Monitoring of Serum Potassium and Calcium Levels in End-Stage Renal Disease Patients by ECG Depolarization Morphology Analysis

Abstract

Objective: Non-invasive estimation of serum potassium, [K+], and calcium, [Ca2+], can help to prevent life-threatening ventricular arrhythmias in patients with advanced renal disease, but current methods for estimation of electrolyte levels have limitations. We aimed to develop new markers based on the morphology of the QRS complex of the electrocardiogram (ECG). Methods: ECG recordings from 29 patients undergoing hemodialysis (HD) were processed. Mean warped QRS complexes were computed in two-minute windows at the start of an HD session, at the end of each HD hour and 48 h after it. We quantified QRS width, amplitude and the proposed QRS morphology-based markers that were computed by warping techniques. Reference [K+] and [Ca2+] were determined from blood samples acquired at the time points where the markers were estimated. Linear regression models were used to estimate electrolyte levels from the QRS markers individually and in combination with T wave morphology markers. Leave-one-out cross-validation was used to assess the performance of the estimators. Results: All markers, except for QRS width, strongly correlated with [K+] (median Pearson correlation coefficients, r, ranging from 0.81 to 0.87) and with [Ca2+] (r ranging from 0.61 to 0.76). QRS morphology markers showed very low sensitivity to heart rate (HR). Actual and estimated serum electrolyte levels differed, on average, by less than 0.035 mM (relative error of 0.018) for [K+] and 0.010 mM (relative error of 0.004) for [Ca2+] when patient-specific multivariable estimators combining QRS and T wave markers were used. Conclusion: QRS morphological markers allow non-invasive estimation of [K+] and [Ca2+] with low sensitivity to HR. The estimation performance is improved when multivariable models, including T wave markers, are considered. Significance: Markers based on the QRS complex of the ECG could contribute to non-invasive monitoring of serum electrolyte levels and arrhythmia risk prediction in patients with renal disease.

Development and validation of a dynamic deep learning algorithm using electrocardiogram to predict dyskalaemias in patients with multiple visits

“…Other study that combined T wave and QRS morphology markers using machine learning method to predict K + values has an MAE improvement (0.539) compared with only using T wave (0.631). 27 Our method had an MAE improvement (0.363/0.366) compared with the direct use of DLM (0.410/0.407) for follow-up ECGs in the internal/external validation set. Although an improvement in MAE of ∼0.1 for K + values may have limited clinical impact, dynamic revision method empowers DLM-enabled ECGs as a more accurate non-invasively tool for K + monitoring.…”

Differences in ventricular wall composition may explain inter-patient variability in the ECG response to variations in serum potassium and calcium

“…The study population included 29 ESRD patients from Hospital Clínico Universitario de Zaragoza, Spain, from which 48-h 12-lead ECGs were acquired (see Supplementary Table S1 in the Supplementary Material with [K + ], [Ca 2+ ] and RR values in the patients). T waves (QRS complexes, respectively) in the first PC were obtained and delineated to compute the below described markers ( Palmieri et al, 2021a ; Bukhari et al, 2022a ; Bukhari et al, 2022b ).…”

“…Morphology-based T wave and QRS complex markers were computed using the time-warping methodology described previously ( Ramírez et al, 2017 ; Bukhari et al, 2022a ). For each model in the population, reference T waves and QRS complexes were calculated from the last beat of the PC-transformed ECG at minimum [K + ] (3 mM) and maximum [Ca 2+ ] (3.2 mM).…”

“…We considered the reference for the simulated T wave (or QRS complex) in the same way as considered for the ESRD patients so as to perform the comparison on a similar basis. In the patients, the reference was computed at the end of the HD session when [K + ] was minimum, closer to 3 mM, and [Ca 2+ ] was maximum, closer to 3.2 mM, as this is the time when the patient was discharged from hospital with restored serum ion levels, thus being an acceptable reference for ambulatory monitoring ( Bukhari et al, 2021 ; Bukhari et al, 2022a ; Bukhari et al, 2022b ).…”

“…Other studies have investigated model-based markers of T wave morphology ( Rodrigues et al, 2020 ), sympathetic activity-related T wave instability during HD ( Schüttler et al, 2021 ) and descriptors of the sine wave shape, amplitude and time voltage area of the QRS complex ( Ojanen et al, 1999 ; An et al, 2012 ; Curione et al, 2013 ; Pilia et al, 2020 ). To characterize overall variations in the morphology of the QRS complex and the T wave, in previous studies we have developed [K + ] and [Ca 2+ ] estimators using non-linear dynamics and time-warping techniques and we have evaluated them during and after HD in ESRD patients ( Bukhari et al, 2019 ; Srinivasan et al, 2020 ; Palmieri et al, 2021a ; Palmieri et al, 2021b ; Bukhari et al, 2021 ; Bukhari et al, 2022a ; Bukhari et al, 2022b ).…”