Novel Two-Step Classifier for Torsades de Pointes Risk Stratification from Direct Features

Role of Machine Learning and Artificial Intelligence in Arrhythmias and Electrophysiology

Machine learning (ML), a subset of artificial intelligence (AI) centered on machines learning from extensive datasets, stands at the forefront of a technological revolution shaping various facets of society. Cardiovascular medicine has emerged as a key domain for ML applications, with considerable efforts to integrate these innovations into routine clinical practice. Within cardiac electrophysiology, ML applications, especially in the automated interpretation of electrocardiograms, have garnered substantial attention in existing literature. However, less recognized are the diverse applications of ML in cardiac electrophysiology and arrhythmias, spanning basic science research on arrhythmia mechanisms, both experimental and computational, as well as contributions to enhanced techniques for mapping cardiac electrical function and translational research related to arrhythmia management. This comprehensive review delves into various ML applications within the scope of this journal, organized into 3 parts. The first section provides a fundamental understanding of general ML principles and methodologies, serving as a foundational resource for readers interested in exploring ML applications in arrhythmia research. The second part offers an in-depth review of studies in arrhythmia and electrophysiology that leverage ML methodologies, showcasing the broad potential of ML approaches. Each subject is thoroughly outlined, accompanied by a review of notable ML research advancements. Finally, the review delves into the primary challenges and future perspectives surrounding ML-driven cardiac electrophysiology and arrhythmias research.

Evaluation of cardiac pro-arrhythmic risks using the artificial neural network with ToR-ORd in silico model output

Torsades de pointes (TdP) is a type of ventricular arrhythmia that can lead to sudden cardiac death. Drug-induced TdP has been an important concern for researchers and international regulatory boards. The Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative was proposed that integrates in vitro testing and computational models of cardiac ion channels and human cardiomyocyte cells to evaluate the proarrhythmic risk of drugs. The TdP risk classification performance using only a single TdP metric may require some improvements because of information limitations and the instability of generalizing results. This study evaluates the performance of TdP metrics from the in silico simulations of the Tomek-O'Hara Rudy (ToR-ORd) ventricular cell model for classifying the TdP risk of drugs. We utilized these metrics as an input to an artificial neural network (ANN)-based classifier. The ANN model was optimized through hyperparameter tuning using the grid search (GS) method to find the optimal model. The study outcomes show an area under the curve (AUC) value of 0.979 for the high-risk category, 0.791 for the intermediate-risk category, and 0.937 for the low-risk category. Therefore, this study successfully demonstrates the capability of the ToR-ORd ventricular cell model in classifying the TdP risk into three risk categories, providing new insights into TdP risk prediction methods.

Combining pharmacokinetic and electrophysiological models for early prediction of drug-induced arrhythmogenicity

BACKGROUND AND OBJECTIVE

In silico methods are gaining attention for predicting drug-induced Torsade de Pointes (TdP) in different stages of drug development. However, many computational models tended not to account for inter-individual response variability due to demographic covariates, such as sex, or physiologic covariates, such as renal function, which may be crucial when predicting TdP. This study aims to compare the effects of drugs in male and female populations with normal and impaired renal function using in silico methods.

METHODS

Pharmacokinetic models considering sex and renal function as covariates were implemented from data published in pharmacokinetic studies. Drug effects were simulated using an electrophysiologically calibrated population of cellular models of 300 males and 300 females. The population of models was built by modifying the endocardial action potential model published by O'Hara et al. (2011) according to the experimentally measured gene expression levels of 12 ion channels.

RESULTS

Fifteen pharmacokinetic models for CiPA drugs were implemented and validated in this study. Eight pharmacokinetic models included the effect of renal function and four the effect of sex. The mean difference in action potential duration (APD) between male and female populations was 24.9 ms (p<0.05). Our simulations indicated that women with impaired renal function were particularly susceptible to drug-induced arrhythmias, whereas healthy men were less prone to TdP. Differences between patient groups were more pronounced for high TdP-risk drugs. The proposed in silico tool also revealed that individuals with impaired renal function, electrophysiologically simulated with hyperkalemia (extracellular potassium concentration [K+]o = 7 mM) exhibited less pronounced APD prolongation than individuals with normal potassium levels. The pharmacokinetic/electrophysiological framework was used to determine the maximum safe dose of dofetilide in different patient groups. As a proof of concept, 3D simulations were also run for dofetilide obtaining QT prolongation in accordance with previously reported clinical values.

