Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: Comparative Study.

BACKGROUND: To date, performance comparisons between men and machines have been carried out in many health domains. Yet machine learning (ML) models and human performance comparisons in audio-based respiratory diagnosis remain largely unexplored. OBJECTIVE: The primary objective of this study was to compare human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. METHODS: In this study, we compared human clinicians and an ML model in predicting COVID-19 from respiratory sound recordings. Prediction performance on 24 audio samples (12 tested positive) made by 36 clinicians with experience in treating COVID-19 or other respiratory illnesses was compared with predictions made by an ML model trained on 1162 samples. Each sample consisted of voice, cough, and breathing sound recordings from 1 subject, and the length of each sample was around 20 seconds. We also investigated whether combining the predictions of the model and human experts could further enhance the performance in terms of both accuracy and confidence. RESULTS: The ML model outperformed the clinicians, yielding a sensitivity of 0.75 and a specificity of 0.83, whereas the best performance achieved by the clinicians was 0.67 in terms of sensitivity and 0.75 in terms of specificity. Integrating the clinicians' and the model's predictions, however, could enhance performance further, achieving a sensitivity of 0.83 and a specificity of 0.92. CONCLUSIONS: Our findings suggest that the clinicians and the ML model could make better clinical decisions via a cooperative approach and achieve higher confidence in audio-based respiratory diagnosis.

Impact of the COVID-19 pandemic on diagnosis of respiratory diseases in the Northern Metropolitan Area in Barcelona (Spain).

OBJECTIVE: The COVID-19 pandemic has had a great effect on the management of chronic diseases, by limiting the access to primary care and to diagnostic procedures, causing a decline in the incidence of most diseases. Our aim was to analyze the impact of the pandemic on primary care new diagnoses of respiratory diseases. METHODS: Observational retrospective study performed to describe the effect of COVID-19 pandemic on the incidence of respiratory diseases according to primary care codification. Incidence rate ratio between pre-pandemic and pandemic period was calculated. RESULTS: We found a decrease in the incidence of respiratory conditions (IRR 0.65) during the pandemic period. When we compared the different groups of diseases according to ICD-10, we found a significant decrease in the number of new cases during the pandemic period, except in the case of pulmonary tuberculosis, abscesses or necrosis of the lungs and other respiratory complications (J95). Instead, we found increases in flu and pneumonia (IRR 2.17) and respiratory interstitial diseases (IRR 1.41). CONCLUSION: There has been a decrease in new diagnosis of most respiratory diseases during the COVID-19 pandemic.

Validity of diagnoses of respiratory diseases recorded in a Japanese administrative database.

BACKGROUND: Validating the information recorded in administrative databases is essential. However, no study has comprehensively validated the accuracy of Japanese Diagnosis Procedure Combination (DPC) data on various respiratory diseases. Therefore, this study aimed to evaluate the validity of diagnoses of respiratory diseases in the DPC database. METHODS: We conducted chart reviews of 400 patients hospitalized in the departments of respiratory medicine in two acute-care hospitals in Tokyo, between April 1, 2019 and March 31, 2021, and used them as reference standards. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of DPC data on 25 respiratory diseases were determined. RESULTS: Sensitivity ranged from 22.2% (aspiration pneumonia) to 100% (chronic eosinophilic pneumonia and malignant pleural mesothelioma) and was <50% for eight diseases, while specificity was >90% for all diseases. PPV ranged from 40.0% (aspiration pneumonia) to 100% (coronavirus disease 2019, bronchiectasis, chronic eosinophilic pneumonia, pulmonary hypertension, squamous cell carcinoma, small cell carcinoma, lung cancer of other histological types, and malignant pleural mesothelioma) and was >80% for 16 diseases. Except for chronic obstructive pulmonary disease (82.9%) and interstitial pneumonia (other than idiopathic pulmonary fibrosis) (85.4%), NPV was >90% for all diseases. These validity indices were similar in both hospitals. CONCLUSIONS: The validity of diagnoses of respiratory diseases in the DPC database was high in general, thereby providing an important basis for future studies.

Comparison of Clinical Findings in SARS-CoV-2 with Other Respiratory Viruses in Critically Ill Children during the COVID-19 Pandemic.

