Noninvasive quantification of blood potassium concentration from ECG in hemodialysis patients

Validation of Noninvasive Detection of Hyperkalemia by Artificial Intelligence-Enhanced Electrocardiography in High Acuity Settings

Background

Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings.

Methods

An emergency department (ED) cohort (February to August 2021) and a mixed intensive care unit (ICU) cohort (August 2017 to February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within 4 hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads 1 and 2 of the 12 lead ECGs to screen for hyperkalemia (potassium >6.0 mEq/L).

Results

The ED cohort (N=40,128) had a mean age of 60 years, 48% were male, and 1% (N=351) had hyperkalemia. The area under the curve (AUC) of the AI-enhanced ECG (AI-ECG) to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive likelihood ratio (LR+) of 80%, 80%, 3%, 99.8%, and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.83, 86%, 60%, 15%, 98%, and 2.2, respectively, in the ED cohort. The ICU cohort (N=2636) had a mean age of 65 years, 60% were male, and 3% (N=87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, PPV, NPV, and LR+ of 82%, 82%, 14%, 99%, and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.85, 88%, 67%, 29%, 97%, and 2.7, respectively in the ICU cohort.

Conclusions

The AI-ECG algorithm demonstrated a high NPV, suggesting that it is useful for ruling out hyperkalemia, but a low PPV, suggesting that it is insufficient for treating hyperkalemia.

Evaluating regression and probabilistic methods for ECG-based electrolyte prediction

Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binary classification of extreme concentration levels. Finally, we investigate probabilistic regression approaches and explore uncertainty estimates for enhanced clinical usefulness. Our results show that DNNs outperform traditional models but model performance varies significantly across different electrolytes. While discretization leads to good classification performance, it does not address the original problem of continuous concentration level prediction. Probabilistic regression has practical potential, but our uncertainty estimates are not perfectly calibrated. Our study is therefore a first step towards developing an accurate and reliable ECG-based method for electrolyte concentration level prediction-a method with high potential impact within multiple clinical scenarios.

Artificial intelligence-based model for automatic real-time and noninvasive estimation of blood potassium levels in pediatric patients

Background

An abnormal variation in blood electrolytes, such as potassium, contributes to mortality in children admitted to intensive care units. Continuous and real-time monitoring of potassium serum levels can prevent fatal arrhythmias, but this is not currently practical. The study aims to use machine learning to estimate blood potassium levels with accuracy in real time noninvasively.

Methods

Hospitalized patients in the Pediatric Department of the Rajaie Cardiology and Medical Research Center and Tehran Heart Center were recruited from December 2021 to June 2022. The electrocardiographic (ECG) features of patients were evaluated. We defined 16 features for each signal and extracted them automatically. The dimension reduction operation was performed with the assistance of the correlation matrix. Linear regression, polynomials, decision trees, random forests, and support vector machine algorithms have been used to find the relationship between characteristics and serum potassium levels. Finally, we used a scatter plot and mean square error (MSE) to display the results.

Results

Of 463 patients (mean age: 8 ± 1 year; 56% boys) hospitalized, 428 patients met the inclusion criteria, with 35 patients having a high noise of ECG were excluded. After the dimension reduction step, 11 features were selected from each cardiac signal. The random forest regression algorithm showed the best performance with an MSE of 0.3.

Conclusion

The accurate estimation of serum potassium levels based on ECG signals is possible using machine learning algorithms. This can be potentially useful in predicting serum potassium levels in specific clinical scenarios.

Multifunctional Siloxene-Decorated Laser-Inscribed Graphene Patch for Sweat Ion Analysis and Electrocardiogram Monitoring

Potentiometric detection in complex biological fluids enables continuous electrolyte monitoring for personal healthcare; however, the commercialization of ion-selective electrode-based devices has been limited by the rapid loss of potential stability caused by electrode surface inactivation and biofouling. Here, we describe a simple multifunctional hybrid patch incorporating an Au nanoparticle/siloxene-based solid contact (SC) supported by a substrate made of laser-inscribed graphene on poly(dimethylsiloxane) for the noninvasive detection of sweat Na+ and K+. These SC nanocomposites prevent the formation of a water layer during ion-to-electron transfer, preserving 3 and 5 μV/h potential drift for the Na+ and K+ ion-selective electrodes, respectively, after 13 h of exposure. The lamellar structure of the siloxene sheets increases the SC area. In addition, the electroplated Au nanoparticles, which have a large surface area and excellent conductivity, further increased the electric double-layer capacitance at the interface between the ion-selective membranes and solid-state contacts, thus facilitating ion-to-electron transduction and ultimately improving the detection stability of Na+ and K+. Furthermore, the integrated temperature and electrocardiogram sensors in the flexible patch assist in monitoring body temperature and electrocardiogram signals, respectively. Featuring both electrochemical ion-selective and physical sensors, this patch offers immense potential for the self-monitoring of health.