CONCLUSIONS

This study presents a novel methodology that combines pharmacokinetic and electrophysiological models to incorporate the effects of sex and renal function into in silico drug simulations and highlights their impact on TdP-risk assessment. Furthermore, it may also help inform maximum dose regimens that ensure TdP-related safety in a specific sub-population of patients.

Machine learning approach to evaluate TdP risk of drugs using cardiac electrophysiological model including inter-individual variability

Introduction: Predicting ventricular arrhythmia Torsade de Pointes (TdP) caused by drug-induced cardiotoxicity is essential in drug development. Several studies used single biomarkers such as qNet and Repolarization Abnormality (RA) in a single cardiac cell model to evaluate TdP risk. However, a single biomarker may not encompass the full range of factors contributing to TdP risk, leading to divergent TdP risk prediction outcomes, mainly when evaluated using unseen data. We addressed this issue by utilizing multi-in silico features from a population of human ventricular cell models that could capture a representation of the underlying mechanisms contributing to TdP risk to provide a more reliable assessment of drug-induced cardiotoxicity. Method: We generated a virtual population of human ventricular cell models using a modified O'Hara-Rudy model, allowing inter-individual variation. IC 50 and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features (dVm dt repol , dVm dt max , Vm peak , Vm resting , APD tri , APD 90 , APD 50 , Ca peak , Ca diastole , Ca tri , CaD 90 , CaD 50 , qNet, qInward) could be generated from the simulation and used as input to several machine learning models, including k-nearest neighbor (KNN), Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN). Optimization of the machine learning model was performed using a grid search to select the best parameter of the proposed model. We applied five-fold cross-validation while training the model with 42 drugs and evaluated the model's performance with test data from 25 drugs. Result: The proposed ANN model showed the highest performance in predicting the TdP risk of drugs by providing an accuracy of 0.923 (0.908-0.937), sensitivity of 0.926 (0.909-0.942), specificity of 0.921 (0.906-0.935), and AUC score of 0.964 (0.954-0.975). Discussion and conclusion: According to the performance results, combining the electrophysiological model including inter-individual variation and optimization of machine learning showed good generalization ability when evaluated using the unseen dataset and produced a reliable drug-induced TdP risk prediction system.

Uncertainty assessment of proarrhythmia predictions derived from multi-level in silico models

In silico methods can be used for an early assessment of arrhythmogenic properties of drug candidates. However, their use for decision-making is conditioned by the possibility to estimate the predictions' uncertainty. This work describes our efforts to develop uncertainty quantification methods for the predictions produced by multi-level proarrhythmia models. In silico models used in this field usually start with experimental or predicted IC50 values that describe drug-induced ion channel blockade. Using such inputs, an electrophysiological model computes how the ion channel inhibition, exerted by a drug in a certain concentration, translates to an altered shape and duration of the action potential in cardiac cells, which can be represented as arrhythmogenic risk biomarkers such as the APD90. Using this framework, we identify the main sources of aleatory and epistemic uncertainties and propose a method based on probabilistic simulations that replaces single-point estimates predicted using multiple input values, including the IC50s and the electrophysiological parameters, by distributions of values. Two selected variability types associated with these inputs are then propagated through the multi-level model to estimate their impact on the uncertainty levels in the output, expressed by means of intervals. The proposed approach yields single predictions of arrhythmogenic risk biomarkers together with value intervals, providing a more comprehensive and realistic description of drug effects on a human population. The methodology was tested by predicting arrhythmogenic biomarkers on a series of twelve well-characterised marketed drugs, belonging to different arrhythmogenic risk classes.

Application of Convolutional Neural Networks Using Action Potential Shape for In-Silico Proarrhythmic Risk Assessment

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.

