Chronic Kidney Disease (Stage 3-4), Hyperkalemia
Conditions
Keywords
hyperkalemia, ambulatory CKD, CKD, chronic kidney disease, ECG
Brief summary
The goal of this observational pilot study is to evaluate the investigational AK+ Guard™ software as a medical device (SaMD) for detection of moderate to severe hyperkalemia (serum potassium (K+) ≥ 6.5 mmol/L) in adults with chronic kidney disease (CKD). Study objectives are: * Arm 2A (Outpatient Diagnostic Accuracy): To generate a preliminary, real-world signal of the diagnostic performance of AK+ Guard™ when used in an ambulatory CKD cohort for identifying clinically significant hyperkalemia episodes (serum K+ ≥ 6.5 mmol/L) at the time of an outpatient laboratory draw. * Arm 2B (Remote Patient Monitoring): To assess participant compliance, usability, and end-to-end system reliability of AK+ Guard™ when deployed for daily remote monitoring of CKD patients outside the clinical environment for up to four weeks.
Detailed description
The AK+ Guard™ application is an investigational Software as a Medical Device (SaMD) developed by AccurKardia, Inc. (New York, USA). It is designed to aid in the diagnosis of moderate to severe hyperkalemia (serum potassium ≥ 6.5 mmol/L) in adults using artificial intelligence analysis of Lead I electrocardiogram (ECG) data. The software is intended as a clinical decision support tool for adults at risk of hyperkalemia, including but not limited to those with end-stage renal disease (ESRD), chronic kidney disease (CKD) on renin-angiotensin-aldosterone system inhibitors, heart failure, adrenal disorders, and patients taking aldosterone synthase inhibitors. The AK+ Guard™ application analyzes only Lead I ECG signals, which may be obtained from standard 12-lead ECGs, clinical-grade ECG devices with Lead I capability, or consumer wearable devices (e.g., Apple Watch). This pilot study is designed to generate preliminary real-world evidence on both the diagnostic performance of the application and its usability in daily life. The study includes two arms: Arm 2A - Outpatient Diagnostic Accuracy: * Estimate sensitivity, specificity, PPV, and NPV of AK+ Guard™ in ambulatory CKD stages III-IV * Evaluate interoperability across selected Lead I ECG capture devices (Apple Watch, HeartBeam, and 12 lead reference) * Characterize system reliability metrics (upload success, algorithm runtime) in the outpatient setting Arm 2B - Remote Patient Monitoring * Quantify participant compliance, data completeness, and attrition during four week remote monitoring * Evaluate user experience using System Usability Scale (SUS) score, Net Promoter Score (NPS), and semi structured feedback * Capture technical performance metrics in a real world, unsupervised context
Interventions
DEVICEAK+ Guard™ ECG Application
An investigational Software as a Medical Device (SaMD) that analyzes Lead I electrocardiogram (ECG) data using artificial intelligence to detect moderate to severe hyperkalemia (serum potassium ≥ 6.5 mmol/L). ECG inputs may be obtained from standard 12-lead ECGs, clinical-grade ECG devices with Lead I capability, or consumer wearable devices (e.g., Apple Watch, HeartBeam).
Sponsors
AccurKardia, Inc.
