Serum Potassium Prediction Using Machine Learning and Single-lead ECG

NCT07493798 | Withdrawn

• 1 other identifier: 2017P002583c
• Study Type: observational
• Target: N/A
• Locations: 1 country
• Sites: 2

Brief Summary

This is a retrospective study drawing on data from the Brigham and Women's Hospital Home Hospital Program's Database. Sociodemographic and clinical data from a training cohort were used to train a machine learning algorithm to predict blood potassium throughout a patient's admission. This algorithm was then validated in a validation cohort.

Conditions

Infection; Heart Failure; Chronic Obstructive Pulmonary Disease; Asthma; Gout Flare; Chronic Kidney Diseases; Hypertensive Urgency; Atrial Fibrillation Rapid; Anticoagulants; Increased

Outcome Measures

Primary Outcomes (1)

• Serum potassium concentration

  Serum potassium, measured in millimol per liter

  From date of admission to date of discharge, through study completion on average 7 days.

Secondary Outcomes (4)

• Hyperkalemia

  From date of admission to date of discharge, through study completion on average 7 days.

• Hypokalemia

  From date of admission to date of discharge, through study completion on average 7 days.

• Normokalemia

  From date of admission to date of discharge, through study completion on average 7 days.

• Serum potassium less than versus greater than or equal to 4 millimol per liter

  From date of admission to date of discharge, through study completion on average 7 days.

Study Arms (2)

Training

A subset of patients that are used to train the machine learning algorithm.

Other: Potassium estimation algorithm

Validation

A subset of patients that are "held back" and used to validate the algorithm's accuracy.

Other: Potassium estimation algorithm

Interventions

Potassium estimation algorithm OTHER

Apply a machine learning algorithm to estimate a patient's potassium.

Training; Validation

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Subjects admitted at Brigham and Women's Hospital and Brigham and Women's Faulkner Hospital who meet primary diagnosis, age, and residence within 5 mile requirements and are enrolled in home hospital.

Was a subject in the Brigham and Women's Home Hospital study and has a completed record in the study's database.

Contact the study team to discuss eligibility requirements. They can help determine if this study is right for you.

Sponsors & Collaborators

• Brigham and Women's Hospital: lead
• Biofourmis Inc.: collaborator

Study Sites (2)

Brigham and Women's Hospital

Boston, Massachusetts, 02115, United States

Location

Brigham and Women's Faulkner Hospital

Boston, Massachusetts, 02130, United States

Location

Related Publications (8)

• Yasin OZ, Attia Z, Dillon JJ, DeSimone CV, Sapir Y, Dugan J, Somers VK, Ackerman MJ, Asirvatham SJ, Scott CG, Bennet KE, Ladewig DJ, Sadot D, Geva AB, Friedman PA. Noninvasive blood potassium measurement using signal-processed, single-lead ecg acquired from a handheld smartphone. J Electrocardiol. 2017 Sep-Oct;50(5):620-625. doi: 10.1016/j.jelectrocard.2017.06.008. Epub 2017 Jun 8.

  PMID: 28641860 BACKGROUND

• Dillon JJ, DeSimone CV, Sapir Y, Somers VK, Dugan JL, Bruce CJ, Ackerman MJ, Asirvatham SJ, Striemer BL, Bukartyk J, Scott CG, Bennet KE, Mikell SB, Ladewig DJ, Gilles EJ, Geva A, Sadot D, Friedman PA. Noninvasive potassium determination using a mathematically processed ECG: proof of concept for a novel "blood-less, blood test". J Electrocardiol. 2015 Jan-Feb;48(1):12-8. doi: 10.1016/j.jelectrocard.2014.10.002. Epub 2014 Oct 18.

  PMID: 25453193 BACKGROUND

• Krogager ML, Kragholm K, Skals RK, Mortensen RN, Polcwiartek C, Graff C, Nielsen JB, Kanters JK, Holst AG, Sogaard P, Pietersen A, Torp-Pedersen C, Hansen SM. The relationship between serum potassium concentrations and electrocardiographic characteristics in 163,547 individuals from primary care. J Electrocardiol. 2019 Nov-Dec;57:104-111. doi: 10.1016/j.jelectrocard.2019.09.005. Epub 2019 Sep 4.

  PMID: 31629993 BACKGROUND

• Corsi C, Cortesi M, Callisesi G, De Bie J, Napolitano C, Santoro A, Mortara D, Severi S. Noninvasive quantification of blood potassium concentration from ECG in hemodialysis patients. Sci Rep. 2017 Feb 15;7:42492. doi: 10.1038/srep42492.

  PMID: 28198403 BACKGROUND

• Rafique Z, Aceves J, Espina I, Peacock F, Sheikh-Hamad D, Kuo D. Can physicians detect hyperkalemia based on the electrocardiogram? Am J Emerg Med. 2020 Jan;38(1):105-108. doi: 10.1016/j.ajem.2019.04.036. Epub 2019 Apr 22.

  PMID: 31047740 BACKGROUND

• Attia ZI, DeSimone CV, Dillon JJ, Sapir Y, Somers VK, Dugan JL, Bruce CJ, Ackerman MJ, Asirvatham SJ, Striemer BL, Bukartyk J, Scott CG, Bennet KE, Ladewig DJ, Gilles EJ, Sadot D, Geva AB, Friedman PA. Novel Bloodless Potassium Determination Using a Signal-Processed Single-Lead ECG. J Am Heart Assoc. 2016 Jan 25;5(1):e002746. doi: 10.1161/JAHA.115.002746.

  PMID: 26811164 BACKGROUND

• Galloway CD, Valys AV, Shreibati JB, Treiman DL, Petterson FL, Gundotra VP, Albert DE, Attia ZI, Carter RE, Asirvatham SJ, Ackerman MJ, Noseworthy PA, Dillon JJ, Friedman PA. Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram. JAMA Cardiol. 2019 May 1;4(5):428-436. doi: 10.1001/jamacardio.2019.0640.

  PMID: 30942845 BACKGROUND

• Lin CS, Lin C, Fang WH, Hsu CJ, Chen SJ, Huang KH, Lin WS, Tsai CS, Kuo CC, Chau T, Yang SJ, Lin SH. A Deep-Learning Algorithm (ECG12Net) for Detecting Hypokalemia and Hyperkalemia by Electrocardiography: Algorithm Development. JMIR Med Inform. 2020 Mar 5;8(3):e15931. doi: 10.2196/15931.

  PMID: 32134388 BACKGROUND

MeSH Terms

Conditions

Infections; Heart Failure; Pulmonary Disease, Chronic Obstructive; Asthma; Renal Insufficiency, Chronic; Hypertensive Crisis

Condition Hierarchy (Ancestors)

Heart Diseases; Cardiovascular Diseases; Lung Diseases, Obstructive; Lung Diseases; Respiratory Tract Diseases; Chronic Disease; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Bronchial Diseases; Respiratory Hypersensitivity; Hypersensitivity, Immediate; Hypersensitivity; Immune System Diseases; Renal Insufficiency; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Hypertension; Vascular Diseases

Study Officials

• David Levine, MD MPH MA

  Associate Physician

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Attending Physician

Study Record Dates

• First Submitted: April 14, 2021
• First Posted: March 25, 2026
• Study Start: March 20, 2021
• Primary Completion: August 1, 2021
• Study Completion: December 1, 2021
• Last Updated: March 25, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

US (2)