1 perception on COVID-19 and part2 understanding using multiple choice questions corresponding to the one to fifteen questionnaire in part1. Ethnical approval was obtained. Result: Sixty-one doctors participated in the study, of which 65.5% were directly involved in management of COVID-19. Perception and understanding regarding transmission status in country was 65.6% and 63.95% respectively, about case definition 90.1% and 62.2%, about when to do diagnostic tests 75.4% and 90.2%. Conclusion: There was difference in perception and understanding regarding COVID-19 among doctors, and areas to be reinforced were case definition, transmission classification, diagnostic tests. Keyword: COVID-19, doctors, perception, understanding