Search

ObjectivesWe investigated machinelearningbased identification of presymptomatic COVID-19 and detection of infection-related changes in physiology using a wearable device.DesignInterim analysis of a prospective cohort study.Setting, participants and interventionsParticipants 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.ResultsA 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.ConclusionWearable 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 numberISRCTN51255782; Pre-results.

Background: We investigated machine learning based identification of the pre-symptomatic coronavirus disease 2019 (COVID-19) and detection of infection-related changes in physiology using a wearable device (the Ava bracelet). Methods: Participants from an ongoing cohort study (GAPP) of the general population in Liechtenstein were included in the current sub-study (COVI-GAPP). Nightly they wore the fertility bracelet that measured every ten seconds skin temperature, heart rate, respiratory rate, skin perfusion, and heart rate variability. Participants reported daily symptoms in a complementary app. Laboratory reverse transcription polymerase chain reaction (RT-PCR) and/or COVID-19 serology samples were collected from all participants. Long short-term memory (LSTM) based recurrent neural networks (RNN) were chosen for the binary classification of an individual as healthy or infected on a given day in a derivation and validation procedure. Findings: A total of 1ž5 million hours of physiological data were recorded from 1163 participants (mean age 44 +/- 5ž5 years). COVID-19 was confirmed in 127 participants. Of these, 66 (52%) had worn their device from baseline to symptom onset and were included in the analysis and RNN. Multi-level modelling revealed significantly different values in pre- versus post-symptomatic respiratory rate, temperature, heart rate, heart rate variability ratio, and skin perfusion. The developed RNN algorithm had a recall of 0ž73 in the training set and 0ž68 in the testing set (overall recall of 0ž71) when detecting COVID-19 up to two days prior to symptom onset. Interpretation: Our proposed RNN algorithm identified 71% of COVID-19 positive participants two days prior to symptom onset. Wearable sensor technology can therefore enable COVID-19’ detection during the pre-symptomatic period. Funding: IMI grant agreement number 101005177, the Princely House of the Principality of Liechtenstein, the government of the Principality of Liechtenstein, and the Hanela Foundation in Switzerland. Declaration of Interest: Lorenz Risch, and Martin Risch are key shareholders of the Dr Risch Medical Laboratory. David Conen has received consulting fees from Roche Diagnostics, outside of the current work. The other authors have no financial or personal conflicts of interest to declare. Ethical Approval: The local ethics committee approved the study protocol, and written informed consent was obtained from each participant (BASEC 2020-00786).

Specialized brain structures encode spatial locations and movements, yet there is growing evidence that this information is also represented in the rodent medial prefrontal cortex (mPFC). Disambiguating such information from the encoding of other types of task-relevant information has proven challenging. To determine the extent to which movement and location information is relevant to mPFC neurons, tetrodes were used to record neuronal activity while limb positions, poses (i.e., recurring constellations of limb positions), velocity, and spatial locations were simultaneously recorded with two cameras every 200 ms as rats freely roamed in an experimental enclosure. Regression analyses using generalized linear models revealed that more than half of the individual mPFC neurons were significantly responsive to at least one of the factors, and many were responsive to more than one. On the other hand, each factor accounted for only a very small portion of the total spike count variance of any given neuron (