Hyperkalemia Detection in Emergency Departments Using Initial ECGs: A Smartphone AI ECG Analyzer vs. Board-Certified Physicians

BACKGROUND

Hyperkalemia is a potentially fatal condition that mandates rapid identification in emergency departments (EDs). Although a 12-lead electrocardiogram (ECG) can indicate hyperkalemia, subtle changes in the ECG often pose detection challenges. An artificial intelligence application that accurately assesses hyperkalemia risk from ECGs could revolutionize patient screening and treatment. We aimed to evaluate the efficacy and reliability of a smartphone application, which utilizes camera-captured ECG images, in quantifying hyperkalemia risk compared to human experts.

METHODS

We performed a retrospective analysis of ED hyperkalemic patients (serum potassium ≥ 6 mmol/L) and their age- and sex-matched non-hyperkalemic controls. The application was tested by five users and its performance was compared to five board-certified emergency physicians (EPs).

RESULTS

Our study included 125 patients. The area under the curve (AUC)-receiver operating characteristic of the application's output was nearly identical among the users, ranging from 0.898 to 0.904 (median: 0.902), indicating almost perfect interrater agreement (Fleiss' kappa 0.948). The application demonstrated high sensitivity (0.797), specificity (0.934), negative predictive value (NPV) (0.815), and positive predictive value (PPV) (0.927). In contrast, the EPs showed moderate interrater agreement (Fleiss' kappa 0.551), and their consensus score had a significantly lower AUC of 0.662. The physicians' consensus demonstrated a sensitivity of 0.203, specificity of 0.934, NPV of 0.527, and PPV of 0.765. Notably, this performance difference remained significant regardless of patients' sex and age (P < 0.001 for both).

CONCLUSION

Our findings suggest that a smartphone application can accurately and reliably quantify hyperkalemia risk using initial ECGs in the ED.

Comparison of quantifiable electrocardiographic changes associated with severe hyperkalemia

BACKGROUND

Hyperkalemia (HK) is a life-threatening condition that is frequently evaluated by electrocardiogram (ECG). ECG changes in severe HK (≥ 6.3 mEq/L) are not well-characterized. This study sought to compare and correlate ECG metrics in severe HK to baseline normokalemic ECGs and serum potassium.

METHODS

A retrospective analysis of 340 severe HK encounters with corresponding normokalemic ECGs was performed.

RESULTS

Various ECG metrics were analyzed. P wave amplitude in lead II, QRS duration, T wave slope, ratio of T wave amplitude: duration, and ratios of T wave: QRS amplitudes were significantly different between normokalemic and HK ECGs. P wave amplitude attenuation in lead II correlated better with serum potassium than in V1. T wave metrics that incorporated both T wave and QRS amplitudes correlated better than metrics utilizing T wave metrics alone.

CONCLUSION

Multiple statistically significant and quantifiable differences among ECG metrics were observed between normokalemic and HK ECGs and correlated with increasing degrees of serum potassium and along the continuum of serum potassium. When incorporated into a logistic regression model, the ability to distinguish HK versus normokalemia on ECG improved significantly. These findings could be integrated into an ECG acquisition system that can more accurately identify severe HK.

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

Objective: Chronic kidney disease patients have a decreased ability to maintain normal electrolyte concentrations in their blood, which increases the risk for ventricular arrhythmias and sudden cardiac death. Non-invasive monitoring of serum potassium and calcium concentration, [K+] and [Ca2+], can help to prevent arrhythmias in these patients. Electrocardiogram (ECG) markers that significantly correlate with [K+] and [Ca2+] have been proposed, but these relations are highly variable between patients. We hypothesized that inter-individual differences in cell type distribution across the ventricular wall can help to explain this variability. Methods: A population of human heart-torso models were built with different proportions of endocardial, midmyocardial and epicardial cells. Propagation of ventricular electrical activity was described by a reaction-diffusion model, with modified Ten Tusscher-Panfilov dynamics. [K+] and [Ca2+] were varied individually and in combination. Twelve-lead ECGs were simulated and the width, amplitude and morphological variability of T waves and QRS complexes were quantified. Results were compared to measurements from 29 end-stage renal disease (ESRD) patients undergoing hemodialysis (HD). Results: Both simulations and patients data showed that most of the analyzed T wave and QRS complex markers correlated strongly with [K+] (absolute median Pearson correlation coefficients, r, ranging from 0.68 to 0.98) and [Ca2+] (ranging from 0.70 to 0.98). The same sign and similar magnitude of median r was observed in the simulations and the patients. Different cell type distributions in the ventricular wall led to variability in ECG markers that was accentuated at high [K+] and low [Ca2+], in agreement with the larger variability between patients measured at the onset of HD. The simulated ECG variability explained part of the measured inter-patient variability. Conclusion: Changes in ECG markers were similarly related to [K+] and [Ca2+] variations in our models and in the ESRD patients. The high inter-patient ECG variability may be explained by variations in cell type distribution across the ventricular wall, with high sensitivity to variations in the proportion of epicardial cells. Significance: Differences in ventricular wall composition help to explain inter-patient variability in ECG response to [K+] and [Ca2+]. This finding can be used to improve serum electrolyte monitoring in ESRD patients.