Considering population variability of electrophysiological models improves the in silico assessment of drug-induced torsadogenic risk

BACKGROUND AND OBJECTIVE

In silico tools are known to aid in drug cardiotoxicity assessment. However, computational models do not usually consider electrophysiological variability, which may be crucial when predicting rare adverse events such as drug-induced Torsade de Pointes (TdP). In addition, classification tools are usually binary and are not validated using an external data set. Here we analyze the role of incorporating electrophysiological variability in the prediction of drug-induced arrhythmogenic-risk, using a ternary classification and two external validation datasets.

METHODS

The effects of the 12 training CiPA drugs were simulated at three different concentrations using a single baseline model and an electrophysiologically calibrated population of models. 9 biomarkers related with action potential (AP), calcium dynamics and net charge were measured for each simulated concentration. These biomarkers were used to build ternary classifiers based on Support Vector Machines (SVM) methodology. Classifiers were validated using two external drug sets: the 16 validation CiPA drugs and 81 drugs from CredibleMeds database.

RESULTS

Population of models allowed to obtain different AP responses under the same pharmacological intervention and improve the prediction of drug-induced TdP with respect to the baseline model. The classification tools based on population of models achieve an accuracy higher than 0.8 and a mean classification error (MCE) lower than 0.3 for both validation drug sets and for the two electrophysiological action potential models studied (Tomek et al. 2020 and a modified version of O'Hara et al. 2011). In addition, simulations with population of models allowed the identification of individuals with lower conductances of I_Kr, I_Ks, and I_NaK and higher conductances of I_CaL, I_NaL, and I_NCX, which are more prone to develop TdP.

CONCLUSIONS

The methodology presented here provides new opportunities to assess drug-induced TdP-risk, taking into account electrophysiological variability and may be helpful to improve current cardiac safety screening methods.

Proarrhythmic risk assessment of drugs by dVm /dt shapes using the convolutional neural network

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.

Assessment of Drug Proarrhythmicity Using Artificial Neural Networks With in silico Deterministic Model Outputs

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/dt_max, AP_resting, APD90, APD50, Ca_resting, 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.

Prediction of arrhythmia susceptibility through mathematical modeling and machine learning

At present, the QT interval on the electrocardiographic (ECG) waveform is the most common metric for assessing an individual's susceptibility to ventricular arrhythmias, with a long QT, or, at the cellular level, a long action potential duration (APD) considered high risk. However, the limitations of this simple approach have long been recognized. Here, we sought to improve prediction of arrhythmia susceptibility by combining mechanistic mathematical modeling with machine learning (ML). Simulations with a model of the ventricular myocyte were performed to develop a large heterogenous population of cardiomyocytes (n = 10,586), and we tested each variant's ability to withstand three arrhythmogenic triggers: 1) block of the rapid delayed rectifier potassium current (I_Kr Block), 2) augmentation of the L-type calcium current (I_CaL Increase), and 3) injection of inward current (Current Injection). Eight ML algorithms were trained to predict, based on simulated AP features in preperturbed cells, whether each cell would develop arrhythmic dynamics in response to each trigger. We found that APD can accurately predict how cells respond to the simple Current Injection trigger but cannot effectively predict the response to I_Kr Block or I_CaL Increase. ML predictive performance could be improved by incorporating additional AP features and simulations of additional experimental protocols. Importantly, we discovered that the most relevant features and experimental protocols were trigger specific, which shed light on the mechanisms that promoted arrhythmia formation in response to the triggers. Overall, our quantitative approach provides a means to understand and predict differences between individuals in arrhythmia susceptibility.

