Real-time tracking of self-reported symptoms to predict potential COVID-19

@article{Menni2020RealtimeTO,
  title={Real-time tracking of self-reported symptoms to predict potential COVID-19},
  author={Cristina Menni and Ana M. Valdes and Maxim B. Freidin and Carole H. Sudre and Long H. Nguyen and David A. Drew and Sajaysurya Ganesh and Thomas Varsavsky and Manuel Jorge Cardoso and Julia Sarah El-sayed Moustafa and Alessia Visconti and Pirro G. Hysi and Ruth C. E. Bowyer and Massimo Mangino and Mario Falchi and Jonathan Wolf and S{\'e}bastien Ourselin and Andrew T. Chan and Claire J. Steves and Tim D. Spector},
  journal={Nature Medicine},
  year={2020},
  volume={26},
  pages={1037-1040}
}
A total of 2,618,862 participants reported their potential symptoms of COVID-19 on a smartphone-based app. Among the 18,401 who had undergone a SARS-CoV-2 test, the proportion of participants who reported loss of smell and taste was higher in those with a positive test result (4,668 of 7,178 individuals; 65.03%) than in those with a negative test result (2,436 of 11,223 participants; 21.71%) (odds ratio = 6.74; 95% confidence interval = 6.31–7.21). A model combining symptoms to predict probable… 

Passive Monitoring of Physiological Data and Self-reported Symptoms to Detect Clusters of People with COVID-19

An app that collects smartwatch and activity tracker data, as well as self-reported symptoms and diagnostic testing results from participants living in the US, found that a combination of symptom and sensor data resulted in an AUC=0.80 which was significantly better than a model which just considered symptoms alone.

Wearable sensor data and self-reported symptoms for COVID-19 detection

A smartphone app that combines smartwatch and activity tracker data together with self-reported symptoms allows continuous monitoring of SARS-CoV-2 infection and finds that a combination of symptom and sensor data resulted in an area under the curve (AUC) of 0.80, which is significantly better than a model 1 that considers symptoms alone.

App-Based Tracking of Self-Reported COVID-19 Symptoms: Analysis of Questionnaire Data (Preprint)

Self-reported symptom tracking helps to identify novel symptoms of COVID-19 and to estimate the predictive value of certain symptoms, which aids in the development of reliable screening tools.

Measuring COVID-19 and Influenza in the Real World via Person-Generated Health Data

PGHD can be a valid source of longitudinal real world data to detect and monitor COVID-19-related symptoms and behaviors at population scale and may provide continuous, near realtime feedback to intervention effectiveness that otherwise requires waiting for symptoms to develop into contacts with the healthcare system.

COVID RADAR app: Description and validation of population surveillance of symptoms and behavior in relation to COVID-19

The COVID Radar may be a valid instrument for future surveillance and potential predictive analytics to identify emerging hotspots because symptoms and risk behavior increase prior to a positive SARS-CoV-2 test, and user-reported case counts match closely with nationally- reported case counts in regions with high user engagement.

Smartwatch data help detect COVID-19.

Smartwatch data can be used in conjunction with self-reported symptoms to determine whether an individual has COVID-19 after the onset of symptoms, and suggests that devices can one day accurately warn us of a potential infection before the authors get sick.

Self-reported symptoms as predictors of SARS-CoV-2 infection in the general population living in the Amsterdam region, the Netherlands

Cough, fever, loss of smell or taste, and muscle ache appear to be most strongly associated with a positive SARS-CoV-2 test in symptomatic people of the general population who were tested.

Assessment of physiological signs associated with COVID-19 measured using wearable devices

Measuringpiration rate and heart rate are typically elevated by illness, while HRV is decreased, and taken in conjunction with molecular-based diagnostics may lead to better early detection and monitoring of COVID-19.

Passive detection of COVID-19 with wearable sensors and explainable machine learning algorithms

An explainable gradient boosting prediction model based on decision trees for the detection of COVID-19 infection that can adapt to the absence of self-reported symptoms and to the available sensor data is proposed that can explain the importance of each feature and the post-test-behavior for the individuals.
...

References

SHOWING 1-10 OF 13 REFERENCES

Rapid implementation of mobile technology for real-time epidemiology of COVID-19

The COVID Symptom Study recruited about 2 million users and found the prevalence of combinations of symptoms (three or more), including fatigue and cough, followed by diarrhea, fever, and/or anosmia, was predictive of a positive test verification for SARS-CoV-2.

Consequences of undetected olfactory loss for human chemosensory communication and well-being

The limited-to-no olfactory perception in the fraction of subjects who neither complain about it nor seek help in ENT clinics does not seem to have a major effect on their social, cognitive, emotional and health functioning.

Sudden and Complete Olfactory Loss Function as a Possible Symptom of COVID-19.

A case where the main symptom expressed by the patient infected by SARS-CoV-2 was the sudden and complete loss of the olfactory function without nasal obstruction is presented.

A framework for identifying regional outbreak and spread of COVID-19 from one-minute population-wide surveys

It is proposed that daily population-wide surveys that assess the development of symptoms caused by the virus could serve as a strategic and valuable tool for identifying such clusters to inform epidemiologists, public health officials, and policy makers.

Isolated sudden onset anosmia in COVID-19 infection. A novel syndrome?

There is an important fourth presenting syndrome, namely isolated sudden onset anosmia (ISOA), which should be considered highly suspicious for SARS-CoV-2, and the international community is urged to consider this presentation in current management advice.

Computationally efficient confidence intervals for cross-validated area under the ROC curve estimates.

An alternative to the bootstrap is demonstrated, a computationally efficient influence curve based approach to obtaining a variance estimate for cross-validated AUC.

SARS-CoV-2 entry factors are highly expressed in nasal epithelial cells together with innate immune genes

An analysis of single-cell transcriptomics datasets from different tissues shows that ACE2 and TMPRSS2 are co-expressed in respiratory, corneal and intestinal epithelial cell populations, and that respiratory expression of ACE2 is associated with genes involved in innate immunity.

Non-neuronal expression of SARS-CoV-2 entry genes in the olfactory system suggests mechanisms underlying COVID-19-associated anosmia

It is suggested that CoV-2 infection of non-neuronal cell types leads to anosmia and related disturbances in odor perception in COVID-19 patients.

Sixty seconds on . . . anosmia

While a high temperature and a new, continuous cough are the most established symptoms of covid-19, the World Health Organization is now examining how common it might be for infected people to

Alterations in Smell or Taste in Mildly Symptomatic Outpatients With SARS-CoV-2 Infection.

This study reports on the prevalence, intensity, and timing of an altered sense of smell or taste in patients with SARS-CoV-2 infections.