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.

Unbearable suffering while working as a nurse during the COVID-19 pandemic: A qualitative descriptive study.

Background: The COVID-19 pandemic resulted in negative consequences for nurse well-being, patient care delivery and outcomes, and organizational outcomes. Objective: The purpose of this study was to explore the experiences of nurses working during the COVID-19 Pandemic in the United States. Design: This study used a qualitative descriptive design. Settings: The setting for this study was a national sample of nurses working during the COVID-19 pandemic in the United States over a period of 18 months. Participants: Convenience and snowball sampling were used to recruit 81 nurses via social media and both national and state listservs. Methods: Using a single question prompt, voicemail and emails were used for nurses to share their experiences anonymously working as a nurse during the COVID-19 pandemic. Voicemails were transcribed and each transcript was analyzed using content analysis with both deductive and inductive coding. Results: The overarching theme identified was Unbearable Suffering. Three additional themes were identified: 1) Facilitators to Nursing Practice During the COVID-19 Pandemic, 2) Barriers to Nursing Practice During the COVID-19 pandemic, with the sub-themes of Barriers Within the Work Environment, Suboptimal Care Delivery, and Negative Consequences for the Nurses; and lastly, 3) the Transitionary Nature of the Pandemic.. Conclusions: The primary finding of this study was that nurses experienced and witnessed unbearable suffering while working during the COVID-19 pandemic that was transitionary in nature. Future research should consider the long-term impacts of this unbearable suffering on nurses. Intervention research should be considered to support nurses who have worked during the COVID-19 pandemic, and mitigate the potential long-term effects. Tweetable abstract: A study on nurses experiences during the pandemic reveals their unbearable suffering. Read here about the reasons nurses are leaving.

A summary of the ComParE COVID-19 challenges.

The COVID-19 pandemic has caused massive humanitarian and economic damage. Teams of scientists from a broad range of disciplines have searched for methods to help governments and communities combat the disease. One avenue from the machine learning field which has been explored is the prospect of a digital mass test which can detect COVID-19 from infected individuals' respiratory sounds. We present a summary of the results from the INTERSPEECH 2021 Computational Paralinguistics Challenges: COVID-19 Cough, (CCS) and COVID-19 Speech, (CSS).

Integrative Wellness Approaches to Mitigate Perceived Stress, Increase Vitality, and Build Community during COVID-19: A Pilot Study.

INTRODUCTION: In January 2020, a small, private school of nursing in a university in the pacific northwest, established the Initiative for Vital Practice (I4VP). The I4VP's primary goal was to create a sustainable pathway for increasing vital practice through increasing resiliency and self-care practices. OBJECTIVES: The ensuing pathway's objectives were to, (1) take previously identified factors related to perceived stress related to workloads, impacts on professional quality of life and psychosocial exposures during the COVID-19 pandemic; and (2) develop and pilot test a wellness intervention (i.e., wellness pods) for faculty and staff to build community and find new ways to enhance well-being through peer support. METHODS: Five focused Wellness Pods were developed on Microsoft Teams platform using the individual channels: (1) stress and mind-body exploration pod; (2) mindfulness in healthcare pod; (3) healing relationship pod; (4) environmental pod; and (5) physical activity pod. Faculty and staff self-selected into a Wellness Pod that interested them. The Wellness Pods met weekly in person over a period of two months. Quantitative and qualitative data was collected via cross-sectional surveys including: four sociodemographic items, one item on current stress level, one write-in item on current stress management at work, two write-in items focused on the cognitive reasoning for participation, the 7-item subjective vitality scale focused individual difference, the 7-item subjective vitality scale focused on the state level, the 10-item perceived stress scale, and one item ranking which wellness pod the individual wanted to participate in. There was one trained facilitator for the overall Wellness Pods operations and communication. RESULTS: The average score on the perceived stress scale was 22.3 (SD = 3.5), indicating moderate levels of perceived stress. The average score on the individual difference vitality score was 26.5 (SD = 7.6), whereas the state level vitality score was 21.4 (SD = 9.98), indicating moderate levels of subjective vitality. Two categories: stress management and wellness pods, were identified through content analysis. CONCLUSIONS: Through pilot testing, this project demonstrated feasibility for future wellness pods interventions for faculty and staff at schools of nursing. Future research is needed to evaluate the effectiveness of the wellness pods intervention.

New Advances on Wellness Therapies Using Integrated Health Focusing on Nature.

The purpose of this Special Issue is to provide you, the reader, with an overview of new advancements in wellness therapies using integrative health focusing on nature [...].

