Detection of Gastrointestinal Bleeding in Intensive Care Patients Via Biosensor Watch

The purpose of this study to improve methods of monitoring and diagnosing gastrointestinal bleeding via the E4 wristband, a biosensor watch.

Study Overview

• Status: Terminated
• Conditions: Gastro Intestinal Bleeding
• Intervention / Treatment: Device: E4 wristband

Detailed Description

The annual occurrence of gastrointestinal (GI) bleeding is approximately 150 per 100,000 in the US and accounts for 300,000 hospitalizations per year with a death rate of 5%. Qualitative assessments of blood tests monitoring patients with or are thought to have GI bleeding can lack accuracy and objectivity, delaying conformation of the bleed through endoscopy. Early endoscopies have been linked to more favorable outcomes for patients with heavier GI bleeding and earlier discharge times for patients with less severe GI bleeding. Additionally, laboratory values are not documented at regular intervals, which makes identifying when GI bleeding exactly occurred difficult. In this study, the investigators aim to improve methods of monitoring and diagnosing GI bleeding via the E4 wristband, a biosensor watch. Using data from the E4 wristband, the investigators will train a model to recognize GI bleeding through analyzing the heart rate and skin conductance of both patients with GI bleeding and who may have GI bleeding while they are not bleeding and while they are bleeding. Monitoring both types of patients while they are and are not bleeding will help the model discern which vital signs are critical. Additionally, the investigators will be using blood tests and other traditional methods of diagnosis to create a standard for vitals that characterize GI bleeding. If the E4 wristband is successfully able to accurately identify when a patient is experiencing GI bleeding, then speed of GI bleeding detection and the ability to monitor GI bleeding will dramatically increase, leading to quicker discharge times, reduced risk of rebleeding, and a lower death rate for afflicted patients.

• Study Type: Observational
• Enrollment (Actual): 20

Contacts and Locations

• Study Contact: Name: Chin Hur, MD; Phone Number: 212-305-2020; Email: ch447@cumc.columbia.edu
• Study Contact Backup: Name: Myles A Ingram, BA; Phone Number: 678-777-0616; Email: mai2125@cumc.columbia.edu

Study Locations

• United States
  • New York
    • New York, New York, United States, 10032
      • Columbia University Irving Medical Center

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 25 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients will be selected from the intensive care unit (ICU) in the Milstein Hospital Building at Columbia University.

Description

Inclusion Criteria:

• Patients with a history of gastrointestinal bleeding and/or showing the symptoms of gastrointestinal bleeding.

Exclusion Criteria:

• Patients who are not showing the symptoms of gastrointestinal bleeding and/or do not have a history of gastrointestinal bleeding.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
High-Risk of GI Bleed; Patients that have a high risk of having a gastrointestinal bleed upon admission into the ICU based on their medical history and symptoms. These patients will have a biosensor watch, the E4 wristband, placed on them to monitor their vital signs.	Device: E4 wristband; A biosensor watch that monitors the patient's heartbeat, heart rate variability, skin conductance, and temperature in order to discover if they are having a GI bleed

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Heart Rate	Using the wristband, heart rate will be collected at a frequency of 64 Hz.	Up to 1 year
Skin Conductance	Using the wristband, skin conductance will be collected at a frequency of 4 Hz.	Up to 1 year

Collaborators and Investigators

• Sponsor: Columbia University

Publications and helpful links

General Publications

• Kim BS, Li BT, Engel A, Samra JS, Clarke S, Norton ID, Li AE. Diagnosis of gastrointestinal bleeding: A practical guide for clinicians. World J Gastrointest Pathophysiol. 2014 Nov 15;5(4):467-78. doi: 10.4291/wjgp.v5.i4.467.

Study record dates

Study Major Dates

• Study Start (Actual): March 29, 2019
• Primary Completion (Actual): July 20, 2021
• Study Completion (Actual): July 20, 2021

Study Registration Dates

• First Submitted: March 12, 2019
• First Submitted That Met QC Criteria: March 12, 2019
• First Posted (Actual): March 14, 2019

Study Record Updates

• Last Update Posted (Actual): May 3, 2023
• Last Update Submitted That Met QC Criteria: April 28, 2023
• Last Verified: April 1, 2023

More Information

Terms related to this study

• Keywords: Intensive Care Unit; GI bleeding; Biosensor watch; E4 Wristband
• Additional Relevant MeSH Terms: Digestive System Diseases; Pathologic Processes; Gastrointestinal Diseases; Hemorrhage; Gastrointestinal Hemorrhage
• Other Study ID Numbers: AAAS1510

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: There is no plan to share with other researchers outside of the research team.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No