The hopes and hazards of using personal health technologies in the diagnosis and prognosis of infections

Radin, Jennifer M; Quer, Giorgio; Jalili, Marwa; Hamideh, Dina; Steinhubl, Steven R.

doi:10.1016/s2589-7500(21)00064-9

Cited by 28 publications

(20 citation statements)

References 52 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results build on our prior retrospective work on resting heart rate 5 and sleep 6 , which when aggregated at the population level, have been shown to significantly improve real-time predictions for influenza-like illness 15 . In an early study, using the initial data from DETECT, we demonstrated the potential of using self-reported symptoms and wearable data for the discrimination of positive and negative cases of COVID-19 7 , which has been validated by several subsequent independent studies evaluating detection of COVID-19 from wearable devices 16 . The availability of high-frequency intra-day data has shown promise to identify pre-symptomatic infection 8 , even if additional studies with a larger number of individuals are needed to prove this point.…”

Section: Discussionmentioning

confidence: 87%

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

Individual smartwatch or fitness band sensor data in the setting of COVID-19 has shown promise to identify symptomatic and pre-symptomatic infection or the need for hospitalization, correlations between peripheral temperature and self-reported fever, and an association between changes in heart-rate-variability and infection. In our study, a total of 38,911 individuals (61% female, 15% over 65) have been enrolled between March 25, 2020 and April 3, 2021, with 1118 reported testing positive and 7032 negative for COVID-19 by nasopharyngeal PCR swab test. We propose 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, and that can explain the importance of each feature and the post-test-behavior for the individuals. We tested it in a cohort of symptomatic individuals who exhibited an AUC of 0.83 [0.81–0.85], or AUC = 0.78 [0.75–0.80] when considering only data before the test date, outperforming state-of-the-art algorithm in these conditions. The analysis of all individuals (including asymptomatic and pre-symptomatic) when self-reported symptoms were excluded provided an AUC of 0.78 [0.76–0.79], or AUC of 0.70 [0.69–0.72] when considering only data before the test date. Extending the use of predictive algorithms for detection of COVID-19 infection based only on passively monitored data from any device, we showed that it is possible to scale up this platform and apply the algorithm in other settings where self-reported symptoms can not be collected.

show abstract

Section: Discussionmentioning

confidence: 87%

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

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…48 However, some developed countries utilise non-wearable passive multiparametric sensors embedded in under-mattress pads to monitor heart rate, respiratory rate and other sleep parameters useful to identify early physiological decompensation. 103 Such technology might not be feasible in developing countries due to cost implications.…”

Section: Results Analysis and Discussionmentioning

confidence: 99%

Virtual healthcare services and digital health technologies deployed during coronavirus disease 2019 (COVID-19) pandemic in South Africa: a systematic review

Mbunge

Batani

Gaobotse

et al. 2022

Global Health Journal

107

View full text Add to dashboard Cite

“…Future work should aim to reproduce and validate the results obtained in this study, ideally with data that is collected in a similar fashion such as through the DE-TECT [65] or Evidation [66] systems in the US as well as TemPredict which covers a broad range of international users [67,68]. We further propose to investigate and improve the representativeness of the user sample, i.e., by comparison with common health survey programs, such as GEDA in Germany [69] or NHIS in the US [70].…”

Section: Discussionmentioning

confidence: 95%

“…Such data would allow for the quantification of more subtle changes in physiology, such as the postural orthostatic tachycardia syndrome (POTS) [71], another typical condition associated with Long COVID [72,73]. After all, it is a unique advantage of wearable sensors that data can be measured over extended periods at high resolution and minimal burden to the individual, thereby making them a promising tool to complement traditional clinical methods for a datadriven approach to public health research [56,57,65].…”

Section: Discussionmentioning

confidence: 99%

Evidence for positive long- and short-term effects of vaccinations against COVID-19 in wearable sensor metrics -- Insights from the German Corona Data Donation Project

Wiedermann¹,

Rose²,

Maïer³

et al. 2022

Preprint

View full text Add to dashboard Cite

Vaccines are among the most powerful tools used to combat the COVID-19 pandemic. They are highly effective against infection and substantially reduce the risk of severe disease, hospitalization, ICU admission, and death. However, their potential for attenuating long-term effects of a SARS-CoV-2 infection, commonly denoted as Long COVID, remains elusive and is still subject of debate. Such long-term effects can be effectively monitored at the individual level by analyzing physiological data collected by consumer-grade wearable sensors. Here, we investigate changes in resting heart rate, daily physical activity, and sleep duration in response to a SARS-CoV-2 infection stratified by vaccination status. Data was collected over a period of two years in the context of the German Corona Data Donation Project with currently around 190,000 monthly active donors. Compared to their unvaccinated counterparts, we find that vaccinated individuals on average experience smaller changes in their vital data that also return to normal levels more quickly. Likewise, extreme changes in vitals during the acute phase of the disease occur less frequently in vaccinated individuals. Our results solidify evidence that vaccines can mitigate long-term detrimental effects of SARS-CoV-2 infections both in terms of duration and magnitude. Furthermore, they demonstrate the value of large scale, high-resolution wearable sensor data in public health research.

show abstract

The hopes and hazards of using personal health technologies in the diagnosis and prognosis of infections

Cited by 28 publications

References 52 publications

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

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

Virtual healthcare services and digital health technologies deployed during coronavirus disease 2019 (COVID-19) pandemic in South Africa: a systematic review

Evidence for positive long- and short-term effects of vaccinations against COVID-19 in wearable sensor metrics -- Insights from the German Corona Data Donation Project

Contact Info

Product

Resources

About