Exploring Longitudinal Cough, Breath, and Voice Data for COVID-19 Progression Prediction via Sequential Deep Learning: Model Development and Validation.

BACKGROUND: Recent work has shown the potential of using audio data (eg, cough, breathing, and voice) in the screening for COVID-19. However, these approaches only focus on one-off detection and detect the infection, given the current audio sample, but do not monitor disease progression in COVID-19. Limited exploration has been put forward to continuously monitor COVID-19 progression, especially recovery, through longitudinal audio data. Tracking disease progression characteristics and patterns of recovery could bring insights and lead to more timely treatment or treatment adjustment, as well as better resource management in health care systems. OBJECTIVE: The primary objective of this study is to explore the potential of longitudinal audio samples over time for COVID-19 progression prediction and, especially, recovery trend prediction using sequential deep learning techniques. METHODS: Crowdsourced respiratory audio data, including breathing, cough, and voice samples, from 212 individuals over 5-385 days were analyzed, alongside their self-reported COVID-19 test results. We developed and validated a deep learning-enabled tracking tool using gated recurrent units (GRUs) to detect COVID-19 progression by exploring the audio dynamics of the individuals' historical audio biomarkers. The investigation comprised 2 parts: (1) COVID-19 detection in terms of positive and negative (healthy) tests using sequential audio signals, which was primarily assessed in terms of the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with 95% CIs, and (2) longitudinal disease progression prediction over time in terms of probability of positive tests, which was evaluated using the correlation between the predicted probability trajectory and self-reported labels. RESULTS: We first explored the benefits of capturing longitudinal dynamics of audio biomarkers for COVID-19 detection. The strong performance, yielding an AUROC of 0.79, a sensitivity of 0.75, and a specificity of 0.71 supported the effectiveness of the approach compared to methods that do not leverage longitudinal dynamics. We further examined the predicted disease progression trajectory, which displayed high consistency with longitudinal test results with a correlation of 0.75 in the test cohort and 0.86 in a subset of the test cohort with 12 (57.1%) of 21 COVID-19-positive participants who reported disease recovery. Our findings suggest that monitoring COVID-19 evolution via longitudinal audio data has potential in the tracking of individuals' disease progression and recovery. CONCLUSIONS: An audio-based COVID-19 progression monitoring system was developed using deep learning techniques, with strong performance showing high consistency between the predicted trajectory and the test results over time, especially for recovery trend predictions. This has good potential in the postpeak and postpandemic era that can help guide medical treatment and optimize hospital resource allocations. The changes in longitudinal audio samples, referred to as audio dynamics, are associated with COVID-19 progression; thus, modeling the audio dynamics can potentially capture the underlying disease progression process and further aid COVID-19 progression prediction. This framework provides a flexible, affordable, and timely tool for COVID-19 tracking, and more importantly, it also provides a proof of concept of how telemonitoring could be applicable to respiratory diseases monitoring, in general.

Sounds of COVID-19: exploring realistic performance of audio-based digital testing.

To identify Coronavirus disease (COVID-19) cases efficiently, affordably, and at scale, recent work has shown how audio (including cough, breathing and voice) based approaches can be used for testing. However, there is a lack of exploration of how biases and methodological decisions impact these tools' performance in practice. In this paper, we explore the realistic performance of audio-based digital testing of COVID-19. To investigate this, we collected a large crowdsourced respiratory audio dataset through a mobile app, alongside symptoms and COVID-19 test results. Within the collected dataset, we selected 5240 samples from 2478 English-speaking participants and split them into participant-independent sets for model development and validation. In addition to controlling the language, we also balanced demographics for model training to avoid potential acoustic bias. We used these audio samples to construct an audio-based COVID-19 prediction model. The unbiased model took features extracted from breathing, coughs and voice signals as predictors and yielded an AUC-ROC of 0.71 (95% CI: 0.65-0.77). We further explored several scenarios with different types of unbalanced data distributions to demonstrate how biases and participant splits affect the performance. With these different, but less appropriate, evaluation strategies, the performance could be overestimated, reaching an AUC up to 0.90 (95% CI: 0.85-0.95) in some circumstances. We found that an unrealistic experimental setting can result in misleading, sometimes over-optimistic, performance. Instead, we reported complete and reliable results on crowd-sourced data, which would allow medical professionals and policy makers to accurately assess the value of this technology and facilitate its deployment.

