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

Rapid dEtection of HyperkAlemia (K+) in the EmergenCy Department Using a SmarTphone-enabled Single-lead EKG (REACT)

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 .

Study Overview

• Status: Completed
• Conditions: Hyperkalemia

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 Type: Observational
• Enrollment (Actual): 1151

Contacts and Locations

Study Locations

• United States
  • Minnesota
    • Rochester, Minnesota, United States, 55905
      • Mayo Clinic

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 50 years to 89 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Probability Sample

Study Population

Patients in the emergency department who meet the above inclusion criteria. Patients with the above inclusion criteria experience hyperkalemia more frequently than the general population at a prevalence near 10% compared to 2-4%, respectively.

Description

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.

Exclusion Criteria:

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

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort
Ambulatory Emergency Department Patients at risk for hyperkalemia; Patients who are at elevated risk for hyperkalemia identified during a visit to the emergency department. Elevated risk individuals are defined in this study as: >50 years of age, eGFR <45, or prior K >5.2

What is the study measuring?

Primary Outcome Measures

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

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Performance metrics for the detection of hyperkalemia by AI enhanced ECG	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.	12 months

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Time to laboratory confirmed hyperkalemia diagnosis	Following the detection of hyperkalemia by AI enhanced ECG time to initial hyperkalemia diagnosis (in minutes) by laboratory analysis following ambulatory emergency department presentation will be assessed.	12 months
Time to first treatment of hyperkalemia in Emergency Department	Following outcome measure 3 for patients determined to have hyperkalemia, time to first treatment intervention of hyperkalemia (in minutes) will be assessed since presentation to the emergency department.	12 months
Total time spent in Emergency Department	Patients who underwent AI enhanced screening for hyperkaliemia, and have a diagnosis of hyperkalemia by laboratory confirmation, will also be assessed for total time spent in the emergency department in hours.	12 Months
Hospital Admission Rate for Hyperkalemia patients	Patients who underwent AI enhanced screening for hyperkaliemia, and have a diagnosis of hyperkalemia by laboratory confirmation, will have the frequency of hospital admission assessed.	12 months
One year survival for hyperkalemic patients	Patients who underwent AI enhanced screening for hyperkaliemia, and have a diagnosis of hyperkalemia by laboratory confirmation, will have evaluation of survival at one year.	12 months
Rate of Adverse Events related to hyperkalemia	Patients who underwent AI enhanced screening for hyperkaliemia, and have a diagnosis of hyperkalemia by laboratory confirmation, will have evaluation of frequency of adverse events related to treatment of hyperkalemia (cardiac arrest, hypoglycemia, complications related to dialysis etc).	12 months
Exploratory AI enhanced ECG analysis for heart failure	A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo screening for hyperkaliemia in the ED with 6L Kardia ECG device. This neural network uses PQRST complexes to yield a probability of heart failure which may not be readily apparent via manual review. Each recorded 6L Kardia ECG will undergo evaluation by this neural network and will produce a probability of heart failure (0-100%) for each individual patient.	12 months
Exploratory AI enhanced ECG analysis for silent/paroxysmal atrial fibrillation	A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo screening for hyperkaliemia in the ED with 6L Kardia ECG device. This neural network uses PQRST complexes to yield a probability of silent/paroxysmal atrial fibrillation which may not be readily apparent via manual review. Each recorded 6L Kardia ECG will undergo evaluation by this neural network and will produce a probability of silent/paroxysmal atrial fibrillation (0-100%) for each individual patient.	12 months
Exploratory AI enhanced ECG analysis for aortic stenosis	A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo screening for hyperkaliemia in the ED with 6L Kardia ECG device. This neural network uses PQRST complexes to yield a probability of aortic stenosis which may not be readily apparent via manual review. Each recorded 6L Kardia ECG will undergo evaluation by this neural network and will produce a probability of aortic stenosis (0-100%) for each individual patient.	12 months
Exploratory AI enhanced ECG analysis for amyloidosis	A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo screening for hyperkaliemia in the ED with 6L Kardia ECG device. This neural network uses PQRST complexes to yield a probability of amyloidosis which may not be readily apparent via manual review. Each recorded 6L Kardia ECG will undergo evaluation by this neural network and will produce a probability of amyloidosis (0-100%) for each individual patient.	12 months
Exploratory AI enhanced ECG analysis to determine age	A previously developed AI algorithm to predict patient age from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo screening for hyperkaliemia in the ED with 6L Kardia ECG device. This neural network uses PQRST complexes to yield an ECG-predicted age. Each recorded 6L Kardia ECG will undergo evaluation by this neural network and determine "ECG age" for each individual patient.	12 months

Collaborators and Investigators

• Sponsor: Mayo Clinic
• Investigators: Principal Investigator: John Dillon, MD, Mayo Clinic

Publications and helpful links

Helpful Links

• Mayo Clinic Clinical Trials

Study record dates

Study Major Dates

• Study Start (Actual): March 31, 2022
• Primary Completion (Actual): July 7, 2023
• Study Completion (Actual): July 7, 2023

Study Registration Dates

• First Submitted: June 9, 2022
• First Submitted That Met QC Criteria: June 29, 2022
• First Posted (Actual): July 1, 2022

Study Record Updates

• Last Update Posted (Actual): July 14, 2023
• Last Update Submitted That Met QC Criteria: July 12, 2023
• Last Verified: July 1, 2023

More Information

Terms related to this study

• Keywords: Smartphone; hyperkalemia; electrocardiogram (ECG); Artificial Intelligence (AI); neural network; Emergency Department (ED); AliveCor Kardia 6 L ECG device
• Additional Relevant MeSH Terms: Metabolic Diseases; Water-Electrolyte Imbalance; Hyperkalemia
• Other Study ID Numbers: 21-006298

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Due to patient confidentiality and IRB rules, we will not make individual patient data available

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No