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
22 Years to No maximum
Healthy volunteers
No
Inclusion criteria
(Arm 2A - Outpatient Diagnostic Accuracy) * Age 22 years or older * CKD stages III-IV managed at Central Jersey Kidney Care outpatient clinic * Scheduled outpatient serum potassium laboratory test * On RAASi therapy or documented hyperkalemia (K+ ≥ 5.5 mmol/L) within the past 12 months * Able to provide written informed consent (Arm 2B - Remote Patient Monitoring) * Completion of Arm 2A visit * Owns an iPhone compatible with the study application
Exclusion criteria
(Both arms): * Age 21 years or younger * Pacemaker or implantable cardioverter defibrillator * Pre existing Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Intraventricular Conduction Delay (IVCD), or clinically significant hypocalcemia * Potassium lowering treatment administered before Lead I ECG acquisition * Trauma, acute events, or active interventions altering potassium homeostasis * Physical limitation precluding ECG acquisition
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Arm 2B: (c) Net Promoter Score (NPS) | Study completion at Week 4 (Day 28) | Participant-reported likelihood of recommending the system to others, measured on a 0-10 scale, with higher scores indicating greater likelihood to recommend. Individual responses are converted into a Net Promoter Score (NPS), which ranges from -100 to +100. Positive values (\>0) indicate overall customer loyalty and advocacy. |
| Arm 2B: (b) Mean System Usability Scale (SUS) score | Study completion at Week 4 (Day 28) | 10-item scale with final score between 0 and 100. The SUS score is an index of perceived usability (not a percentage), with higher scores indicating better usability. A score above 68 is generally considered above average usability, while lower scores suggest more usability concerns. The reported outcome will be the mean SUS score across participants. |
| Arm 2B: (a) Daily compliance rate (proportion of completed ECGs out of scheduled ECGs) | Daily monitoring up to 4 weeks (Day 28) | — |
| Arm 2A: Sensitivity and specificity of AK+ Guard™ for detecting serum potassium greater than or equal to 6.5 mmol/L | Baseline (Day 0) | Defined as serum K+ ≥ 6.5 mmol/L |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Arm 2A: Algorithm runtime | Baseline (Day 0) | Time in seconds (s) required for the AK+ Guard™ algorithm to complete analysis, defined as the total of transmission time, processing time, and time to return results. |
| Arm 2A: Upload success rate | Baseline (Day 0) | Percentage (%) of attempted ECG uploads that successfully complete without failure. |
| Arm 2A: Positive Predictive Value (PPV) | Baseline (Day 0) | Percentage (%) of positive hyperkalemia alerts generated by AK+ Guard™ that are confirmed as true positives by outpatient laboratory results. |
| Arm 2A: Negative Predictive Value (NPV) | Baseline (Day 0) | Percentage (%) of negative results generated by AK+ Guard™ that are confirmed as true negatives by outpatient laboratory results. |
| Arm 2A: Device specific concordance | Baseline (Day 0) | Percentage (%) of device-detected results that agree with outpatient laboratory results. |
| Arm 2B: Data completeness | Daily monitoring up to 4 weeks (Day 28) | Percentage (%) of scheduled ECGs that are successfully completed. |
| Arm 2B: System reliability (application (app) crash rate, upload failure less than 2 percent (%)) | Daily monitoring up to 4 weeks (Day 28) | — |
| Arm 2B: Number of service calls per participant | Daily monitoring up to 4 weeks (Day 28) | — |
| Arm 2B: False positive alarm rate (less than 20%) | Daily monitoring up to 4 weeks (Day 28) | Percentage (%) of alarms generated by AK+ Guard™ that are not confirmed as true clinical events by outpatient laboratory results. |
Other
| Measure | Time frame | Description |
|---|---|---|
| Arm 2A (Exploratory): Positive Predictive Value (PPV, stratified) | Baseline (Day 0) | PPV of AK+ Guard™ for detecting serum K+ ≥ 6.5 mmol/L, stratified by CKD stage, renin-angiotensin-aldosterone system inhibitor (RAASi) use, and comorbidity profile. Reported as point estimate (%) with confidence interval. |
| Arm 2A (Exploratory): Sensitivity (stratified) | Baseline (Day 0) | Sensitivity of AK+ Guard™ for detecting serum K+ ≥ 6.5 mmol/L, stratified by CKD stage, renin-angiotensin-aldosterone system inhibitor (RAASi) use, and comorbidity profile. Reported as point estimate (%) with confidence interval. |
| Arm 2B (Exploratory): Participant anxiety and comfort | Baseline (Day 0) and at study completion (Day 28) | Change from baseline in survey responses on reassurance and anxiety, and comfort with using AK+ Guard™. Each item is rated on a 5-point Likert scale (1 = Strongly Disagree, 5 = Strongly Agree). |
| Arm 2B (Exploratory): Participant perception of medication safety | Baseline (Day 0) and at study completion (Day 28) | Change from baseline in survey responses on perceived benefit of AK+ Guard™ for monitoring potassium and identifying dangerous levels earlier. Each item is rated on a 5-point Likert scale (1 = Strongly Disagree, 5 = Strongly Agree). |
| Arm 2A (Exploratory): Negative Predictive Value (NPV, stratified) | Baseline (Day 0) | NPV of AK+ Guard™ for detecting serum K+ ≥ 6.5 mmol/L, stratified by CKD stage, renin-angiotensin-aldosterone system inhibitor (RAASi) use, and comorbidity profile. Reported as point estimate (%) with confidence interval. |
Countries
United States
Contacts
Primary ContactMoin Hussaini
Outcome results
None listed