OBJECTIVES: The aim of this study was to compare the clinical and laboratory findings in SARS-CoV-2 (COVID-19) with those of other respiratory viruses in critically ill children. METHODS: It is a single center retrospective descriptive study conducted in a 32-bed pediatric intensive care unit (PICU). Our study was performed in Ankara City Hospital, Ankara, Turkey, between 1 March 2020, and 1 March 2021. Demographic and clinical characteristics of the patients were collected and we recorded the antibiotic use, antiviral treatments, respiratory and extracorporeal supports, PICU stay and survival rates. RESULTS: A total of 202 pediatric patients who tested positive for either COVID-19 or for another respiratory virus panel (RVP) were included in the study. Seventy-two patients were COVID-19 positive. The median age of COVID-19 positive patients and RVP positive patients was 97 and 17 months, respectively. Hypoxia was much more common in patients with RVP than in COVID-19 patients. Low oxygen saturation in arterial blood (SaO2), increased oxygen saturation index (OSI) and fraction of inspired oxygen (FiO2) needs were more significant in RVP patients than in COVID-19 patients. Respiratory support therapies, such as high-flow nasal cannula and non-invasive ventilation (NIV), were used more frequently in RVP patients than in COVID-19 patients. CONCLUSION: It is important to distinguish between COVID-19 and RVP cases in order to prioritize intensive care needs in these patients. In addition, non-Covid diseases should not be left aside in the pandemic and appropriate care should be provided to them.

COVID-19 originated in Wuhan, China, at the end of 2019 and has since spread around the world. During the key period of the pandemic from 1 March 2020, to 1 March 2021, the pediatric intensive care unit registered a total of 72 patients testing positive for SARS-CoV-2 and 130 patients positive for RVP on the respiratory virus panel. In this single-center study, we compared the clinical differences and course of the disease in pediatric intensive care patients infected with SARS-CoV-2 with patients diagnosed with respiratory tract viruses during the COVID-19 outbreak. Unlike previous studies, this is the first to compare the clinical manifestations of COVID-19 with other respiratory pathogens requiring intensive care. Respiratory support therapy, such as high-flow nasal cannula (HFNC) and NIV, was prescribed more frequently in RVP patients than in COVID-19 patients. In our study, low oxygen saturation in the arterial blood (SaO2), increased OSI and increased fraction of inspired oxygen (FiO2) requirements were more significant in RVP patients than in COVID-19 patients. In parallel, the need for mechanical ventilation was higher in RVP patients than in COVID-19 patients. Therefore, we believe that RVP patients should be followed more carefully during this pandemic period.

Admission respiratory status predicts mortality in COVID-19.

COVID-19 has significant case fatality. Glucocorticoids are the only treatment shown to improve survival, but only among patients requiring supplemental oxygen. WHO advises patients to seek medical care for "trouble breathing," but hypoxemic patients frequently have no respiratory symptoms. Our cohort study of hospitalized COVID-19 patients shows that respiratory symptoms are uncommon and not associated with mortality. By contrast, objective signs of respiratory compromise-oxygen saturation and respiratory rate-are associated with markedly elevated mortality. Our findings support expanding guidelines to include at-home assessment of oxygen saturation and respiratory rate in order to expedite life-saving treatments patients to high-risk COVID-19 patients.

Interleukin-11 signaling underlies fibrosis, parenchymal dysfunction, and chronic inflammation of the airway.

Interleukin (IL)-11 evolved as part of the innate immune response. In the human lung, IL-11 upregulation has been associated with viral infections and a range of fibroinflammatory diseases, including idiopathic pulmonary fibrosis. Transforming growth factor-beta (TGFß) and other disease factors can initiate an autocrine loop of IL-11 signaling in pulmonary fibroblasts, which, in a largely ERK-dependent manner, triggers the translation of profibrotic proteins. Lung epithelial cells also express the IL-11 receptor and transition into a mesenchymal-like state in response to IL-11 exposure. In mice, therapeutic targeting of IL-11 with antibodies can arrest and reverse bleomycin-induced pulmonary fibrosis and inflammation. Intriguingly, fibroblast-specific blockade of IL-11 signaling has anti-inflammatory effects, which suggests that lung inflammation is sustained, in part, through IL-11 activity in the stroma. Proinflammatory fibroblasts and their interaction with the damaged epithelium may represent an important but overlooked driver of lung disease. Initially thought of as a protective cytokine, IL-11 is now increasingly recognized as an important determinant of lung fibrosis, inflammation, and epithelial dysfunction.

