MétaCan
Menu
Back to cohort
Record W3200996625 · doi:10.2196/30819

Early Detection of Symptom Exacerbation in Patients With SARS-CoV-2 Infection Using the Fitbit Charge 3 (DEXTERITY): Pilot Evaluation

2021· article· en· W3200996625 on OpenAlexvenueno aff
Kan Yamagami, Akihiro Nomura, Mitsuhiro Kometani, Masaya Shimojima, Kenji Sakata, Soichiro Usui, Kenji Furukawa, Masayuki Takamura, Masaki Okajima, Kazuyoshi Watanabe, Takashi Yoneda

Bibliographic record

VenueJMIR Formative Research · 2021
Typearticle
Languageen
FieldMedicine
TopicLong-Term Effects of COVID-19
Canadian institutionsnot available
FundersKanazawa University
KeywordsAsymptomaticExacerbationMedicineOxygen saturationHeart rateHypoxia (environmental)Coronavirus disease 2019 (COVID-19)Stage (stratigraphy)Respiratory rateInternal medicineBlood pressureDiseaseInfectious disease (medical specialty)Biology

Abstract

fetched live from OpenAlex

Background Some patients with COVID-19 experienced sudden death due to rapid symptom deterioration. Thus, it is important to predict COVID-19 symptom exacerbation at an early stage prior to increasing severity in patients. Patients with COVID-19 could experience a unique “silent hypoxia” at an early stage of the infection when they are apparently asymptomatic, but with rather low SpO2 (oxygen saturation) levels. In order to continuously monitor SpO2 in daily life, a high-performance wearable device, such as the Apple Watch or Fitbit, has become commercially available to monitor several biometric data including steps, resting heart rate (RHR), physical activity, sleep quality, and estimated oxygen variation (EOV). Objective This study aimed to test whether EOV measured by the wearable device Fitbit can predict COVID-19 symptom exacerbation. Methods We recruited patients with COVID-19 from August to November 2020. Patients were asked to wear the Fitbit for 30 days, and biometric data including EOV and RHR were extracted. EOV is a relative physiological measure that reflects users’ SpO2 levels during sleep. We defined a high EOV signal as a patient’s oxygen level exhibiting a significant dip and recovery within the index period, and a high RHR signal as daily RHR exceeding 5 beats per day compared with the minimum RHR of each patient in the study period. We defined successful prediction as the appearance of those signals within 2 days before the onset of the primary outcome. The primary outcome was the composite of deaths of all causes, use of extracorporeal membrane oxygenation, use of mechanical ventilation, oxygenation, and exacerbation of COVID-19 symptoms, irrespective of readmission. We also assessed each outcome individually as secondary outcomes. We made weekly phone calls to discharged patients to check on their symptoms. Results We enrolled 23 patients with COVID-19 diagnosed by a positive SARS-CoV-2 polymerase chain reaction test. The patients had a mean age of 50.9 (SD 20) years, and 70% (n=16) were female. Each patient wore the Fitbit for 30 days. COVID-19 symptom exacerbation occurred in 6 (26%) patients. We were successful in predicting exacerbation using EOV signals in 4 out of 5 cases (sensitivity=80%, specificity=90%), whereas the sensitivity and specificity of high RHR signals were 50% and 80%, respectively, both lower than those of high EOV signals. Coincidental obstructive sleep apnea syndrome confirmed by polysomnography was detected in 1 patient via consistently high EOV signals. Conclusions This pilot study successfully detected early COVID-19 symptom exacerbation by measuring EOV, which may help to identify the early signs of COVID-19 exacerbation. Trial Registration University Hospital Medical Information Network Clinical Trials Registry UMIN000041421; https://upload.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000047290

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.297
Threshold uncertainty score0.396

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.075
GPT teacher head0.418
Teacher spread0.344 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations15
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative ResearchSame topicLong-Term Effects of COVID-19French-language works237,207