A Study to Detect Hyperkalemia Using Smartphone-enabled Electrocardiogram (EKG)

Completed

• Conditions: Hyperkalemia

• Registration Number: NCT05441852
• Lead Sponsor: Mayo Clinic

Brief Summary

The purpose of this study is to validate the real-world performance of a previously developed Artificial Intelligence - Electrocardiogram (AI-ECG) algorithm for identification of hyperkalemia with a six-lead mobile-enhanced device .

Detailed Description

1. Ambulatory adult patients in the Emergency Department (ED) at increased risk for hyperkalemia (due to age ≥ 50 years, and one or more criteria including estimated Glomerular filtration rate (eGFR) (from serum creatinine) \< 45 ml/minute and/or a history of serum potassium \> 5.2 milliequivalents per liter (mEq/l) who present to the emergency department will be approached to consent for the rapid screening process.

2. Those who consent will undergo 30 second 6 L ECG recording with a portable, mobile-enhanced device (AliveCor Kardia).

3. This ECG data is subsequently evaluated by our artificial intelligence algorithm to detect hyperkalemia, and the estimated probability of hyperkalemia is recorded.

4. The research team notifies supervising Emergency Department staff of patients whose probability of hyperkalemia is significantly elevated above the optimized cutoff point according to the AI-ECG algorithm.

Study Timeline

• Study Start: 2022-03-31
• Study First Submitted: 2022-06-09
• Study First Submitted QC: 2022-06-29
• Study First Posted: 2022-07-01
• Status Verified: 2023-07
• Primary Completion: 2023-07-07
• Study Completion: 2023-07-07
• Last Update Submitted: 2023-07-12
• Last Update Posted: 2023-07-14

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 1151

Inclusion Criteria

• Age greater than/equal to 50 years and able to provide consent.
• Patients with eGFR (from serum creatinine) < 45 ml/minute and/or a history of serum potassium > 5.2 mEq/l.

Read More

Exclusion Criteria

• Patients underage < 50.
• Do not meet inclusion criteria.
• Unstable patients requiring emergent resuscitation.
• Patients unable to provide consent.

Read More

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
Hyperkalemia detection by AI enhanced ECG	12 months	Understanding model's ability to predict hyperkalemia as determined by the area under the receiver operating characteristic

Secondary Outcome Measures

Name	Time	Method
Performance metrics for the detection of hyperkalemia by AI enhanced ECG	12 months	Detailed performance metrics of the algorithm (sensitivity, specificity, positive predictive value and negative predictive value) will be calculated using an optimized cutoff threshold determined from the primary outcome.

Trial Locations

Locations (1)

Mayo Clinic; 🇺🇸 Rochester, Minnesota, United States