Personalized Analytics and a Wearable Biosensor Platform for Early Detection of COVID-19 Decompensation (DeCODe): Protocol for the Development of the COVID-19 Decompensation Index

Karen Larimer, Stephan Wegerich, Joel Splan, David Chestek, Heather Prendergast, Terry Vanden Hoek, Karen Larimer, Stephan Wegerich, Joel Splan, David Chestek, Heather Prendergast, Terry Vanden Hoek

Abstract

Background: During the COVID-19 pandemic, novel digital health technologies have the potential to improve our understanding of SARS-CoV-2 and COVID-19, improve care delivery, and produce better health outcomes. The National Institutes of Health called on digital health leaders to contribute to a high-quality data repository that will support researchers to make discoveries that are otherwise not possible with small, limited data sets.

Objective: To this end, we seek to develop a COVID-19 digital biomarker for early detection of physiological exacerbation or decompensation. We propose the development and validation of a COVID-19 decompensation Index (CDI) in a 2-phase study that builds on existing wearable biosensor-derived analytics generated by physIQ's end-to-end cloud platform for continuous physiological monitoring with wearable biosensors. This effort serves to achieve two primary objectives: (1) to collect adequate data to help develop the CDI and (2) to collect rich deidentified clinical data correlating with outcomes and symptoms related to COVID-19 progression. Our secondary objectives include evaluation of the feasibility and usability of pinpointIQ, a digital platform through which data are gathered, analyzed, and displayed.

Methods: This is a prospective, nonrandomized, open-label, 2-phase study. Phase I will involve data collection for the digital data hub of the National Institutes of Health as well as data to support the preliminary development of the CDI. Phase II will involve data collection for the hub and contribute to continued refinement and validation of the CDI. While this study will focus on the development of a CDI, the digital platform will also be evaluated for feasibility and usability while clinicians deliver care to continuously monitored patients enrolled in the study.

Results: Our target CDI will be a binary classifier trained to distinguish participants with and those without decompensation. The primary performance metric for CDI will be the area under the receiver operating characteristic curve with a minimum performance criterion of ≥0.75 (α=.05; power [1-β]=0.80). Furthermore, we will determine the sex or gender and race or ethnicity of the participants, which would account for differences in the CDI performance, as well as the lead time-time to predict decompensation-and its relationship with the ultimate disease severity based on the World Health Organization COVID-19 ordinal scale.

Conclusions: Using machine learning techniques on a large data set of patients with COVID-19 could provide valuable insights into the pathophysiology of COVID-19 and a digital biomarker for COVID-19 decompensation. Through this study, we intend to develop a tool that can uniquely reflect physiological data of a diverse population and contribute to high-quality data that will help researchers better understand COVID-19.

Trial registration: ClinicalTrials.gov NCT04575532; https://www.clinicaltrials.gov/ct2/show/NCT04575532.

International registered report identifier (irrid): DERR1-10.2196/27271.

Keywords: COVID-19; analytic; artificial intelligence; biomarker; cloud; decompensation; detection; development; index; monitoring; outcome; remote monitoring; symptom validation; wearable.

Conflict of interest statement

Conflicts of Interest: KL, SW, and JS own shares in and are engaged in paid employment at physIQ.

©Karen Larimer, Stephan Wegerich, Joel Splan, David Chestek, Heather Prendergast, Terry Vanden Hoek. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 26.05.2021.

Figures

Figure 1
Figure 1
Study protocol. ED: emergency department, HR: heart rate, RR: respiratory rate, ECG: electrocardiography, UIH: University of Illinois Health. ©2021 physIQ.
Figure 2
Figure 2
Smartphone app and an example survey.
Figure 3
Figure 3
Daily patient reported-health surveys displayed to the clinical user.
Figure 4
Figure 4
Watchlist and patient dashboard.
Figure 5
Figure 5
Clinical user's patient dashboard.

