A Scalable Risk-Scoring System Based on Consumer-Grade Wearables for Inpatients With COVID-19: Statistical Analysis and Model Development

Overview

Journal JMIR Form Res

Publisher JMIR Publications

Specialty Biomedical Engineering

Date 2022 May 25

PMID 35613417

Authors

Simon Foll

Adrian Lison

Martin Maritsch

Karsten Klingberg

Vera Lehmann

Thomas Zuger

David Srivastava

Sabrina Jegerlehner

Stefan Feuerriegel

Elgar Fleisch

Aristomenis Exadaktylos

Felix Wortmann

Affiliations

Soon will be listed here.

Abstract

Background: To provide effective care for inpatients with COVID-19, clinical practitioners need systems that monitor patient health and subsequently allow for risk scoring. Existing approaches for risk scoring in patients with COVID-19 focus primarily on intensive care units (ICUs) with specialized medical measurement devices but not on hospital general wards.

Objective: In this paper, we aim to develop a risk score for inpatients with COVID-19 in general wards based on consumer-grade wearables (smartwatches).

Methods: Patients wore consumer-grade wearables to record physiological measurements, such as the heart rate (HR), heart rate variability (HRV), and respiration frequency (RF). Based on Bayesian survival analysis, we validated the association between these measurements and patient outcomes (ie, discharge or ICU admission). To build our risk score, we generated a low-dimensional representation of the physiological features. Subsequently, a pooled ordinal regression with time-dependent covariates inferred the probability of either hospital discharge or ICU admission. We evaluated the predictive performance of our developed system for risk scoring in a single-center, prospective study based on 40 inpatients with COVID-19 in a general ward of a tertiary referral center in Switzerland.

Results: First, Bayesian survival analysis showed that physiological measurements from consumer-grade wearables are significantly associated with patient outcomes (ie, discharge or ICU admission). Second, our risk score achieved a time-dependent area under the receiver operating characteristic curve (AUROC) of 0.73-0.90 based on leave-one-subject-out cross-validation.

Conclusions: Our results demonstrate the effectiveness of consumer-grade wearables for risk scoring in inpatients with COVID-19. Due to their low cost and ease of use, consumer-grade wearables could enable a scalable monitoring system.

Trial Registration: Clinicaltrials.gov NCT04357834; https://www.clinicaltrials.gov/ct2/show/NCT04357834.

Citing Articles

The Value of Smartwatches in the Health Care Sector for Monitoring, Nudging, and Predicting: Viewpoint on 25 Years of Research.

Kohler C, Bartschke A, Furstenau D, Schaaf T, Salgado-Baez E J Med Internet Res. 2024; 26:e58936.

PMID: 39356287 PMC: 11549588. DOI: 10.2196/58936.

Wearable Devices to Diagnose and Monitor the Progression of COVID-19 Through Heart Rate Variability Measurement: Systematic Review and Meta-Analysis.

Sanches C, Silva G, Librantz A, Sampaio L, Belan P J Med Internet Res. 2023; 25:e47112.

PMID: 37820372 PMC: 10685286. DOI: 10.2196/47112.

The Impact of SARS-CoV-2 Infection on Heart Rate Variability: A Systematic Review of Observational Studies with Control Groups.

Kwon C Int J Environ Res Public Health. 2023; 20(2).

PMID: 36673664 PMC: 9859268. DOI: 10.3390/ijerph20020909.

References

Bent B, Cho P, Henriquez M, Wittmann A, Thacker C, Feinglos M . Engineering digital biomarkers of interstitial glucose from noninvasive smartwatches. NPJ Digit Med. 2021; 4(1):89. PMC: 8172541. DOI: 10.1038/s41746-021-00465-w. View

Austin P, Lee D, Fine J . Introduction to the Analysis of Survival Data in the Presence of Competing Risks. Circulation. 2016; 133(6):601-9. PMC: 4741409. DOI: 10.1161/CIRCULATIONAHA.115.017719. View

Hasty F, Garcia G, Davila H, Wittels S, Hendricks S, Chong S . Heart Rate Variability as a Possible Predictive Marker for Acute Inflammatory Response in COVID-19 Patients. Mil Med. 2020; 186(1-2):e34-e38. PMC: 7717314. DOI: 10.1093/milmed/usaa405. View

