Search

Due to the outbreak of the SARS-CoV-2 virus, drug repurposing and Emergency Use Authorization have been proposed to treat the coronavirus disease 2019 (COVID-19) during the pandemic. While the efficiency of the drugs has been discussed, it was identified that certain compounds, such as chloroquine and hydroxychloroquine, cause QT interval prolongation and potential cardiotoxic effects. Drug-induced cardiotoxicity and QT prolongation may lead to life-threatening arrhythmias such as torsades de pointes (TdP), a potentially fatal arrhythmic symptom. Here, we evaluated the risk of repurposed pyronaridine or artesunate-mediated cardiac arrhythmias alone and in combination for COVID-19 treatment through in vitro and in silico investigations using the Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative. The potential effects of each drug or in combinations on cardiac action potential (AP) and ion channels were explored using human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) and Chinese hamster ovary (CHO) cells transiently expressing cardiac ion channels (Nav1.5, Cav1.2, and hERG). We also performed in silico computer simulation using the optimized O’Hara-Rudy human ventricular myocyte model (ORd model) to classify TdP risk. Artesunate and dihydroartemisinin (DHA), the active metabolite of artesunate, are classified as a low risk of inducing TdP based on the torsade metric score (TMS). Moreover, artesunate does not significantly affect the cardiac APs of hiPSC-CMs even at concentrations up to 100 times the maximum serum concentration (Cmax). DHA modestly prolonged at APD90 (10.16%) at 100 times the Cmax. When considering Cmax, pyronaridine, and the combination of both drugs (pyronaridine and artesunate) are classified as having an intermediate risk of inducing TdP. However, when considering the unbound concentration (the free fraction not bound to carrier proteins or other tissues inducing pharmacological activity), both drugs are classified as having a low risk of inducing TdP. In summary, pyronaridine, artesunate, and a combination of both drugs have been confirmed to pose a low proarrhythmogenic risk at therapeutic and supratherapeutic (up to 4 times) free Cmax. Additionally, the CiPA initiative may be suitable for regulatory use and provide novel insights for evaluating drug-induced cardiotoxicity.

Abstract Comprehensive in vitro Proarrhythmia Assay (CiPA) projects for assessing proarrhythmic drugs suggested a logistic regression model using qNet as the Torsades de Pointes (TdP) risk assessment biomarker, obtained from in silico simulation. However, using a single in silico feature, such as qNet, cannot reflect whole characteristics related to TdP in the entire action potential (AP) shape. Thus, this study proposed a deep convolutional neural network (CNN) model using differential action potential shapes to classify three proarrhythmic risk levels: high, intermediate, and low, considering both characteristics related to TdP not only in the depolarization phase but also the repolarization phase of AP shape. We performed an in silico simulation and got AP shapes with drug effects using half‐maximal inhibitory concentration and Hill coefficients of 28 drugs released by CiPA groups. Then, we trained the deep CNN model with the differential AP shapes of 12 drugs and tested it with those of 16 drugs. Our model had a better performance for classifying the proarrhythmic risk of drugs than the traditional logistic regression model using qNet. The classification accuracy was 98% for high‐risk level drugs, 94% for intermediate‐risk level drugs, and 89% for low‐risk level drugs.