Flow Cytometry: From Experimental Design to Its Application in the Diagnosis and Monitoring of Respiratory Diseases.

Recent advances in the field of flow cytometry (FCM) have highlighted the importance of incorporating it as a basic analysis tool in laboratories. FCM not only allows the identification of cell subpopulations by detecting the expression of molecules in the cell membrane or cytoplasm, but it can also quantify and identify soluble molecules. The proper functioning of the FCM requires six fundamental systems, from those related to the transport of events to the systems dedicated to the analysis of information. In this review, we have identified the main considerations that every FCM user must know for an optimal antibody panel design, the quality systems that must govern the FCM protocols to guarantee reproducible results in research or clinical laboratories. Finally, we have introduced the current evidence that highlights the relevance of FCM in the investigation and clinical diagnosis of respiratory diseases, establishing important advances in the basic and clinical study of diseases as old as Tuberculosis along with the recent proposals for the monitoring and classification of patients infected with the new SARS-CoV2 virus.

Differential diagnosis of COVID-19 in symptomatic patients at the University Hospital Center Mohammed VI, Marrakesh.

INTRODUCTION: coronavirus disease 2019 caused by severe acute respiratory syndrome coronavirus 2 was first reported in Wuhan, China. Clinical spectrum of this disease has nonspecific symptoms shared by many other frequent infectious diseases of the respiratory tract and other respiratory tract diseases. This study explains the importance of differential diagnosis between COVID-19 and other lung diseases. METHODS: we analyzed in this study, the demographic features, clinical presentations, laboratory data and radiologic findings of the COVID-19 patients in comparison to those with other respiratory infections or diseases. RESULTS: the mean age of all patients was 38.04 years; 35 patients were later confirmed to be positive for SARS-CoV-2 infection. The most common symptoms reported by both groups included nonproductive cough and myalgia. Two of the non-COVID-19 patients were having below 92% oxygen saturation and low systolic blood pressure. The patients shared relatively similar laboratory findings except 3% of the non-COVID-19 patients who had lympho-neutropenia and 22.6% had high levels of C-reactive protein. Pulmonary tuberculosis and autoimmune disease respiratory disorder were suspected in 2 of the non-COVID-19 patients respectively. CONCLUSION: we emphasize the importance of good screening protocols, rapid detection of SARS-CoV-2 and other most common respiratory pathogens, which may help for a better control of COVID-19 spread and avoid delayed care of other lung diseases.

Management of suspected COVID-19 patients in a low prevalence region.

The spread of the SARS-CoV-2 infection among population has imposed a re-organization of healthcare services, aiming at stratifying patients and dedicating specific areas where patients with suspected COVID-related respiratory disease could receive the necessary health care assistance while waiting for the confirmation of the diagnosis of COVID-19 disease. In this scenario, the pathway defined as a "grey zone" is strongly advocated. We describe the application of rules and pathways in a regional context with low diffusion of the infection among the general population in the attempt to provide the best care to respiratory patients with suspected COVID-19. To date, this process has avoided the worst-case scenario of intra-hospital epidemic outbreak.

The Role of Chest Imaging in Patient Management During the COVID-19 Pandemic: A Multinational Consensus Statement From the Fleischner Society.

With more than 900,000 confirmed cases worldwide and nearly 50,000 deaths during the first 3 months of 2020, the coronavirus disease 2019 (COVID-19) pandemic has emerged as an unprecedented health care crisis. The spread of COVID-19 has been heterogeneous, resulting in some regions having sporadic transmission and relatively few hospitalized patients with COVID-19 and others having community transmission that has led to overwhelming numbers of severe cases. For these regions, health care delivery has been disrupted and compromised by critical resource constraints in diagnostic testing, hospital beds, ventilators, and health care workers who have fallen ill to the virus exacerbated by shortages of personal protective equipment. Although mild cases mimic common upper respiratory viral infections, respiratory dysfunction becomes the principal source of morbidity and mortality as the disease advances. Thoracic imaging with chest radiography and CT are key tools for pulmonary disease diagnosis and management, but their role in the management of COVID-19 has not been considered within the multivariable context of the severity of respiratory disease, pretest probability, risk factors for disease progression, and critical resource constraints. To address this deficit, a multidisciplinary panel comprised principally of radiologists and pulmonologists from 10 countries with experience managing patients with COVID-19 across a spectrum of health care environments evaluated the utility of imaging within three scenarios representing varying risk factors, community conditions, and resource constraints. Fourteen key questions, corresponding to 11 decision points within the three scenarios and three additional clinical situations, were rated by the panel based on the anticipated value of the information that thoracic imaging would be expected to provide. The results were aggregated, resulting in five main and three additional recommendations intended to guide medical practitioners in the use of chest radiography and CT in the management of COVID-19.

