Nonlinear T-Wave Time Warping-Based Sensing Model for Non-Invasive Personalised Blood Potassium Monitoring in Hemodialysis Patients: A Pilot Study

Sensors

Alba Martín-Yebra¹  Juan Pablo Martínez¹  Pablo Laguna¹  Esther Pueyo¹  Flavio Palmieri²  Pedro Gomis²  Dina Ferreira³  José Esteban Ruiz⁴  Julia Ramírez⁵ 

[1] CIBER en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN), 50018 Zaragoza, Spain;Centre de Recerca en Enginyeria Biomèdica, Universitat Politècnica de Catalunya, 08028 Barcelona, Spain;Laboratorios Rubió, Castellbisbal, 08755 Barcelona, Spain;Nephrology Ward, Hospital Clínico Universitario Lozano Blesa, 50009 Zaragoza, Spain;William Harvey Research Institute, Queen Mary University of London, London E1 4NS, UK;

关键词: electrocardiogram;    periodic component analysis;    T-wave morphology;    time warping;    noninvasive potassium sensing;    personalised medicine;   

DOI  :  10.3390/s21082710

来源: DOAJ

【 摘 要 】

$\mathit{Background}:$ End-stage renal disease patients undergoing hemodialysis (ESRD-HD) therapy are highly susceptible to malignant ventricular arrhythmias caused by undetected potassium concentration ([$K^{+}$]) variations ($\Delta \left[K^{+}\right]$) out of normal ranges. Therefore, a reliable method for continuous, noninvasive monitoring of [$K^{+}$] is crucial. The morphology of the T-wave in the electrocardiogram (ECG) reflects $\Delta \left[K^{+}\right]$ and two time-warping-based T-wave morphological parameters, $d_w$ and its heart-rate corrected version $d_{w,c}$, have been shown to reliably track $\Delta \left[K^{+}\right]$ from the ECG. The aim of this study is to derive polynomial models relating $d_w$ and $d_{w,c}$ with $\Delta \left[K^{+}\right]$, and to test their ability to reliably sense and quantify $\Delta \left[K^{+}\right]$ values. $\mathit{Methods}:$ 48-hour Holter ECGs and [$K^{+}$] values from six blood samples were collected from 29 ESRD-HD patients. For every patient, $d_w$ and $d_{w,c}$ were computed, and linear, quadratic, and cubic fitting models were derived from them. Then, Spearman’s ($\rho$) and Pearson’s (r) correlation coefficients, and the estimation error ($e_d$) between $\Delta \left[K^{+}\right]$ and the corresponding model-estimated values ($\widehat{\Delta }\left[K^{+}\right]$) were calculated. $\mathit{Results\; and\; Discussions}:$ Nonlinear models were the most suitable for $\Delta \left[K^{+}\right]$ estimation, rendering higher Pearson’s correlation (median 0.77 $\le r\le$ 0.92) and smaller estimation error (median 0.20 $\le e_d\le$ 0.43) than the linear model (median 0.76 $\le r\le$ 0.86 and 0.30 $\le e_d\le$ 0.40), even if similar Spearman’s $\rho$ were found across models (median 0.77 $\le \rho \le$ 0.83). $\mathit{Conclusion}:$ Results support the use of nonlinear T-wave-based models as $\Delta \left[K^{+}\right]$ sensors in ESRD-HD patients.

【 授权许可】

Unknown