Human-induced pluripotent stem cell-derived cardiomyocytes, 3D cardiac structures, and heart-on-a-chip as tools for drug research

Development of new drugs is of high interest for the field of cardiac and cardiovascular diseases, which are a dominant cause of death worldwide. Before being allowed to be used and distributed, every new potentially therapeutic compound must be strictly validated during preclinical and clinical trials. The preclinical studies usually involve the in vitro and in vivo evaluation. Due to the increasing reporting of discrepancy in drug effects in animal and humans and the requirement to reduce the number of animals used in research, improvement of in vitro models based on human cells is indispensable. Primary cardiac cells are difficult to access and maintain in cell culture for extensive experiments; therefore, the human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) became an excellent alternative. This technology enables a production of high number of patient- and disease-specific cardiomyocytes and other cardiac cell types for a large-scale research. The drug effects can be extensively evaluated in the context of electrophysiological responses with a use of well-established tools, such as multielectrode array (MEA), patch clamp, or calcium ion oscillation measurements. Cardiotoxicity, which is a common reason for withdrawing drugs from marketing or rejection at final stages of clinical trials, can be easily verified with a use of hiPSC-CM model providing a prediction of human-specific responses and higher safety of clinical trials involving patient cohort. Abovementioned studies can be performed using two-dimensional cell culture providing a high-throughput and relatively lower costs. On the other hand, more complex structures, such as engineered heart tissue, organoids, or spheroids, frequently applied as co-culture systems, represent more physiological conditions and higher maturation rate of hiPSC-derived cells. Furthermore, heart-on-a-chip technology has recently become an increasingly popular tool, as it implements controllable culture conditions, application of various stimulations and continuous parameters read-out. This paper is an overview of possible use of cardiomyocytes and other cardiac cell types derived from hiPSC as in vitro models of heart in drug research area prepared on the basis of latest scientific reports and providing thorough discussion regarding their advantages and limitations.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

In Silico Classifiers for the Assessment of Drug Proarrhythmicity

Drug-induced torsade de pointes (TdP) is a life-threatening ventricular arrhythmia responsible for the withdrawal of many drugs from the market. Although currently used TdP risk-assessment methods are effective, they are expensive and prone to produce false positives. In recent years, in silico cardiac simulations have proven to be a valuable tool for the prediction of drug effects. The objective of this work is to evaluate different biomarkers of drug-induced proarrhythmic risk and to develop an in silico risk classifier. Cellular simulations were performed using a modified version of the O'Hara et al. ventricular action potential model and existing pharmacological data (IC₅₀ and effective free therapeutic plasma concentration, EFTPC) for 109 drugs of known torsadogenic risk (51 positive). For each compound, four biomarkers were tested: T_x (drug concentration leading to a 10% prolongation of the action potential over the EFTPC), T_qNet (net charge carried by ionic currents when exposed to 10 times the EFTPC with respect to the net charge in control), T_triang (triangulation for a drug concentration of 10 times the EFTPC over triangulation in control), and T_EAD (drug concentration originating early afterdepolarizations over EFTPC). Receiver operating characteristic (ROC) curves were built for each biomarker to evaluate their individual predictive quality. At the optimal cutoff point, accuracies for T_x, T_qNet, T_triang, and T_EAD were 89.9, 91.7, 90.8, and 78.9% respectively. The resulting accuracy of the hERG IC₅₀ test (current biomarker) was 78.9%. When combining T_x, T_qNet and T_triang into a classifier based on decision trees, the prediction improves, achieving an accuracy of 94.5%. The sensitivity analysis revealed that most of the effects on the action potential are mainly due to changes in I_Kr, I_CaL, I_NaL and I_Ks. In fact, considering that drugs affect only these four currents, TdP risk classification can be as accurate as when considering effects on the seven main currents proposed by the CiPA initiative. Finally, we built a ready-to-use tool (based on more than 450 000 simulations), which can be used to quickly assess the proarrhythmic risk of a compound. In conclusion, our in silico tool can be useful for the preclinical assessment of TdP-risk and to reduce costs related with new drug development. The TdP risk-assessment tool and the software used in this work are available at https://riunet.upv.es/handle/10251/136919.