Reducing Inequities During the COVID-19 Pandemic: A Rapid Review and Synthesis of Public Health Recommendations.

Objectives: Efforts to contain the COVID-19 pandemic should take into account worsening health inequities. While many public health experts have commented on inequities, no analysis has yet synthesized recommendations into a guideline for practitioners. The objective of this rapid review was to identify the areas of greatest concern and synthesize recommendations. Methods: We conducted a rapid systematic review (PROSPERO: CRD42020178131). We searched Ovid MEDLINE, Embase, PsycINFO, CINAHL and Cochrane Central Register of Controlled Trials databases from December 1, 2019 to April 27, 2020. We included English language peer-reviewed commentaries, editorials, and opinion pieces that addressed the social determinants of health in the context of COVID-19. Results: 338 articles met our criteria. Authors represented 81 countries. Income, housing, mental health, age and occupation were the most discussed social determinants of health. We categorized recommendations into primordial, primary, secondary and tertiary prevention that spoke to the social determinants of COVID-19 and equity. Conclusion: These recommendations can assist efforts to contain COVID-19 and reduce health inequities during the pandemic. Using these recommendations, public health practitioners could support a more equitable pandemic response. Systematic Review Registration: PROSPERO, CRD42020178131.

Randomised controlled trial of a just-in-time adaptive intervention (JITAI) smoking cessation smartphone app: the Quit Sense feasibility trial protocol.

INTRODUCTION: A lapse (any smoking) early in a smoking cessation attempt is strongly associated with reduced success. A substantial proportion of lapses are due to urges to smoke triggered by situational cues. Currently, no available interventions proactively respond to such cues in real time. Quit Sense is a theory-guided just-in-time adaptive intervention smartphone app that uses a learning tool and smartphone sensing to provide in-the-moment tailored support to help smokers manage cue-induced urges to smoke. The primary aim of this randomised controlled trial (RCT) is to assess the feasibility of delivering a definitive online efficacy trial of Quit Sense. METHODS AND ANALYSES: A two-arm parallel-group RCT allocating smokers willing to make a quit attempt, recruited via online adverts, to usual care (referral to the NHS SmokeFree website) or usual care plus Quit Sense. Randomisation will be stratified by smoking rate (<16 vs ≥16 cigarettes/day) and socioeconomic status (low vs high). Recruitment, enrolment, baseline data collection, allocation and intervention delivery will be automated through the study website. Outcomes will be collected at 6 weeks and 6 months follow-up via the study website or telephone, and during app usage. The study aims to recruit 200 smokers to estimate key feasibility outcomes, the preliminary impact of Quit Sense and potential cost-effectiveness, in addition to gaining insights on user views of the app through qualitative interviews. ETHICS AND DISSEMINATION: Ethics approval has been granted by the Wales NHS Research Ethics Committee 7 (19/WA/0361). The findings will be disseminated to the public, the funders, relevant practice and policy representatives and other researchers. TRIAL REGISTRATION NUMBER: ISRCTN12326962.

Social determinants of COVID-19 incidence and outcomes: A rapid review.

Early reports indicate that the social determinants of health are implicated in COVID-19 incidence and outcomes. To inform the ongoing response to the pandemic, we conducted a rapid review of peer-reviewed studies to examine the social determinants of COVID-19. We searched Ovid MEDLINE, Embase, PsycINFO, CINAHL and Cochrane Central Register of Controlled Trials from December 1, 2019 to April 27, 2020. We also searched the bibliographies of included studies, COVID-19 evidence repositories and living evidence maps, and consulted with expert colleagues internationally. We included studies identified through these supplementary sources up to June 25, 2020. We included English-language peer-reviewed quantitative studies that used primary data to describe the social determinants of COVID-19 incidence, clinical presentation, health service use and outcomes in adults with a confirmed or presumptive diagnosis of COVID-19. Two reviewers extracted data and conducted quality assessment, confirmed by a third reviewer. Forty-two studies met inclusion criteria. The strongest evidence was from three large observational studies that found associations between race or ethnicity and socioeconomic deprivation and increased likelihood of COVID-19 incidence and subsequent hospitalization. Limited evidence was available on other key determinants, including occupation, educational attainment, housing status and food security. Assessing associations between sociodemographic factors and COVID-19 was limited by small samples, descriptive study designs, and the timeframe of our search. Systematic reviews of literature published subsequently are required to fully understand the magnitude of any effects and predictive utility of sociodemographic factors related to COVID-19 incidence and outcomes. PROSPERO: CRD4202017813.