Many researchers have suggested evaluation methods and Torsades de Pointes (TdP) metrics to assess the proarrhythmic risk of a drug based on the in silico simulation, as part of the Comprehensive in-vitro Proarrhythmia Assay (CiPA) project. In the previous study, we validated the robustness of 12 in silico features using the ordinal logistic regression (OLR) model by comparing the classification performances of metrics according to the in-vitro experimental datasets used; however, the OLR model using 12 in silico features did not provide desirable results. This study proposed a convolutional neural network (CNN) model using the variability of promising in silico TdP metrics hypothesizing that the variability of in silico features based on beats has more information than the single value of in silico features. We performed the action potential (AP) simulation using a human ventricular myocyte model to calculate seven in silico features representing the electrophysiological cell states of drug effects over 1,000 beats: qNet, qInward, intracellular calcium duration at returning to 50% baseline (CaD50) and 90% baseline (CaD90), AP duration at 50% repolarization (APD50) and 90% repolarization (APD90), and dVm/dtMax_repol. The proposed CNN classifier was trained using 12 train drugs and tested using 16 test drugs among CiPA drugs. The torsadogenic risk of drugs was classified as high, intermediate, and low risks. We determined the CNN classifier by comparing the classification performance according to the variabilities of seven in silico biomarkers computed from the in silico drug simulation using the Chantest dataset. The proposed CNN classifier performed the best when using qInward variability to classify the TdP-risk drugs with 0.94 AUC for high risk and 0.93 AUC for low risk. In addition, the final CNN classifier was validated using the qInward variability obtained after merging three in-vitro datasets, but the model performance decreased to a moderate level of 0.75 and 0.78 AUC. These results suggest the need for the proposed CNN model to be trained and tested using various types of drugs.

Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients’ health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN–LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN–LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN–LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.

Abstract Electrocardiograms (ECGs) are widely used for diagnosing cardiac arrhythmia based on the deformation of signal shapes due to changes in various heart diseases. However, these abnormal signs may not be observed in some 12 ECG channels, depending on the location, the heart shape, and the type of cardiac arrhythmia. Therefore, it is necessary to closely and comprehensively observe ECG records acquired from 12 channel electrodes to diagnose cardiac arrhythmias accurately. In this study, we proposed a clustering algorithm that can classify persistent cardiac arrhythmia as well as episodic cardiac arrhythmias using the standard 12-lead ECG records and the 2D CNN model using the time–frequency feature maps to classify the eight types of arrhythmias and normal sinus rhythm. The standard 12-lead ECG records were provided by China Physiological Signal Challenge 2018 and consisted of 6877 patients. The proposed algorithm showed high performance in classifying persistent cardiac arrhythmias; however, its accuracy was somewhat low in classifying episodic arrhythmias. If our proposed model is trained and verified using more clinical data, we believe it can be used as an auxiliary device for diagnosing cardiac arrhythmias.

Since the Comprehensive in vitro Proarrhythmia Assay (CiPA) initiation, many studies have suggested various in silico features based on ionic charges, action potentials (AP), or intracellular calcium (Ca) to assess proarrhythmic risk. These in silico features are computed through electrophysiological simulations using in vitro experimental datasets as input, therefore changing with the quality of in vitro experimental data; however, research to validate the robustness of in silico features for proarrhythmic risk assessment of drugs depending on in vitro datasets has not been conducted. This study aims to verify the availability of in silico features commonly used in assessing the cardiac toxicity of drugs through an ordinal logistic regression model and three in vitro datasets measured under different experimental environments and with different purposes. We performed in silico drug simulations using the Tomek-Ohara Rudy (ToR-ORD) ventricular myocyte model and computed 12 in silico features comprising six AP features, four Ca features, and two ion charge features, which reflected the effect and characteristics of each in vitro data for CiPA 28 drugs. We then compared the classific performances of ordinal logistic regressions according to these 12 in silico features and used in vitro datasets to validate which in silico feature is the best for assessing the proarrhythmic risk of drugs at high, intermediate, and low levels. All 12 in silico features helped determine high-risky torsadogenic drugs, regardless of the in vitro datasets used in the in silico simulation as input. In the three types of in silico features, AP features were the most reliable for determining the three Torsade de Pointes (TdP) risk standards. Among AP features, AP duration at 50% repolarization (APD50) was the best when individually using in silico features per in vitro dataset. In contrast, the AP repolarization velocity (dVm/dtMax_repol) was the best when merging all in silico features computed through three in vitro datasets.