In silico models for evaluating proarrhythmic risk of drugs

Safety evaluation of drugs requires examination of the risk of generating Torsade de Pointes (TdP) because it can lead to sudden cardiac death. Until recently, the QT interval in the electrocardiogram (ECG) has been used in the evaluation of TdP risk because the QT interval is known to be associated with the development of TdP. Although TdP risk evaluation based on QT interval has been successful in removing drugs with TdP risk from the market, some safe drugs may have also been affected due to the low specificity of QT interval-based evaluation. For more accurate evaluation of drug safety, the comprehensive in vitro proarrhythmia assay (CiPA) has been proposed by regulatory agencies, industry, and academia. Although the CiPA initiative includes in silico evaluation of cellular action potential as a component, attempts to utilize in silico simulation in drug safety evaluation are expanding, even to simulating human ECG using biophysical three-dimensional models of the heart and torso under the effects of drugs. Here, we review recent developments in the use of in silico models for the evaluation of the proarrhythmic risk of drugs. We review the single cell, one-dimensional, two-dimensional, and three-dimensional models and their applications reported in the literature and discuss the possibility of utilizing ECG simulation in drug safety evaluation.

All-Optical Electrophysiology Refines Populations of In Silico Human iPSC-CMs for Drug Evaluation

High-throughput in vitro drug assays have been impacted by recent advances in human induced pluripotent stem cell-derived cardiomyocyte (hiPSC-CM) technology and by contact-free all-optical systems simultaneously measuring action potentials (APs) and Ca2+ transients (CaTrs). Parallel computational advances have shown that in silico simulations can predict drug effects with high accuracy. We combine these in vitro and in silico technologies and demonstrate the utility of high-throughput experimental data to refine in silico hiPSC-CM populations and to predict and explain drug action mechanisms. Optically obtained hiPSC-CM APs and CaTrs were used from spontaneous activity and under optical pacing in control and drug conditions at multiple doses. An updated version of the Paci2018 model was developed to refine the description of hiPSC-CM spontaneous electrical activity; a population of in silico hiPSC-CMs was constructed and calibrated using simultaneously recorded APs and CaTrs. We tested in silico five drugs (astemizole, dofetilide, ibutilide, bepridil, and diltiazem) and compared the outcomes to in vitro optical recordings. Our simulations showed that physiologically accurate population of models can be obtained by integrating AP and CaTr control records. Thus, constructed population of models correctly predicted the drug effects and occurrence of adverse episodes, even though the population was optimized only based on control data and in vitro drug testing data were not deployed during its calibration. Furthermore, the in silico investigation yielded mechanistic insights; e.g., through simulations, bepridil's more proarrhythmic action in adult cardiomyocytes compared to hiPSC-CMs could be traced to the different expression of ion currents in the two. Therefore, our work 1) supports the utility of all-optical electrophysiology in providing high-content data to refine experimentally calibrated populations of in silico hiPSC-CMs, 2) offers insights into certain limitations when translating results obtained in hiPSC-CMs to humans, and 3) shows the strength of combining high-throughput in vitro and population in silico approaches.

Classifying Drugs by their Arrhythmogenic Risk Using Machine Learning

All medications have adverse effects. Among the most serious of these are cardiac arrhythmias. Current paradigms for drug safety evaluation are costly, lengthy, conservative, and impede efficient drug development. Here, we combine multiscale experiment and simulation, high-performance computing, and machine learning to create a risk estimator to stratify new and existing drugs according to their proarrhythmic potential. We capitalize on recent developments in machine learning and integrate information across 10 orders of magnitude in space and time to provide a holistic picture of the effects of drugs, either individually or in combination with other drugs. We show, both experimentally and computationally, that drug-induced arrhythmias are dominated by the interplay between two currents with opposing effects: the rapid delayed rectifier potassium current and the L-type calcium current. Using Gaussian process classification, we create a classifier that stratifies drugs into safe and arrhythmic domains for any combinations of these two currents. We demonstrate that our classifier correctly identifies the risk categories of 22 common drugs exclusively on the basis of their concentrations at 50% current block. Our new risk assessment tool explains under which conditions blocking the L-type calcium current can delay or even entirely suppress arrhythmogenic events. Using machine learning in drug safety evaluation can provide a more accurate and comprehensive mechanistic assessment of the proarrhythmic potential of new drugs. Our study paves the way toward establishing science-based criteria to accelerate drug development, design safer drugs, and reduce heart rhythm disorders.

