ABSTRACT
Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.
Subject(s)
Body Temperature , COVID-19/diagnosis , Wearable Electronic Devices , Adolescent , Adult , Aged , Aged, 80 and over , Algorithms , COVID-19/virology , Female , Humans , Male , Middle Aged , SARS-CoV-2/isolation & purification , Young AdultABSTRACT
Demographic and socioeconomic factors can contribute to community spread of COVID-19. The aim of this study is to describe the demographics and socioeconomic factors in relation to geolocation of COVID-19 patients who were discharged from the emergency department (ED) back into the community. This retrospective study was conducted over a 7-week period, at an urban, adult, level 1 trauma center in New York City. Demographics, socioeconomic factors, and geolocation of COVID-19 patients discharged from the ED were extracted from the electronic medical records. Patients were stratified by gender for data analysis. A total of 634 patients were included in the study, 376 (59.3%) were male and 205 (32.3%) were Hispanic White. The median age of patients was 50 years (IQR: 38, 60, Min:15, Max:96). The unemployment rate in our population was 41.2% and 75.5% reported contracting the virus via community spread. ED mortality rate was 11.8%; the majority of which were male (N = 50, 66.7%) and the median age was 70 years (IQR: 59, 82). There were 9.4% (95% CI 2.9-12.4) more Black males and 5.4% (95% CI 0.4-10.4) more males who had no insurance coverage compared to females. 26.8% (95% CI 14.5-39) more females worked in the healthcare field and 7.1% (95% CI 0.3-13.9) more were infected via primary contact compared to males. COVID-19 disproportionately affected minorities and males. Socioeconomic factors should be taken into consideration when preparing strategies for preventing the spread of the virus, especially for individuals who are expected to self-isolate.