Abstract The pulse arrival time (PAT), the difference between the R-peak time of electrocardiogram (ECG) signal and the systolic peak of photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure PAT from ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PAT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between ECG and PPG as a new feature that can include PAT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). We used a total of 48 patients on the PhysioNet website by splitting them into 38 patients for training and 10 patients for testing. The prediction accuracies of SBP and DBP were 0.0 ± 1.6 mmHg and 0.2 ± 1.3 mmHg, respectively. Even though the proposed model was assessed with only 10 patients, this result was satisfied with three guidelines, which are the BHS, AAMI, and IEEE standards for blood pressure measurement devices.

Abstract Many studies have revealed changes in specific protein channels due to physiological causes such as mutation and their effects on action potential duration changes. However, no studies have been conducted to predict the type of protein channel abnormalities that occur through an action potential (AP) shape. Therefore, in this study, we aim to predict the ion channel conductance that is altered from various AP shapes using a machine learning algorithm. We perform electrophysiological simulations using a single-cell model to obtain AP shapes based on variations in the ion channel conductance. In the AP simulation, we increase and decrease the conductance of each ion channel at a constant rate, resulting in 1,980 AP shapes and one standard AP shape without any changes in the ion channel conductance. Subsequently, we calculate the AP difference shapes between them and use them as the input of the machine learning model to predict the changed ion channel conductance. In this study, we demonstrate that the changed ion channel conductance can be predicted with high prediction accuracy, as reflected by an F1 score of 0.985, using only AP shapes and simple machine learning.

This study proposes a convolutional neural network (CNN) model using action potential (AP) shapes as input for proarrhythmic risk assessment, considering the hypothesis that machine-learning features automatically extracted from AP shapes contain more meaningful information than do manually extracted indicators. We used 28 drugs listed in the comprehensive in vitro proarrhythmia assay (CiPA), consisting of eight high-risk, eleven intermediate-risk, and nine low-risk torsadogenic drugs. We performed drug simulations to generate AP shapes using experimental drug data, obtaining 2000 AP shapes per drug. The proposed CNN model was trained to classify the TdP risk into three levels, high-, intermediate-, and low-risk, based on in silico AP shapes generated using 12 drugs. We then evaluated the performance of the proposed model for 16 drugs. The classification accuracy of the proposed CNN model was excellent for high- and low-risk drugs, with AUCs of 0.914 and 0.951, respectively. The model performance for intermediate-risk drugs was good, at 0.814. Our proposed model can accurately assess the TdP risks of drugs from in silico AP shapes, reflecting the pharmacokinetics of ionic currents. We need to secure more drugs for future studies to improve the TdP-risk-assessment robustness.

As part of the Comprehensive in vitro Proarrhythmia Assay initiative, methodologies for predicting the occurrence of drug-induced torsade de pointes via computer simulations have been developed and verified recently. However, their predictive performance still requires improvement. Herein, we propose an artificial neural networks (ANN) model that uses nine multiple input features, considering the action potential morphology, calcium transient morphology, and charge features to further improve the performance of drug toxicity evaluation. The voltage clamp experimental data for 28 drugs were augmented to 2,000 data entries using an uncertainty quantification technique. By applying these data to the modified O’Hara Rudy in silico model, nine features (dVm/dtmax, APresting, APD90, APD50, Caresting, CaD90, CaD50, qNet, and qInward) were calculated. These nine features were used as inputs to an ANN model to classify drug toxicity into high-risk, intermediate-risk, and low-risk groups. The model was trained with data from 12 drugs and tested using the data of the remaining 16 drugs. The proposed ANN model demonstrated an AUC of 0.92 in the high-risk group, 0.83 in the intermediate-risk group, and 0.98 in the low-risk group. This was higher than the classification performance of the method proposed in previous studies.

