ABSTRACT
OBJECTIVES: We investigated machinelearningbased identification of presymptomatic COVID-19 and detection of infection-related changes in physiology using a wearable device. DESIGN: Interim analysis of a prospective cohort study. SETTING, PARTICIPANTS AND INTERVENTIONS: Participants from a national cohort study in Liechtenstein were included. Nightly they wore the Ava-bracelet that measured respiratory rate (RR), heart rate (HR), HR variability (HRV), wrist-skin temperature (WST) and skin perfusion. SARS-CoV-2 infection was diagnosed by molecular and/or serological assays. RESULTS: A total of 1.5 million hours of physiological data were recorded from 1163 participants (mean age 44±5.5 years). COVID-19 was confirmed in 127 participants of which, 66 (52%) had worn their device from baseline to symptom onset (SO) and were included in this analysis. Multi-level modelling revealed significant changes in five (RR, HR, HRV, HRV ratio and WST) device-measured physiological parameters during the incubation, presymptomatic, symptomatic and recovery periods of COVID-19 compared with baseline. The training set represented an 8-day long instance extracted from day 10 to day 2 before SO. The training set consisted of 40 days measurements from 66 participants. Based on a random split, the test set included 30% of participants and 70% were selected for the training set. The developed long short-term memory (LSTM) based recurrent neural network (RNN) algorithm had a recall (sensitivity) of 0.73 in the training set and 0.68 in the testing set when detecting COVID-19 up to 2 days prior to SO. CONCLUSION: Wearable sensor technology can enable COVID-19 detection during the presymptomatic period. Our proposed RNN algorithm identified 68% of COVID-19 positive participants 2 days prior to SO and will be further trained and validated in a randomised, single-blinded, two-period, two-sequence crossover trial. Trial registration number ISRCTN51255782; Pre-results.
Subject(s)
COVID-19 , Adult , COVID-19/diagnosis , Cohort Studies , Humans , Middle Aged , Prospective Studies , SARS-CoV-2ABSTRACT
Although SARS-CoV-2 antibody assays have been found to provide valid results in EDTA-anticoagulated whole blood, so far, they have not demonstrated that antibody levels in whole blood originating from capillary blood samples are comparable to antibody levels measured in blood from a venous origin. Here, blood is drawn simultaneously by capillary and venous blood sampling. Antibody titers are determined by an assay employing electrochemiluminescence (ECLIA) and SARS-CoV-2 total immunoglobulins are detected with specificity directed against the nucleocapsid antigen. Six individuals with confirmed COVID-19 and six individuals without COVID-19 are analyzed. Antibody titers in capillary venous whole blood did not show significant differences, and when corrected for hematocrit, they did not differ from the results obtained from serum. In conclusion, capillary sampled EDTA-anticoagulated whole blood seems to be an attractive alternative matrix for the evaluation of SARS-CoV-2 antibodies when employing ECLIA for detecting total antibodies directed against nucleocapsid antibodies.
ABSTRACT
While lateral flow test formats can be utilized with whole blood and low sample volumes, their diagnostic characteristics are inferior to immunoassays based on chemiluminescence immunoassay (CLIA) or enzyme-linked immunosorbent assay (ELISA) technology. CLIAs and ELISAs can be automated to a high degree but commonly require larger serum or plasma volumes for sample processing. We addressed the suitability of EDTA-anticoagulated whole blood as an alternative sample material for antibody testing against SARS-CoV-2 by electro-CLIA (ECLIA; Roche, Rotkreuz, Switzerland) and ELISA (IgG and IgA; Euroimmun, Germany). Simultaneously drawn venous serum and EDTA-anticoagulated whole blood samples from 223 individuals were included. Correction of the whole blood results for hematocrit led to a good agreement with the serum results for weakly to moderately positive antibody signals. In receiver-operating characteristic curve analysis, all three assays displayed comparable diagnostic accuracy (area under the curve (AUC)) using corrected whole blood and serum (AUCs: 0.97 for ECLIA and IgG ELISA; 0.84 for IgA ELISA). In conclusion, our results suggest that the investigated assays can reliably detect antibodies against SARS-CoV-2 in hemolyzed whole blood anticoagulated with EDTA. Correction of these results for hematocrit is suggested. This study demonstrates that the automated processing of whole blood for identification of SARS-CoV-2 antibodies with common ECLIA and ELISA methods is accurate and feasible.