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

Aims

Deep learning models (DLMs) have shown superiority in electrocardiogram (ECG) analysis and have been applied to diagnose dyskalaemias. However, no study has explored the performance of DLM-enabled ECG in continuous follow-up scenarios. Therefore, we proposed a dynamic revision of DLM-enabled ECG to use personal pre-annotated ECGs to enhance the accuracy in patients with multiple visits.

Methods and results

We retrospectively collected 168 450 ECGs with corresponding serum potassium (K⁺) levels from 103 091 patients as development samples. In the internal/external validation sets, the numbers of ECGs with corresponding K⁺ were 37 246/47 604 from 13 555/20 058 patients. Our dynamic revision method showed better performance than the traditional direct prediction for diagnosing hypokalaemia [area under the receiver operating characteristic curve (AUC) = 0.730/0.720-0.788/0.778] and hyperkalaemia (AUC = 0.884/0.888-0.915/0.908) in patients with multiple visits.

Conclusion

Our method has shown a distinguishable improvement in DLMs for diagnosing dyskalaemias in patients with multiple visits, and we also proved its application in ejection fraction prediction, which could further improve daily clinical practice.

Point-of-care and self-testing for potassium: recent advances

Potassium is an important bodily electrolyte which is kept within tight limits in health. Many medical conditions as well as commonly-used drugs either raise or lower blood potassium levels, which can be dangerous or even fatal. For at-risk patients, frequent monitoring of potassium can improve safety and lifestyle, but conventional venous blood draws are inconvenient, don't provide a timely result and may be inaccurate. This review summarises current solutions and recent developments in point-of-care and self-testing potassium measurement technologies, which include devices for measurement of potassium in venous blood, devices for home blood collection and remote measurement, devices for rapid home measurement of potassium, wearable sensors for potassium in interstitial fluid, in sweat, in urine, as well as non-invasive potassium detection. We discuss the practical and clinical applicability of these technologies and provide future outlooks.

ECG frequency changes in potassium disorders: a narrative review

Nowadays, electrocardiogram (ECG) changes are one of the valuable diagnostic clues for recognizing abnormalities. Potassium is one of the essential electrolytes in cardiac cells, and its variations affect ECG. Potassium disorders, including hyperkalemia and hypokalemia in authoritarian states, may lead to heart dysfunctions and could be life-threatening, and urgent interventions are needed in this conditions. The current review summarizes studies to elucidate the correlation between potassium disorders and ECG demonstrations. In this review, we summarized ECG changes related to hyperkalemia and interventions. Moreover; animal studies on ECG changes related to hyper- and hypokalemia are provided. The studies showed peaked T wave, as well as expanded QRS complex and low P amplitude, are important changes that can guide us to immediate diagnosis. ECG Changes in severe hyperkalemia that can endanger patients' lives are noteworthy. Manifestations change in hyperkalemia, for correct diagnosis clinical history of the patients is essential.

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

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.

Estimation of potassium levels in hemodialysis patients by T wave nonlinear dynamics and morphology markers

OBJECTIVE

Noninvasive screening of hypo- and hyperkalemia can prevent fatal arrhythmia in end-stage renal disease (ESRD) patients, but current methods for monitoring of serum potassium (K+) have important limitations. We investigated changes in nonlinear dynamics and morphology of the T wave in the electrocardiogram (ECG) of ESRD patients during hemodialysis (HD), assessing their relationship with K+ and designing a K+ estimator.

METHODS

ECG recordings from twenty-nine ESRD patients undergoing HD were processed. T waves in 2-min windows were extracted at each hour during an HD session as well as at 48 h after HD start. T wave nonlinear dynamics were characterized by two indices related to the maximum Lyapunov exponent (λt, λwt) and a divergence-related index (η). Morphological variability in the T wave was evaluated by three time warping-based indices (dw, reflecting morphological variability in the time domain, and da and daNL, in the amplitude domain). K+was measured from blood samples extracted during and after HD. Stage-specific and patient-specific K+ estimators were built based on the quantified indices and leave-one-out cross-validation was performed separately for each of the estimators.

