WAVE. Wearable-based COVID-19 Markers for Prediction of Clinical Trajectories
- Conditions
- COVID 19COVIDSARS-CoV 2
- Interventions
- Other: Equipment with smartwatch throughout hospital stay on the general ward
- Registration Number
- NCT04357834
- Lead Sponsor
- Insel Gruppe AG, University Hospital Bern
- Brief Summary
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.
- 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.
Recruitment & Eligibility
- Status
- COMPLETED
- Sex
- All
- Target Recruitment
- 46
- 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
- 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 & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Arm && Interventions
Group Intervention Description Smartwatch group Equipment with smartwatch throughout hospital stay on the general ward -
- Primary Outcome Measures
Name Time Method 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). until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) 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.
- Secondary Outcome Measures
Name Time Method 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). until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) 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.
Change of blood oxygen saturation from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Blood oxygen saturation will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors
Change of sleep pattern from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Sleep will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of heart rate variability from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Heart rate variability will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of physical activity from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Physical activity will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of diastolic blood pressure from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Diastolic blood pressure will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors
Change of base excess from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Base excess will be routinely assessed during the hospitalization in arterial or venous blood gas analyses
Diagnostic accuracy of predicting hospital discharge without ICU admission in COVID-19 contracted in-patients quantified as area under the receiver operator characteristics curve until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) 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
Change of respiration rate from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Respiration rate will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors
Change of steps per day from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Steps per day will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of oxygen partial pressure (pO2) from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Oxygen partial pressure (pO2) will be routinely assessed during the hospitalization in arterial or venous blood gas analyses
Change of heart rate from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Heart rate will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors.
Change of stress level from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Stress level will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of CO2 partial pressure (pCO2) from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) CO2 partial pressure (pCO2) will be routinely assessed during the hospitalization in arterial or venous blood gas analyses
Change of blood pH from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Blood pH will be routinely assessed during the hospitalization in arterial or venous blood gas analyses
Change of skin temperature from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Skin temperature will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S)
Change of systolic blood pressure from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Systolic blood pressure will be recorded throughout the hospitalization using a smartwatch (Garmin vivoactive 4S) and using routine medical monitors
Change of body temperature from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Body temperature will be recorded throughout the hospitalization using a routine medical thermometer
Change of bicarbonate from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Bicarbonate will be routinely assessed during the hospitalization in arterial or venous blood gas analyses
Change of oxygen flow rate from baseline (hospitalization) to ICU admission until hospital discharge, transfer to ICU or palliative care is initiated (expected to be on average after 7-30 days) Oxygen flow rate will be routinely assessed during the hospitalization
Trial Locations
- Locations (1)
Emergency Department, University Hospital Bern, Inselspital
🇨ðŸ‡Bern, Switzerland