Best practice for infection prevention in pediatric respiratory clinics during the COVID-19 epidemic.

During the COVID-19 epidemic, it is important for ensuring infection prevention and control in the pediatric respiratory clinics. Herein, we introduced the practice of infection prevention and control in pediatric respiratory clinics in China. Triage measures for patients who visit respiratory clinics, quality control for pediatric respiratory clinics and other preventive measures for related examinations and treatment have been introduced in this review article.

Improving Detection and Response to Respiratory Events - Kenya, April 2016-April 2020.

Respiratory pathogens, such as novel influenza A viruses, Middle East respiratory syndrome coronavirus (MERS-CoV), and now, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), are of particular concern because of their high transmissibility and history of global spread (1). Clusters of severe respiratory disease are challenging to investigate, especially in resource-limited settings, and disease etiology often is not well understood. In 2014, endorsed by the Group of Seven (G7),* the Global Health Security Agenda (GHSA) was established to help build country capacity to prevent, detect, and respond to infectious disease threats.† GHSA is a multinational, multisectoral collaboration to support countries towards full implementation of the World Health Organization's International Health Regulations (IHR).§ Initially, 11 technical areas for collaborator participation were identified to meet GHSA goals. CDC developed the Detection and Response to Respiratory Events (DaRRE) strategy in 2014 to enhance country capacity to identify and control respiratory disease outbreaks. DaRRE initiatives support the four of 11 GHSA technical areas that CDC focuses on: surveillance, laboratory capacity, emergency operations, and workforce development.¶ In 2016, Kenya was selected to pilot DaRRE because of its existing respiratory disease surveillance and laboratory platforms and well-developed Field Epidemiology and Laboratory Training Program (FELTP) (2). During 2016-2020, Kenya's DaRRE partners (CDC, the Kenya Ministry of Health [MoH], and Kenya's county public health officials) conceptualized, planned, and implemented key components of DaRRE. Activities were selected based on existing capacity and determined by the Kenya MoH and included 1) expansion of severe acute respiratory illness (SARI) surveillance sites; 2) piloting of community event-based surveillance; 3) expansion of laboratory diagnostic capacity; 4) training of public health practitioners in detection, investigation, and response to respiratory threats; and 5) improvement of response capacity by the national emergency operations center (EOC). Progress on DaRRE activity implementation was assessed throughout the process. This pilot in Kenya demonstrated that DaRRE can support IHR requirements and can capitalize on a country's existing resources by tailoring tools to improve public health preparedness based on countries' needs.

Respiratory and pulmonary complications in head and neck cancer patients: Evidence-based review for the COVID-19 era.

BACKGROUND: Pulmonary complications and infections frequently affect patients with head and neck squamous cell carcinoma (HNSCC). Common characteristics can predispose these patients to the development of severe respiratory illness, which may be particularly relevant during the 2019 coronavirus disease (COVID-19) pandemic. METHODS: A scoping review was performed to assess the impact of pulmonary comorbidities and adverse respiratory outcomes in HNSCC patients. RESULTS: Advanced age, history of tobacco and alcohol abuse, and cardiopulmonary comorbidities are significant risk factors for the development of adverse respiratory outcomes. Treatment toxicities from radiation or chemoradiation therapy significantly increase these risks. CONCLUSION: Respiratory complications are a frequent cause of morbidity and mortality among HNSCC patients, and the COVID-19 pandemic may disproportionately affect this population. Interventions designed to decrease smoking and alcohol use, improve oral hygiene, and aggressively manage medical comorbidities are important to the long-term management and health of these patients.