Artificial Intelligence Identified Dyskalemia Using Electrocardiogram (AIDE)
Primary Purpose
Hyperkalemia, Hypokalemia
Status
Completed
Phase
Not Applicable
Locations
Taiwan
Study Type
Interventional
Intervention
Artificial Intelligence identified Dyskalemia using Electrocardiogram (AIDE) system
Sponsored by
About this trial
This is an interventional screening trial for Hyperkalemia
Eligibility Criteria
Inclusion Criteria:
- Patients in emergency department.
- Patients recieved at least 1 ECG examination.
Exclusion Criteria:
- Patients recieved potassium blood test before ECG examination.
- The patients recieved ECG at the period of inactive AI-ECG system.
Sites / Locations
- National Defense Medical Center
Arms of the Study
Arm 1
Arm 2
Arm Type
Experimental
No Intervention
Arm Label
Intervention
Control
Arm Description
Patients randomized to intervention will be cared by physicians under AI-ECG support.
Patients randomized to control will be cared by routine practice.
Outcomes
Primary Outcome Measures
Cumulative proportion of hyperkalemia treatment
Calcium supplement, insulin, potassium binding resin, β2-agonist, loop diuretics, sodium bicarbonate, and hemodialysis.
Cumulative proportion of hypokalemia treatment
Intravenous potassium chloride, oral potassium gluconate, and oral potassium chloride
Cumulative proportion of echocardiogram
Echocardiogram for patients with abnormal ECG.
Secondary Outcome Measures
Cumulative proportion of ICU admission
ICU admission
Cumulative proportion of Discharge
Discharge from inpatient department or emergency department
Cumulative proportion of ED revisits in patients without hospitalization
ED revisits in patients without hospitalization
Full Information
NCT ID
NCT05118022
First Posted
November 1, 2021
Last Updated
March 1, 2023
Sponsor
National Defense Medical Center, Taiwan
1. Study Identification
Unique Protocol Identification Number
NCT05118022
Brief Title
Artificial Intelligence Identified Dyskalemia Using Electrocardiogram (AIDE)
Official Title
Artificial Intelligence Identified Dyskalemia Using Electrocardiogram (AIDE) Prompts Immediate Treatment
Study Type
Interventional
2. Study Status
Record Verification Date
March 2023
Overall Recruitment Status
Completed
Study Start Date
January 1, 2022 (Actual)
Primary Completion Date
October 31, 2022 (Actual)
Study Completion Date
February 28, 2023 (Actual)
3. Sponsor/Collaborators
Responsible Party, by Official Title
Principal Investigator
Name of the Sponsor
National Defense Medical Center, Taiwan
4. Oversight
Studies a U.S. FDA-regulated Drug Product
No
Studies a U.S. FDA-regulated Device Product
No
Data Monitoring Committee
No
5. Study Description
Brief Summary
This is a randomized controlled trial (RCT) to test a novel artificial intelligence (AI)-enabled electrocardiogram (ECG)-based screening tool for improving the diagnosis and management of potassium abnormalities.
6. Conditions and Keywords
Primary Disease or Condition Being Studied in the Trial, or the Focus of the Study
Hyperkalemia, Hypokalemia
7. Study Design
Primary Purpose
Screening
Study Phase
Not Applicable
Interventional Study Model
Parallel Assignment
Masking
None (Open Label)
Allocation
Randomized
Enrollment
14989 (Actual)
8. Arms, Groups, and Interventions
Arm Title
Intervention
Arm Type
Experimental
Arm Description
Patients randomized to intervention will be cared by physicians under AI-ECG support.
Arm Title
Control
Arm Type
No Intervention
Arm Description
Patients randomized to control will be cared by routine practice.
Intervention Type
Other
Intervention Name(s)
Artificial Intelligence identified Dyskalemia using Electrocardiogram (AIDE) system
Intervention Description
Once the AIDE indicates high risk of dyskalemia, an obvious message by scarlet letter was appeared in the HIS operation interface to corresponding physicians. To avoid the alert fatigue, we selected the cut-off points with expected positive predictive values of ≥40% according to previous data, which was the consensus of enrolled physicians before the trial considering the clinical loading. The physicians received the AIDE alerts as long as they were operating HIS logged in by their account, even if they were caring other patients. Physicians can review the AIDE predictions of patients in the intervention group. Therefore, this was a single-blind study since HIS presented different information for patients in intervention and control groups. The participated physicians understood the likelihood of dyskalemia and cardiac risk for those patients with ECG-dyskalemia, and provided suitable medical care according to patients' conditions.
Primary Outcome Measure Information:
Title
Cumulative proportion of hyperkalemia treatment
Description
Calcium supplement, insulin, potassium binding resin, β2-agonist, loop diuretics, sodium bicarbonate, and hemodialysis.
Time Frame
Within 3 hours
Title
Cumulative proportion of hypokalemia treatment
Description
Intravenous potassium chloride, oral potassium gluconate, and oral potassium chloride
Time Frame
Within 3 hours
Title
Cumulative proportion of echocardiogram
Description
Echocardiogram for patients with abnormal ECG.
Time Frame
Within 12 hours
Secondary Outcome Measure Information:
Title
Cumulative proportion of ICU admission
Description
ICU admission
Time Frame
Within 3 days
Title
Cumulative proportion of Discharge
Description
Discharge from inpatient department or emergency department
Time Frame
Within 14 days
Title
Cumulative proportion of ED revisits in patients without hospitalization
Description
ED revisits in patients without hospitalization
Time Frame
Within 30 days
10. Eligibility
Sex
All
Minimum Age & Unit of Time
18 Years
Accepts Healthy Volunteers
No
Eligibility Criteria
Inclusion Criteria:
Patients in emergency department.
Patients recieved at least 1 ECG examination.
Exclusion Criteria:
Patients recieved dyskalemia-related treatment before ECG examination.
The patients recieved ECG at the period of inactive AI-ECG system.
Facility Information:
Facility Name
National Defense Medical Center
City
Taipei
ZIP/Postal Code
114
Country
Taiwan
12. IPD Sharing Statement
Plan to Share IPD
No
Learn more about this trial
Artificial Intelligence Identified Dyskalemia Using Electrocardiogram (AIDE)
We'll reach out to this number within 24 hrs