RESULTS

The analyzed indices showed high inter-individual variability in their relationship with K+. Nevertheless, all of them had higher values at the HD start and 48 h after it, corresponding to the highest K+. The indices η and dw were the most strongly correlated with K+ (median Pearson correlation coefficient of 0.78 and 0.83, respectively) and were used in univariable and multivariable linear K+ estimators. Agreement between actual and estimated K+ was confirmed, with averaged errors over patients and time points being 0.000 ± 0.875 mM and 0.046 ± 0.690 mM for stage-specific and patient-specific multivariable K+ estimators, respectively.

CONCLUSION

ECG descriptors of T wave nonlinear dynamics and morphological variability allow noninvasive monitoring of K+ in ESRD patients.

SIGNIFICANCE

ECG markers have the potential to be used for hypo- and hyperkalemia screening in ESRD patients.

Electrocardiogram-based index for the assessment of drug-induced hERG potassium channel block

INTRODUCTION

Drug-induced block of the hERG potassium channel could predispose to torsade de pointes, depending on occurrence of concomitant blocks of the calcium and/or sodium channels. Since the hERG potassium channel block affects cardiac repolarization, the aim of this study was to propose a new reliable index for non-invasive assessment of drug-induced hERG potassium channel block based on electrocardiographic T-wave features.

METHODS

ERD_30% (early repolarization duration) and T_S/A (down-going T-wave slope to T-wave amplitude ratio) features were measured in 22 healthy subjects who received, in different days, doses of dofetilide, ranolazine, verapamil and quinidine (all being hERG potassium channel blockers and the latter three being also blockers of calcium and/or sodium channels) while undergoing continuous electrocardiographic acquisition from which ERD_30% and T_S/A were evaluated in fifteen time points during the 24 h following drug administration ("ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects" database by Physionet). A total of 1320 pairs of ERD_30% and T_S/A measurements, divided in training (50%) and testing (50%) datasets, were obtained. Drug-induced hERG potassium channel block was modelled by the regression equation B_ECG(%) = a·ERD_30% + b·T_S/A+ c·ERD_30%·T_S/A + d; B_ECG(%) values were compared to plasma-based measurements, B_REF(%).

RESULTS

Regression coefficients values, obtained on the training dataset, were: a = -561.0 s^-1, b = -9.7 s, c = 77.2 and d = 138.9. In the testing dataset, correlation coefficient between B_ECG(%) and B_REF(%) was 0.67 (p < 10^-81); estimation error was -11.5 ± 16.7%.

CONCLUSION

B_ECG(%) is a reliable non-invasive index for the assessment of drug-induced hERG potassium channel block, independently from concomitant blocks of other ions.

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

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 (Δ[K+]) 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 Δ[K+] and two time-warping-based T-wave morphological parameters, dw and its heart-rate corrected version dw,c, have been shown to reliably track Δ[K+] from the ECG. The aim of this study is to derive polynomial models relating dw and dw,c with Δ[K+], and to test their ability to reliably sense and quantify Δ[K+] values. Methods: 48-hour Holter ECGs and [K+] values from six blood samples were collected from 29 ESRD-HD patients. For every patient, dw and dw,c were computed, and linear, quadratic, and cubic fitting models were derived from them. Then, Spearman’s (ρ) and Pearson’s (r) correlation coefficients, and the estimation error (ed) between Δ[K+] and the corresponding model-estimated values (Δ^[K+]) were calculated. Results and Discussions: Nonlinear models were the most suitable for Δ[K+] estimation, rendering higher Pearson’s correlation (median 0.77 ≤r≤ 0.92) and smaller estimation error (median 0.20 ≤ed≤ 0.43) than the linear model (median 0.76 ≤r≤ 0.86 and 0.30 ≤ed≤ 0.40), even if similar Spearman’s ρ were found across models (median 0.77 ≤ρ≤ 0.83). Conclusion: Results support the use of nonlinear T-wave-based models as Δ[K+] sensors in ESRD-HD patients.

