The Role of Wearable Devices in Predicting and Detecting Complications and Adverse Events
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorMassachusetts General Hospital
About this trial
The overarching goal of this research is to use machine learning analysis of high-resolution data-collected by wearable technology-to predict complications and poor recovery in patients undergoing treatment for benign or malignant conditions.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older
Individuals scheduled to undergo one of the following surgical or non-surgical treatments: cardiothoracic surgery, orthopedic surgery, vascular surgery, colorectal surgery, pancreatic surgery, other major abdominal surgeries, treatment for chronic disease, or systemic therapy (i.e., chemotherapy, immunotherapy, or targeted therapy), radiotherapy, or ablation.
Amenable to using one of the wearable devices of interest (Fitbit, iWatch, Biostrap).
Individuals willing to provide informed consent and who have capacity for all study procedures
Disqualifiers
Individuals with mental incapacity and/or cognitive impairment that would preclude adequate understanding of, or cooperation with the study protocol.
Any pregnant participant.
Trial population
Patients undergoing treatment for benign or malignant conditions that are amenable to wearing a device of interest and meet the inclusion and exclusion criteria above will be approached for informed consent.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Device: Wearable Device
DeviceA Wearable Device will be placed on the wrist of the patient \~30 days prior to the patient's scheduled treatment and for up to 5 years following treatment. The device will record activity in terms of steps, sleep quality, heart rate, etc.
Treatment groups
2,400 Participants
are divided into 1 treatment groupGroup A: Treatment Group1 intervention
Trial outcomes
Primary outcomes
1
Early detection of complications and adverse events using machine learning analysis of patient biometric data.
Proportion of complications detected by the machine learning algorithm.
Time frame
Five Years2
Prediction of the quality of recovery after treatment using patient biometric data.
Proportion of patients whose quality of recovery is correctly predicted by the machine learning algorithm.
Time frame
Four YearsSponsors and contacts
Click on the lead sponsor to view all of their trials.
Massachusetts General Hospital
Lead sponsor
Case Western Reserve University
Collaborator
Source ClinicalTrials.gov