WAVE. Wearable-based COVID-19 Markers for Prediction of Clinical Trajectories (WAVE)

Wearable-based COVID-19 Markers for Prediction of Clinical Trajectories. The WAVE Study.

The aim is to develop a wearable-based ICU (intensive care unit) prediction algorithm for inpatients contracted with SARS-CoV-2. Inpatients with suspicion of COVID-19 or with confirmed SARS-CoV-2 infection will be included. The participants will be equipped with a smartwatch, which gathers physiological data throughout hospitalisation.

Study Overview

• Status: Completed
• Conditions: SARS-CoV 2; COVID 19; COVID
• Intervention / Treatment: Other: Equipment with smartwatch throughout hospital stay on the general ward

Detailed Description

The SARS-CoV-2 pandemic puts an unprecedented burden on the healthcare system, specifically its healthcare providers and the resource demands for intensive care units (ICUs). To support effective care despite large case numbers, hospital operations urgently need improved decision support in early identification of patients at risk of an acute COVID-19 deterioration that requires ICU.

The investigators aim at developing a wearable-based ICU algorithm for inpatients contracted with SARS-CoV-2. Inpatients on the general ward with suspicion of COVID-19 or with confirmed SARS-CoV-2 infection will be included. The participant will be equipped with a smartwatch and wear the device throughout the hospital stay until the patient (1) is discharged home, (2) is transferred to the ICU, or (3) palliative care is initiated. The smartwatch collects several physiological parameters (e.g. heart rate, heart rate variability, respiration rate, oxygen saturation). The collected data will be used to develop an ICU prediction algorithm to detect patients at risk of an acute COVID-19 deterioration that requires ICU.

• Study Type: Observational
• Enrollment (Actual): 46

Contacts and Locations

Study Locations

• Switzerland
  • Bern, Switzerland, 3010
    • Emergency Department, University Hospital Bern, Inselspital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 120 years (ADULT, OLDER_ADULT)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients with suspicion of COVID-19 or tested positive for SARS-CoV-2 that are or will be hospitalized on the general ward

Description

Inclusion Criteria:

• Informed consent as documented by signature
• Age >= 18 years
• Suspicion of COVID-19 or patient tested positive for SARS-CoV-2
• Hospitalisation on the general ward

Exclusion Criteria:

• Smartwatch cannot be attached around the wrist of the patient
• Direct transfer from the emergency department or external institution to ICU (i.e. no hospitalization on the general ward)
• Known allergies to components of the smartwatch
• Rejection of ICU transfer in the patient decree

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Smartwatch group	Other: Equipment with smartwatch throughout hospital stay on the general ward; Participants with confirmed SARS-CoV-2 infection or suspicion of COVID-19 will be equipped with a smartwatch and wear the device throughout the hospital stay on the general ward.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of smartwatch data in predicting ICU requirement in COVID-19 contracted inpatients quantified as the area under the receiver operator characteristics curve (AUC ROC > 0.85).	Accuracy of the WAVE-model will be assessed using physiological data recorded by the smartwatch (Garmin vivoactive 4) during hospitalization complemented by demographic and health-related patient-information and will be analysed using applied machine learning technology for ICU prediction.	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of routine physiological data in predicting ICU requirement in COVID-19 contracted in-patients quantified as the area under the receiver operator characteristics curve (AUC ROC > 0.85).	Accuracy of the model will be assessed using physiological data routinely recorded during hospitalization and will be analysed using applied machine learning technology for ICU prediction.	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Diagnostic accuracy of predicting hospital discharge without ICU admission in COVID-19 contracted in-patients quantified as area under the receiver operator characteristics curve	Accuracy of the model will be assessed using data on comorbidities, medication treatment during hospitalization and physiological data and will be analysed using casual machine-learning approaches	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of heart rate from baseline (hospitalization) to ICU admission	Heart rate will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors.	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of heart rate variability from baseline (hospitalization) to ICU admission	Heart rate variability will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of skin temperature from baseline (hospitalization) to ICU admission	Skin temperature will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of blood oxygen saturation from baseline (hospitalization) to ICU admission	Blood oxygen saturation will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of respiration rate from baseline (hospitalization) to ICU admission	Respiration rate will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of physical activity from baseline (hospitalization) to ICU admission	Physical activity will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of stress level from baseline (hospitalization) to ICU admission	Stress level will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of sleep pattern from baseline (hospitalization) to ICU admission	Sleep will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of steps per day from baseline (hospitalization) to ICU admission	Steps per day will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of systolic blood pressure from baseline (hospitalization) to ICU admission	Systolic blood pressure will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of diastolic blood pressure from baseline (hospitalization) to ICU admission	Diastolic blood pressure will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of body temperature from baseline (hospitalization) to ICU admission	Body temperature will be recorded throughout the hospitalization using a routine medical thermometer	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of oxygen partial pressure (pO2) from baseline (hospitalization) to ICU admission	Oxygen partial pressure (pO2) will be routinely assessed during the hospitalization in arterial or venous blood gas analyses	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of CO2 partial pressure (pCO2) from baseline (hospitalization) to ICU admission	CO2 partial pressure (pCO2) will be routinely assessed during the hospitalization in arterial or venous blood gas analyses	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of blood pH from baseline (hospitalization) to ICU admission	Blood pH will be routinely assessed during the hospitalization in arterial or venous blood gas analyses	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of bicarbonate from baseline (hospitalization) to ICU admission	Bicarbonate will be routinely assessed during the hospitalization in arterial or venous blood gas analyses	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of base excess from baseline (hospitalization) to ICU admission	Base excess will be routinely assessed during the hospitalization in arterial or venous blood gas analyses	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)
Change of oxygen flow rate from baseline (hospitalization) to ICU admission	Oxygen flow rate will be routinely assessed during the hospitalization	until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days)

Collaborators and Investigators

• Sponsor: University Hospital Inselspital, Berne
• Collaborators: ETH Zurich
• Investigators: Study Chair: Aristomenis Extradaktylos, Prof. MD, University Hospital Bern - Department of Emergency Medicine

Publications and helpful links

General Publications

• Foll S, Lison A, Maritsch M, Klingberg K, Lehmann V, Zuger T, Srivastava D, Jegerlehner S, Feuerriegel S, Fleisch E, Exadaktylos A, Wortmann F. A Scalable Risk-Scoring System Based on Consumer-Grade Wearables for Inpatients With COVID-19: Statistical Analysis and Model Development. JMIR Form Res. 2022 Jun 21;6(6):e35717. doi: 10.2196/35717.

Study record dates

Study Major Dates

• Study Start (ACTUAL): October 22, 2020
• Primary Completion (ACTUAL): June 30, 2021
• Study Completion (ACTUAL): June 30, 2021

Study Registration Dates

• First Submitted: April 17, 2020
• First Submitted That Met QC Criteria: April 17, 2020
• First Posted (ACTUAL): April 22, 2020

Study Record Updates

• Last Update Posted (ACTUAL): August 26, 2021
• Last Update Submitted That Met QC Criteria: August 25, 2021
• Last Verified: August 1, 2021

More Information

Terms related to this study

• Keywords: Intensive care unit; Artificial intelligence; Smartwatch; Prediction; Intensive care; Clinical trajectories
• Additional Relevant MeSH Terms: Coronavirus Infections; Coronaviridae Infections; Nidovirales Infections; RNA Virus Infections; Virus Diseases; Infections; Respiratory Tract Infections; Respiratory Tract Diseases; Pneumonia, Viral; Pneumonia; Lung Diseases; COVID-19
• Other Study ID Numbers: WAVE

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No