Saha P, Heagerty P . Time-dependent predictive accuracy in the presence of competing risks. Biometrics. 2010; 66(4):999-1011. PMC: 4512205. DOI: 10.1111/j.1541-0420.2009.01375.x. View

Laguna P, Moody G, Mark R . Power spectral density of unevenly sampled data by least-square analysis: performance and application to heart rate signals. IEEE Trans Biomed Eng. 1998; 45(6):698-715. DOI: 10.1109/10.678605. View

Ngwa J, Cabral H, Cheng D, Pencina M, Gagnon D, LaValley M . A comparison of time dependent Cox regression, pooled logistic regression and cross sectional pooling with simulations and an application to the Framingham Heart Study. BMC Med Res Methodol. 2016; 16(1):148. PMC: 5094095. DOI: 10.1186/s12874-016-0248-6. View

Natarajan A, Su H, Heneghan C . Assessment of physiological signs associated with COVID-19 measured using wearable devices. NPJ Digit Med. 2020; 3(1):156. PMC: 7705652. DOI: 10.1038/s41746-020-00363-7. View

Truog R, Mitchell C, Daley G . The Toughest Triage - Allocating Ventilators in a Pandemic. N Engl J Med. 2020; 382(21):1973-1975. DOI: 10.1056/NEJMp2005689. View

Jose R, Manuel A . COVID-19 cytokine storm: the interplay between inflammation and coagulation. Lancet Respir Med. 2020; 8(6):e46-e47. PMC: 7185942. DOI: 10.1016/S2213-2600(20)30216-2. View

10.

Bent B, Goldstein B, Kibbe W, Dunn J . Investigating sources of inaccuracy in wearable optical heart rate sensors. NPJ Digit Med. 2020; 3:18. PMC: 7010823. DOI: 10.1038/s41746-020-0226-6. View

11.

Rajendra Acharya U, Joseph K, Kannathal N, Lim C, Suri J . Heart rate variability: a review. Med Biol Eng Comput. 2006; 44(12):1031-51. DOI: 10.1007/s11517-006-0119-0. View

12.

Nelson B, Allen N . Accuracy of Consumer Wearable Heart Rate Measurement During an Ecologically Valid 24-Hour Period: Intraindividual Validation Study. JMIR Mhealth Uhealth. 2019; 7(3):e10828. PMC: 6431828. DOI: 10.2196/10828. View

13.

Mietus J, Peng C, Henry I, Goldsmith R, Goldberger A . The pNNx files: re-examining a widely used heart rate variability measure. Heart. 2002; 88(4):378-80. PMC: 1767394. DOI: 10.1136/heart.88.4.378. View

14.

Emanuel E, Persad G, Upshur R, Thome B, Parker M, Glickman A . Fair Allocation of Scarce Medical Resources in the Time of Covid-19. N Engl J Med. 2020; 382(21):2049-2055. DOI: 10.1056/NEJMsb2005114. View

15.

Heagerty P, Zheng Y . Survival model predictive accuracy and ROC curves. Biometrics. 2005; 61(1):92-105. DOI: 10.1111/j.0006-341X.2005.030814.x. View

16.

Lu S, Zhao H, Ju K, Shin K, Lee M, Shelley K . Can photoplethysmography variability serve as an alternative approach to obtain heart rate variability information?. J Clin Monit Comput. 2007; 22(1):23-9. DOI: 10.1007/s10877-007-9103-y. View

17.

Cho S, Park S, Song M, Bae Y, Lee D, Kim D . Prognosis Score System to Predict Survival for COVID-19 Cases: a Korean Nationwide Cohort Study. J Med Internet Res. 2021; 23(2):e26257. PMC: 7901599. DOI: 10.2196/26257. View

18.

Morelli D, Rossi A, Cairo M, Clifton D . Analysis of the Impact of Interpolation Methods of Missing RR-intervals Caused by Motion Artifacts on HRV Features Estimations. Sensors (Basel). 2019; 19(14). PMC: 6679245. DOI: 10.3390/s19143163. View

19.

Foll S, Maritsch M, Spinola F, Mishra V, Barata F, Kowatsch T . FLIRT: A feature generation toolkit for wearable data. Comput Methods Programs Biomed. 2021; 212:106461. DOI: 10.1016/j.cmpb.2021.106461. View

20.

. Heart rate variability. Standards of measurement, physiological interpretation, and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. Eur Heart J. 1996; 17(3):354-81. View