Monitoring blood potassium concentration in hemodialysis patients by quantifying T-wave morphology dynamics

We investigated the ability of time-warping-based ECG-derived markers of T-wave morphology changes in time ([Formula: see text]) and amplitude ([Formula: see text]), as well as their non-linear components ([Formula: see text] and [Formula: see text]), and the heart rate corrected counterpart ([Formula: see text]), to monitor potassium concentration ([Formula: see text]) changes ([Formula: see text]) in end-stage renal disease (ESRD) patients undergoing hemodialysis (HD). We compared the performance of the proposed time-warping markers, together with other previously proposed [Formula: see text] markers, such as T-wave width ([Formula: see text]) and T-wave slope-to-amplitude ratio ([Formula: see text]), when computed from standard ECG leads as well as from principal component analysis (PCA)-based leads. 48-hour ECG recordings and a set of hourly-collected blood samples from 29 ESRD-HD patients were acquired. Values of [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text] and [Formula: see text] were calculated by comparing the morphology of the mean warped T-waves (MWTWs) derived at each hour along the HD with that from a reference MWTW, measured at the end of the HD. From the same MWTWs [Formula: see text] and [Formula: see text] were also extracted. Similarly, [Formula: see text] was calculated as the difference between the [Formula: see text] values at each hour and the [Formula: see text] reference level at the end of the HD session. We found that [Formula: see text] and [Formula: see text] showed higher correlation coefficients with [Formula: see text] than [Formula: see text]-Spearman's ([Formula: see text]) and Pearson's (r)-and [Formula: see text]-Spearman's ([Formula: see text])-in both SL and PCA approaches being the intra-patient median [Formula: see text] and [Formula: see text] in SL and [Formula: see text] and [Formula: see text] in PCA respectively. Our findings would point at [Formula: see text] and [Formula: see text] as the most suitable surrogate of [Formula: see text], suggesting that they could be potentially useful for non-invasive monitoring of ESRD-HD patients in hospital, as well as in ambulatory settings. Therefore, the tracking of T-wave morphology variations by means of time-warping analysis could improve continuous and remote [Formula: see text] monitoring of ESRD-HD patients and flagging risk of [Formula: see text]-related cardiovascular events.

Characterization of T Wave Amplitude, Duration and Morphology Changes During Hemodialysis: Relationship With Serum Electrolyte Levels and Heart Rate

OBJECTIVE

Chronic kidney disease affects more than 10% of the world population. Changes in serum ion concentrations increase the risk for ventricular arrhythmias and sudden cardiac death, particularly in end-stage renal disease (ESRD) patients. We characterized how T wave amplitude, duration and morphology descriptors change with variations in serum levels of potassium and calcium and in heart rate, both in ESRD patients and in simulated ventricular fibers.

METHODS

Electrocardiogram (ECG) recordings from twenty ESRD patients undergoing hemodialysis (HD) and pseudo-ECGs (pECGs) calculated from twenty-two simulated ventricular fibers at varying transmural heterogeneity levels were processed to quantify T wave width ( T_w), T wave slope-to-amplitude ratio ([Formula: see text]) and four indices of T wave morphological variability based on time warping ( d_w, [Formula: see text], d_a and [Formula: see text]). Serum potassium and calcium levels and heart rate were measured along HD.

RESULTS

[Formula: see text] was the marker most strongly correlated with serum potassium, dw with calcium and da with heart rate, after correction for covariates. Median values of partial correlation coefficients were 0.75, -0.74 and -0.90, respectively. For all analyzed T wave descriptors, high inter-patient variability was observed in the pattern of such relationships. This variability, accentuated during the first HD time points, was reproduced in the simulations and shown to be influenced by differences in transmural heterogeneity.

CONCLUSION

Changes in serum potassium and calcium levels and in heart rate strongly affect T wave descriptors, particularly those quantifying morphological variability.

SIGNIFICANCE

ECG markers have the potential to be used for monitoring serum ion concentrations in ESRD patients.

Quantification and classification of potassium and calcium disorders with the electrocardiogram: What do clinical studies, modeling, and reconstruction tell us?

Diseases caused by alterations of ionic concentrations are frequently observed challenges and play an important role in clinical practice. The clinically established method for the diagnosis of electrolyte concentration imbalance is blood tests. A rapid and non-invasive point-of-care method is yet needed. The electrocardiogram (ECG) could meet this need and becomes an established diagnostic tool allowing home monitoring of the electrolyte concentration also by wearable devices. In this review, we present the current state of potassium and calcium concentration monitoring using the ECG and summarize results from previous work. Selected clinical studies are presented, supporting or questioning the use of the ECG for the monitoring of electrolyte concentration imbalances. Differences in the findings from automatic monitoring studies are discussed, and current studies utilizing machine learning are presented demonstrating the potential of the deep learning approach. Furthermore, we demonstrate the potential of computational modeling approaches to gain insight into the mechanisms of relevant clinical findings and as a tool to obtain synthetic data for methodical improvements in monitoring approaches.