Action potential duration (APD) alternans, an alternating phenomenon between action potentials in cardiomyocytes, causes heart arrhythmia when the heart rate is high. However, some of the APD alternans observed in clinical trials occurs under slow heart rate conditions of 100 to 120 bpm, increasing the likelihood of heart arrhythmias such as atrial fibrillation. Advanced studies have identified the occurrence of this type of APD alternans in terms of electrophysiological ion channel currents in cells. However, they only identified physiological phenomena, such as action potential due to random changes in a particular ion channel’s conductivity through ion models specializing in specific ion channel currents. In this study, we performed parameter sensitivity analysis via population modeling using a validated human ventricular physiology model to check the sensitivity of APD alternans to ion channel conductances. Through population modeling, we expressed the changes in alternans onset cycle length (AOCL) and mean APD in AOCL (AO meanAPD) according to the variations in ion channel conductance. Finally, we identified the ion channel that maximally affected the occurrence of APD alternans. AOCL and AO meanAPD were sensitive to changes in the plateau Ca2+ current. Accordingly, it was expected that APD alternans would be vulnerable to changes in intracellular calcium concentration.

In ventricular tachyarrhythmia, electrical instability features including action potential duration, dominant frequency, phase singularity, and filaments are associated with mechanical contractility. However, there are insufficient studies on estimated mechanical contractility based on electrical features during ventricular tachyarrhythmia using a stochastic model. In this study, we predicted cardiac mechanical performance from features of electrical instability during ventricular tachyarrhythmia simulation using machine learning algorithms, including support vector regression (SVR) and artificial neural network (ANN) models. We performed an electromechanical tachyarrhythmia simulation and extracted 12 electrical instability features and two mechanical properties, including stroke volume and the amplitude of myocardial tension (ampTens). We compared predictive performance according to kernel types of the SVR model and the number of hidden layers of the ANN model. In the SVR model, the prediction accuracies of stroke volume and ampTens were the highest when using the polynomial kernel and linear kernel, respectively. The predictive performance of the ANN model was better than that of the SVR model. The prediction accuracies were the highest when the ANN model consisted of three hidden layers. Accordingly, we propose the ANN model with three hidden layers as an optimal model for predicting cardiac mechanical contractility in ventricular tachyarrhythmia. The results of this study are expected to be used to indirectly estimate the hemodynamic response from the electrical cardiac map measured by the optical mapping system during cardiac surgery, as well as cardiac contractility under normal sinus rhythm conditions.

There are representative electrical parameters for understanding the mechanism of reentrant waves in studies on tachyarrhythmia, namely the action potential duration (APD), dominant frequency, phase singularity, and filament. However, there are no studies that have directly identified the correlation between these electrophysiological parameters and cardiac contractility. Therefore, we have identified individual and integrative correlations between these electrical phenomena and contractility during tachyarrhythmia by deriving regression equations and also investigated the electrophysiological parameters affecting cardiac contractility during tachyarrhythmia. We simulated ventricular tachyarrhythmia with 48 types of electrical patterns by applying four reentry generation methods and changing the electrical conductivity of the potassium channel, which has the greatest effect on ventricular tissue. The mechanical responses reflecting electrical complexity were obtained through deterministic simulations of excitation–contraction coupling. We used the stroke volume and amplitude of myocardial tension (ampTens) as the variables representing contractility. We derived stochastic models through single- and multivariable regression analyses to identify the electrical parameters affecting contractility during tachyarrhythmia. In single-variable regression analysis, the APD, dominant frequency, and filament, excluding phase singularity, have statistically significant correlations with the stroke volume and ampTens. Among them, the APD has the maximum influence on these two mechanical parameters (standard beta coefficient: 0.859 for stroke volume, 0.930 for ampTens). The stochastic model using all four electrical parameters fails to accurately predict contractility owing to the multicollinearity between the APD and dominant frequency. We have rederived the multi-variable stochastic model using three electrical parameters without the APD. The filament has the greatest effect on the stroke volume stochastically (standard beta coefficient: 0.853 and 0.752). The dominant frequency has the greatest effect on ampTens statistically (standard beta coefficient: −0.813). We conclude that among the electrical parameters, the APD has the highest individual influence on mechanical contraction, and the filament has the highest integrative influence in both statistical terms.

