Novel bloodless potassium determination using a signal-processed single-lead ECG

Zachi I. Attia, Christopher V. DeSimone, John J. Dillon, Yehu Sapir, Virend Somers, Jennifer L. Dugan, Charles J Bruce, Michael John Ackerman, Samuel J Asirvatham, Bryan L. Striemer, Jan Bukartyk, Christopher G. Scott, Kevin E. Bennet, Dorothy J. Ladewig, Emily J. Gilles, Dan Sadot, Amir B. Geva, Paul Andrew Friedman

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Background-Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. Methods and Results-Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent highresolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassiumvalues during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data,we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10% of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11% of the measured blood potassium) and 0.5±0.42 for the validation set (or 12% of the measured blood potassium). Conclusions-The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.

Original languageEnglish (US)
Article numbere002746
JournalJournal of the American Heart Association
Volume5
Issue number1
DOIs
StatePublished - 2016

Fingerprint

Potassium
Electrocardiography
Hematologic Tests
Dialysis
Lead
Hyperkalemia
Hypokalemia
Renal Dialysis
Heart Diseases
Kidney
Costs and Cost Analysis

Keywords

  • Electrophysiology
  • Potassium
  • Waves

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine

Cite this

Novel bloodless potassium determination using a signal-processed single-lead ECG. / Attia, Zachi I.; DeSimone, Christopher V.; Dillon, John J.; Sapir, Yehu; Somers, Virend; Dugan, Jennifer L.; Bruce, Charles J; Ackerman, Michael John; Asirvatham, Samuel J; Striemer, Bryan L.; Bukartyk, Jan; Scott, Christopher G.; Bennet, Kevin E.; Ladewig, Dorothy J.; Gilles, Emily J.; Sadot, Dan; Geva, Amir B.; Friedman, Paul Andrew.

In: Journal of the American Heart Association, Vol. 5, No. 1, e002746, 2016.

Research output: Contribution to journalArticle

Attia, ZI, DeSimone, CV, Dillon, JJ, Sapir, Y, Somers, V, 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 2016, 'Novel bloodless potassium determination using a signal-processed single-lead ECG', Journal of the American Heart Association, vol. 5, no. 1, e002746. https://doi.org/10.1161/JAHA.115.002746
Attia, Zachi I. ; DeSimone, Christopher V. ; Dillon, John J. ; Sapir, Yehu ; Somers, Virend ; Dugan, Jennifer L. ; Bruce, Charles J ; Ackerman, Michael John ; Asirvatham, Samuel J ; Striemer, Bryan L. ; Bukartyk, Jan ; Scott, Christopher G. ; Bennet, Kevin E. ; Ladewig, Dorothy J. ; Gilles, Emily J. ; Sadot, Dan ; Geva, Amir B. ; Friedman, Paul Andrew. / Novel bloodless potassium determination using a signal-processed single-lead ECG. In: Journal of the American Heart Association. 2016 ; Vol. 5, No. 1.
@article{2d830a90f1374c9bbb03ecdefaf97de0,
title = "Novel bloodless potassium determination using a signal-processed single-lead ECG",
abstract = "Background-Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. Methods and Results-Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent highresolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassiumvalues during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data,we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10{\%} of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11{\%} of the measured blood potassium) and 0.5±0.42 for the validation set (or 12{\%} of the measured blood potassium). Conclusions-The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.",
keywords = "Electrophysiology, Potassium, Waves",
author = "Attia, {Zachi I.} and DeSimone, {Christopher V.} and Dillon, {John J.} and Yehu Sapir and Virend Somers and Dugan, {Jennifer L.} and Bruce, {Charles J} and Ackerman, {Michael John} and Asirvatham, {Samuel J} and Striemer, {Bryan L.} and Jan Bukartyk and Scott, {Christopher G.} and Bennet, {Kevin E.} and Ladewig, {Dorothy J.} and Gilles, {Emily J.} and Dan Sadot and Geva, {Amir B.} and Friedman, {Paul Andrew}",
year = "2016",
doi = "10.1161/JAHA.115.002746",
language = "English (US)",
volume = "5",
journal = "Journal of the American Heart Association",
issn = "2047-9980",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Novel bloodless potassium determination using a signal-processed single-lead ECG

AU - Attia, Zachi I.

AU - DeSimone, Christopher V.

AU - Dillon, John J.

AU - Sapir, Yehu

AU - Somers, Virend

AU - Dugan, Jennifer L.

AU - Bruce, Charles J

AU - Ackerman, Michael John

AU - Asirvatham, Samuel J

AU - Striemer, Bryan L.

AU - Bukartyk, Jan

AU - Scott, Christopher G.

AU - Bennet, Kevin E.

AU - Ladewig, Dorothy J.

AU - Gilles, Emily J.

AU - Sadot, Dan

AU - Geva, Amir B.

AU - Friedman, Paul Andrew

PY - 2016

Y1 - 2016

N2 - Background-Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. Methods and Results-Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent highresolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassiumvalues during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data,we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10% of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11% of the measured blood potassium) and 0.5±0.42 for the validation set (or 12% of the measured blood potassium). Conclusions-The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.

AB - Background-Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. Methods and Results-Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent highresolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassiumvalues during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data,we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10% of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11% of the measured blood potassium) and 0.5±0.42 for the validation set (or 12% of the measured blood potassium). Conclusions-The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.

KW - Electrophysiology

KW - Potassium

KW - Waves

UR - http://www.scopus.com/inward/record.url?scp=84997787387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84997787387&partnerID=8YFLogxK

U2 - 10.1161/JAHA.115.002746

DO - 10.1161/JAHA.115.002746

M3 - Article

C2 - 26811164

AN - SCOPUS:84997787387

VL - 5

JO - Journal of the American Heart Association

JF - Journal of the American Heart Association

SN - 2047-9980

IS - 1

M1 - e002746

ER -