ECG-based Estimation of Potassium and Calcium Concentrations: Proof of Concept with Simulated Data

In Europe, the prevalence of chronic kidney disease lay at approximately 18.38% in 2016. A common treatment for patients in the end stage of this disease is haemodialysis. However, patients undergoing this therapy suffer from an increased risk of cardiac death. A hypothesis is that the cause is an inbalanced electrolyte concentration. To study the underlying mechanisms of this phenomenon and fight the consequences, a continous non-invasive monitoring technique is desired. In this work, we investigated the possibility to reconstruct the extracellular concentrations of potassium and calcium from ECG signals. Therefore, we extracted 71 ECGs using the simulation results of a modified Himeno et al. ventricular cell model comprising variations of the extracellular ionic concentrations of potassium and calcium. The changes dependent on the different extracellular ionic concentrations were captured with five ECG features. These were used to train an artificial neural network for regression. The study was performed both for noise-free and noisy data. The estimation error for the reconstruction of the potassium concentrations was -0.01±0.14mmol/l (mean±standard deviation) in the noise-free case, -0.03±0.46mmol/l in the noisy case (30dB SNR). For calcium, the result was 0.01±0.11mmol/l in the noise-free case, 0.02±0.17mmol/l in the noisy case. For both ion types, the result was improved by augmenting the dataset. We therefore conclude that with the calculated features, we are able to reconstruct the extracellular ionic concentrations for both potassium and calcium with an acceptable precision. When analysing noisy signals, the accuracy of the estimation method is still sufficient but can be further improved by an augmentation of the dataset.

Electrocardiographic T wave alterations and prediction of hyperkalemia in patients with acute kidney injury

Electrocardiographic (ECG) alterations are common in hyperkalemic patients. While the presence of peaked T waves is the most frequent ECG alteration, reported findings on ECG sensitivity in detecting hyperkalemia are conflicting. Moreover, no studies have been conducted specifically in patients with acute kidney injury (AKI). We used the best subset selection and cross-validation methods [via linear and logistic regression and leave-one-out cross-validation (LOOCV)] to assess the ability of T waves to predict serum potassium levels or hyperkalemia (defined as serum potassium ≥ 5.5 mEq/L). We included the following clinical variables as a candidate for the predictive models: peaked T waves, T wave maximum amplitude, T wave/R wave maximum amplitude ratio, age, and indicator variates for oliguria, use of ACE-inhibitors, sartans, mineralocorticoid receptor antagonists, and loop diuretics. Peaked T waves poorly predicted the serum potassium levels in both full and test sample (R² = 0.03 and R² = 0.01, respectively), and also poorly predicted hyperkalemia. The selection algorithm based on Bayesian information criterion identified T wave amplitude and use of loop diuretics as the best subset of variables predicting serum potassium. Nonetheless, the model accuracy was poor in both full and test sample [root mean square error (RMSE) = 0.96 mEq/L and adjR² = 0.08 and RMSE = 0.97 mEq/L, adjR² = 0.06, respectively]. T wave amplitude and the use of loop diuretics had also poor accuracy in predicting hyperkalemia in both full and test sample [area-under-curve (AUC) at receiver-operator curve (ROC) analysis 0.74 and AUC 0.72, respectively]. Our findings show that, in patients with AKI, electrocardiographic changes in T waves are poor predictors of serum potassium levels and of the presence of hyperkalemia.

A Deep-Learning Algorithm (ECG12Net) for Detecting Hypokalemia and Hyperkalemia by Electrocardiography: Algorithm Development

Background

The detection of dyskalemias—hypokalemia and hyperkalemia—currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results.

Objective

Our study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model.

Methods

Spanning from May 2011 to December 2016, 66,321 ECG records with corresponding serum potassium (K⁺) concentrations were obtained from 40,180 patients admitted to the emergency department. ECG12Net is an 82-layer convolutional neural network that estimates serum K⁺ concentration. Six clinicians—three emergency physicians and three cardiologists—participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians.

Results

In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively.

Conclusions

A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.