References

    1. NIH awards contracts to develop innovative digital health technologies for COVID-19. National Institutes of Health. 2020. Sep 15, [2021-05-11]. .
    1. Golinelli D, Boetto E, Carullo G, Nuzzolese A, Landini M, Fantini M. Adoption of Digital Technologies in Health Care During the COVID-19 Pandemic: Systematic Review of Early Scientific Literature. J Med Internet Res. 2020 Nov 06;22(11):e22280. doi: 10.2196/22280.
    1. Steinhubl S, Larimer K. Healthcare’s Failures in the Time Of COVID-19: It is Time to Completely Rethink Patient Care in a Digital Age. Healthcare IT Today. 2020. Jun 15, [2021-05-11].
    1. Guan WJ, Ni ZY, Hu Y, Liang WH, Ou CQ, He JX, Liu L, Shan H, Lei CL, Hui DSC, Du B, Li LJ, Zeng G, Yuen KY, Chen RC, Tang CL, Wang T, Chen PY, Xiang J, Li SY, Wang JL, Liang ZJ, Peng YX, Wei L, Liu Y, Hu YH, Peng P, Wang JM, Liu JY, Chen Z, Li G, Zheng ZJ, Qiu SQ, Luo J, Ye CJ, Zhu SY, Zhong NS, China Medical Treatment Expert Group for Covid-19 Clinical Characteristics of Coronavirus Disease 2019 in China. N Engl J Med. 2020 Apr 30;382(18):1708–1720. doi: 10.1056/NEJMoa2002032.
    1. Petrilli CM, Jones SA, Yang J, Rajagopalan H, O'Donnell L, Chernyak Y, Tobin KA, Cerfolio RJ, Francois F, Horwitz LI. Factors associated with hospital admission and critical illness among 5279 people with coronavirus disease 2019 in New York City: prospective cohort study. BMJ. 2020 May 22;369:m1966. doi: 10.1136/bmj.m1966.
    1. 6 ML, Davis S, Patel T, Hernandez M, Ciccarelli G, Schwartz S, Samsi S, Hensley L, Goff A, Trefry J, Johsnston S, Purcell B, Cabrera C, Fleischman J, Reuther A, Rossi F, Honko A, Pratt W, Swiston A. Detecting pathogen exposure during the non-symptomatic incubation period using physiological data. bioRxiv. doi: 10.1101/218818. doi: 10.1101/218818. Preprint posted online November 13, 2017.
    1. Madjid M, Safavi-Naeini P, Solomon SD, Vardeny O. Potential Effects of Coronaviruses on the Cardiovascular System: A Review. JAMA Cardiol. 2020 Jul 01;5(7):831–840. doi: 10.1001/jamacardio.2020.1286.
    1. Mitchell UA, Chebli P, Ruggiero L, Muramatsu N. The Digital Divide in Health-Related Technology Use: The Significance of Race/Ethnicity. Gerontologist. 2019 Jan 09;59(1):6–14. doi: 10.1093/geront/gny138.
    1. Schmidt N, Stephens B. An introduction to artificial intelligence and solutions to the problems of algorithmic discrimination. arXiv. Preprint posted online November 8, 2019.
    1. World Health Organization. [2021-05-11]. .
    1. Bowen DJ, Kreuter M, Spring B, Cofta-Woerpel L, Linnan L, Weiner D, Bakken S, Kaplan CP, Squiers L, Fabrizio C, Fernandez M. How we design feasibility studies. Am J Prev Med. 2009 May;36(5):452–457. doi: 10.1016/j.amepre.2009.02.002.
    1. Brahmbhatt DH, Cowie MR. Remote Management of Heart Failure: An Overview of Telemonitoring Technologies. Card Fail Rev. 2019 May;5(2):86–92. doi: 10.15420/cfr.2019.5.3.

Source: PubMed

Patrocinadores y Colaboradores

Condiciones médicas

Intervenciones de drogas

3
Suscribir