Abstract Background and aims Although studies on the relation between arrhythmias and the action potential duration (APD) have been carried out, most of them are based only on electrophysiological factors of the heart and lack experiments that consider cardiac mechanical and electromechanical characteristics. Therefore, we conducted this study to clarify the relevance of the shortening of APD of a cell in relation to the mechanical contraction activity of the heart and the associated risk of arrhythmia. Methods The human ventricular model used in this study has two dynamic characteristics: electrophysiological conduction and mechanical contraction. The model simulating electrophysiological characteristics was consisted of lumped parameter circuit that can mimic the phenomenon of ion exchange through the cell membrane of myocyte and consisted of 214,319 tetrahedral finite elements. In contrast, the model simulating mechanical contraction characteristics was constructed to mimic cardiac contraction by means of the crossbridge of a myofilament and consisted of 14,720 hermite-based finite elements to represent a natural 3D curve of the cardiac surface. First, we performed a single cell simulation and the electrophysiological simulation according to the change of the APD by changing the electrical conductivity of the I Ks channel. Thus, we confirmed the correlation between APD and intracellular Ca2+ concentration. Then, we compared mechanical response through mechanical simulation using Ca2+ data from electrical simulation. Results The APD and the sum of the intracellular Ca2+ concentrations showed a positive correlation. The shortened APD reduced the conduction wavelength of ventricular cells by shortening the plateau and early repolarization in myocardial cells. The decrease in APD reduced ventricular pumping efficiency by more than 60% as compared with the normal group (normal conditions). This change is caused by the decline of ventricular output owing to reduced ATP consumption during the crossbridge of myofilaments and decreased tension. Conclusion The shortening of APD owing to increased electrical conductivity of a protein channel on myocardial cells likely decreases the wavelength and the pumping efficiency of the ventricles. Additionally, it may increase tissue sensitivity to ventricular fibrillation, including reentry, and cause symptoms such as dyspnea and dizziness.

The KCNQ1 S140G mutation, which is involved in IKs current, affects atrial fibrillation. However, little is known about its effect on the mechanical behavior of the heart. Therefore, we assessed the influence of the KCNQ1 S140G mutation on ventricular electrophysiological stability and mechanical pumping performance using a multi-scale model of cardiac electromechanics. An image-based electromechanical model was used to assess the effect on electrical propagation and arrhythmogenesis of the KCNQ1 S140G mutation. In addition, it was used to compare the mechanical response under the wild-type (WT) and S140G mutation conditions. The intracellular calcium transient obtained from the electrophysiological model was applied as an input parameter to a mechanical model to implement excitation–contraction coupling. The IKs current equation was modified to account for expression of the KCNQ1 S140G mutation, and it included a scaling factor (ϕ) for mutant expressivity. The WT and S140G mutation conditions were compared at the single-cell and three-dimensional (3D) tissue levels. The action potential duration (APD) was reduced by 60% by the augmented IKs current under the S140G mutation condition, which resulted in shorter QT interval. This reduced the 3D sinus rhythm wavelength by 60% and the sustained re-entry by 56%. However, pumping efficiency of mutant ventricles was superior in sinus rhythm condition. In addition, the shortened wavelength in cardiac tissue allowed a re-entrant circuit to form and increased the probability of sustaining ventricular tachycardia and ventricular fibrillation. In contrast, under the WT condition, a normal wavelength (20.8 cm) was unlikely to initiate and sustain re-entry in the cardiac tissue. Subsequently, the S140G mutant ventricles developed a higher dominant frequency distribution range (2.0–5.3 Hz) than the WT condition (2.8–3.7 Hz). In addition, stroke volume of mutant ventricles was reduced by 65% in sustained re-entry compared to the WT condition. In conclusion, signs of the S140G mutation might be difficult to identify in sinus rhythm even though the mutant ventricles show shortened QT interval. This suggests that the KCNQ1 S140G mutation increases the risk of death by sudden cardiac arrest. In addition, the KCNQ1 S140G mutation can induce ventricular arrhythmia and lessen ventricular contractility under re-entrant conditions.