Hypocalcemia-Induced Slowing of Human Sinus Node Pacemaking

Each heartbeat is initiated by cyclic spontaneous depolarization of cardiomyocytes in the sinus node forming the primary natural pacemaker. In patients with end-stage renal disease undergoing hemodialysis, it was recently shown that the heart rate drops to very low values before they suffer from sudden cardiac death with an unexplained high incidence. We hypothesize that the electrolyte changes commonly occurring in these patients affect sinus node beating rate and could be responsible for severe bradycardia. To test this hypothesis, we extended the Fabbri et al. computational model of human sinus node cells to account for the dynamic intracellular balance of ion concentrations. Using this model, we systematically tested the effect of altered extracellular potassium, calcium, and sodium concentrations. Although sodium changes had negligible (0.15 bpm/mM) and potassium changes mild effects (8 bpm/mM), calcium changes markedly affected the beating rate (46 bpm/mM ionized calcium without autonomic control). This pronounced bradycardic effect of hypocalcemia was mediated primarily by ICaL attenuation due to reduced driving force, particularly during late depolarization. This, in turn, caused secondary reduction of calcium concentration in the intracellular compartments and subsequent attenuation of inward INaCa and reduction of intracellular sodium. Our in silico findings are complemented and substantiated by an empirical database study comprising 22,501 pairs of blood samples and in vivo heart rate measurements in hemodialysis patients and healthy individuals. A reduction of extracellular calcium was correlated with a decrease of heartrate by 9.9 bpm/mM total serum calcium (p < 0.001) with intact autonomic control in the cross-sectional population. In conclusion, we present mechanistic in silico and empirical in vivo data supporting the so far neglected but experimentally testable and potentially important mechanism of hypocalcemia-induced bradycardia and asystole, potentially responsible for the highly increased and so far unexplained risk of sudden cardiac death in the hemodialysis patient population.

Classification of drug-induced hERG potassium-channel block from electrocardiographic T-wave features using artificial neural networks

BACKGROUND

Human ether-à-go-go-related gene (hERG) potassium-channel block represents a harmful side effect of drug therapy that may cause torsade de pointes (TdP). Analysis of ventricular repolarization through electrocardiographic T-wave features represents a noninvasive way to accurately evaluate the TdP risk in drug-safety studies. This study proposes an artificial neural network (ANN) for noninvasive electrocardiography-based classification of the hERG potassium-channel block.

METHODS

The data were taken from the "ECG Effects of Ranolazine, Dofetilide, Verapamil, and Quinidine in Healthy Subjects" Physionet database; they consisted of median vector magnitude (VM) beats of 22 healthy subjects receiving a single 500 μg dose of dofetilide. Fourteen VM beats were considered for each subject, relative to time-points ranging from 0.5 hr before to 14.0 hr after dofetilide administration. For each VM, changes in two indexes accounting for the early and the late phases of repolarization, ΔERD_30% and ΔT_{S /A} , respectively, were computed as difference between values at each postdose time-point and the predose time-point. Thus, the dataset contained 286 ΔERD_30% -ΔT_{S /A} pairs, partitioned into training, validation, and test sets (114, 29, and 143 pairs, respectively) and used as inputs of a two-layer feedforward ANN with two target classes: high block (HB) and low block (LB). Optimal ANN (OANN) was identified using the training and validation sets and tested on the test set.

RESULTS

Test set area under the receiver operating characteristic was 0.91; sensitivity, specificity, accuracy, and precision were 0.93, 0.83, 0.92, and 0.96, respectively.

CONCLUSION

OANN represents a reliable tool for noninvasive assessment of the hERG potassium-channel block.

Acute effect of a peritoneal dialysis exchange on electrolyte concentration and QT interval in uraemic patients

BACKGROUND

Hemodialysis (HD) sessions induce changes in plasma electrolytes that lead to modifications of QT interval, virtually associated with dangerous arrhythmias. It is not known whether such a phenomenon occurs even during peritoneal dialysis (PD). The aim of the study is to analyze the relationship between dialysate and plasma electrolyte modifications and QT interval during a PD exchange.

METHODS

In 15 patients, two manual PD 4-h exchanges were performed, using two isotonic solutions with different calcium concentration (Ca⁺⁺1.25 and Ca1.75⁺⁺ mmol/L). Dialysate and plasma electrolyte concentration and QT interval (ECG Holter recording) were monitored hourly. A computational model simulating the ventricular action potential during the exchange was also performed.

RESULTS

Dialysis exchange induced a significant plasma alkalizing effect (p < 0.001). Plasma K⁺ significantly decreased at the third hour (p < 0.05). Plasma Na⁺ significantly decreased (p < 0.001), while plasma Ca⁺⁺ slightly increased only when using the Ca 1.75⁺⁺ mmol/L solution (p < 0.01). The PD exchange did not induce modifications of clinical relevance in the QT interval, while a significant decrease in heart rate (p < 0.001) was observed. The changes in plasma K⁺ values were significantly inversely correlated to QT interval modifications (p < 0.001), indicating that even small decreases of K⁺ were consistently paralleled by small QT prolongations. These results were perfectly confirmed by the computational model.

CONCLUSIONS

The PD exchange guarantees a greater cardiac electrical stability compared to the HD session and should be preferred in patients with a higher arrhythmic risk. Moreover, our study shows that ventricular repolarization is extremely sensitive to plasma K⁺ changes, also in normal range.

Quantitative Evaluation of the Relationship between T-Wave-Based Features and Serum Potassium Level in Real-World Clinical Practice

BACKGROUND

Proper management of hyperkalemia that leads to fatal cardiac arrhythmia has become more important because of the increased prevalence of hyperkalemia-prone diseases. Although T-wave changes in hyperkalemia are well known, their usefulness is debatable. We evaluated how well T-wave-based features of electrocardiograms (ECGs) are correlated with estimated serum potassium levels using ECG data from real-world clinical practice.

METHODS

We collected ECGs from a local ECG repository (MUSE™) from 1994 to 2017 and extracted the ECG waveforms. Of about 1 million reports, 124,238 were conducted within 5 minutes before or after blood collection for serum potassium estimation. We randomly selected 500 ECGs and two evaluators measured the amplitude (T-amp) and right slope of the T-wave (T-right slope) on five lead waveforms (V3, V4, V5, V6, and II). Linear correlations of T-amp, T-right slope, and their normalized feature (T-norm) with serum potassium levels were evaluated using Pearson correlation coefficient analysis.

RESULTS

Pearson correlation coefficients for T-wave-based features with serum potassium between the two evaluators were 0.99 for T-amp and 0.97 for T-right slope. The coefficient for the association between T-amp, T-right slope, and T-norm, and serum potassium ranged from -0.22 to 0.02. In the normal ECG subgroup (normal ECG or otherwise normal ECG), there was no correlation between T-wave-based features and serum potassium level.

CONCLUSIONS

T-wave-based features were not correlated with serum potassium level, and their use in real clinical practice is currently limited.

A response surface optimization approach to adjust ionic current conductances of cardiac electrophysiological models. Application to the study of potassium level changes

Cardiac electrophysiological computational models are often developed from previously published models. The new models may incorporate additional features to adapt the model to a different species or may upgrade a specific ionic formulation based on newly available experimental data. A relevant challenge in the development of a new model is the estimation of certain ionic current conductances that cannot be reliably identified from experiments. A common strategy to estimate those conductances is by means of constrained non-linear least-squares optimization. In this work, a novel methodology is proposed for estimation of ionic current conductances of cardiac electrophysiological models by using a response surface approximation-based constrained optimization with trust region management. Polynomial response surfaces of a number of electrophysiological markers were built using statistical sampling methods. These markers included action potential duration (APD), triangulation, diastolic and systolic intracellular calcium concentration, and time constants of APD rate adaptation. The proposed methodology was applied to update the Carro et al. human ventricular action potential model after incorporation of intracellular potassium ([K⁺]_i) dynamics. While the Carro et al. model was well suited for investigation of arrhythmogenesis, it did not allow simulation of [K⁺]_i changes. With the methodology proposed in this study, the updated Carro et al. human ventricular model could be used to simulate [K⁺]_i changes in response to varying extracellular potassium ([K⁺]_o) levels. Additionally, it rendered values of evaluated electrophysiological markers within physiologically plausible ranges. The optimal values of ionic current conductances in the updated model were found in a notably shorter time than with previously proposed methodologies. As a conclusion, the response surface optimization-based approach proposed in this study allows estimating ionic current conductances of cardiac electrophysiological computational models while guaranteeing replication of key electrophysiological features and with an important reduction in computational cost with respect to previously published approaches. The updated Carro et al. model developed in this study is thus suitable for the investigation of arrhythmic risk-related conditions, including those involving large changes in potassium concentration.

Towards Addressing the Body Electrolyte Environment via Sweat Analysis:Pilocarpine Iontophoresis Supports Assessment of Plasma Potassium Concentration

Electrolyte concentration in sweat depends on environmental context and physical condition but also on the pathophysiological status. Sweat analyzers may be therefore the future way for biological survey although how sweat electrolyte composition can reflect plasma composition remains unclear. We recruited 10 healthy subjects and 6 patients to have a broad range of plasma electrolyte concentrations (chloride, potassium and sodium) and pH. These variables were compared to those found in sweat produced following cycling exercise or pilocarpine iontophoresis, a condition compatible with operating a wearable device. We found no correlation between plasma and sweat parameters when exercise-induced sweat was analyzed, and we could identify a correlation only between plasma and sweat potassium concentration (R = 0.78, p < 0.01) when sweat was induced using pilocarpine iontophoresis. We tested measurement repeatability in sweat at 24hr-interval for 3 days in 4 subjects and found a great intra-individual variability regarding all parameters in exercise-induced sweat whereas similar electrolyte levels were measured in pilocarpine-induced sweat. Thus, electrolyte concentration in sweat sampled following physical activity does not reflect concentration in plasma while pilocarpine iontophoresis appears to be promising to reproducibly address sweat electrolytes, and to make an indirect evaluation of plasma potassium concentration in chronic kidney disease and arrhythmia.