Classifying Drugs by their Arrhythmogenic Risk Using Machine Learning

All medications have adverse effects. Among the most serious of these are cardiac arrhythmias. Current paradigms for drug safety evaluation are costly, lengthy, conservative, and impede efficient drug development. Here, we combine multiscale experiment and simulation, high-performance computing, and machine learning to create a risk estimator to stratify new and existing drugs according to their proarrhythmic potential. We capitalize on recent developments in machine learning and integrate information across 10 orders of magnitude in space and time to provide a holistic picture of the effects of drugs, either individually or in combination with other drugs. We show, both experimentally and computationally, that drug-induced arrhythmias are dominated by the interplay between two currents with opposing effects: the rapid delayed rectifier potassium current and the L-type calcium current. Using Gaussian process classification, we create a classifier that stratifies drugs into safe and arrhythmic domains for any combinations of these two currents. We demonstrate that our classifier correctly identifies the risk categories of 22 common drugs exclusively on the basis of their concentrations at 50% current block. Our new risk assessment tool explains under which conditions blocking the L-type calcium current can delay or even entirely suppress arrhythmogenic events. Using machine learning in drug safety evaluation can provide a more accurate and comprehensive mechanistic assessment of the proarrhythmic potential of new drugs. Our study paves the way toward establishing science-based criteria to accelerate drug development, design safer drugs, and reduce heart rhythm disorders.

Blinded In Silico Drug Trial Reveals the Minimum Set of Ion Channels for Torsades de Pointes Risk Assessment

Torsades de Pointes (TdP) is a type of ventricular arrhythmia which could be observed as an unwanted drug-induced cardiac side effect, and it is associated with repolarization abnormalities in single cells. The pharmacological evaluations of TdP risk in previous years mainly focused on the hERG channel due to its vital role in the repolarization of cardiomyocytes. However, only considering drug effects on hERG led to false positive predictions since the drug action on other ion channels can also have crucial regulatory effects on repolarization. To address the limitation of only evaluating hERG, the Comprehensive in Vitro Proarrhythmia Assay initiative has proposed to systematically integrate drug effects on multiple ion channels into in silico drug trial to improve TdP risk assessment. It is not clear how many ion channels are sufficient for reliable TdP risk predictions, and whether differences in IC₅₀ and Hill coefficient values from independent sources can lead to divergent in silico prediction outcomes. The rationale of this work is to investigate the above two questions using a computationally efficient population of human ventricular cells optimized to favor repolarization abnormality. Our blinded results based on two independent data sources confirm that simulations with the optimized population of human ventricular cell models enable efficient in silico drug screening, and also provide direct observation and mechanistic analysis of repolarization abnormality. Our results show that 1) the minimum set of ion channels required for reliable TdP risk predictions are Nav1.5 (peak), Cav1.2, and hERG; 2) for drugs with multiple ion channel blockage effects, moderate IC₅₀ variations combined with variable Hill coefficients can affect the accuracy of in silico predictions.

General Principles for the Validation of Proarrhythmia Risk Prediction Models: An Extension of the CiPA In Silico Strategy

This white paper presents principles for validating proarrhythmia risk prediction models for regulatory use as discussed at the In Silico Breakout Session of a Cardiac Safety Research Consortium/Health and Environmental Sciences Institute/US Food and Drug Administration-sponsored Think Tank Meeting on May 22, 2018. The meeting was convened to evaluate the progress in the development of a new cardiac safety paradigm, the Comprehensive in Vitro Proarrhythmia Assay (CiPA). The opinions regarding these principles reflect the collective views of those who participated in the discussion of this topic both at and after the breakout session. Although primarily discussed in the context of in silico models, these principles describe the interface between experimental input and model-based interpretation and are intended to be general enough to be applied to other types of nonclinical models for proarrhythmia assessment. This document was developed with the intention of providing a foundation for more consistency and harmonization in developing and validating different models for proarrhythmia risk prediction using the example of the CiPA paradigm.

Usefulness of Bnet, a Simple Linear Metric in Discerning Torsades De Pointes Risks in 28 CiPA Drugs

The Comprehensive in vitro Proarrhythmia Assay (CiPA) project suggested the torsade metric score (TMS) which requires substantial computing resources as a useful biomarker to predict proarrhythmic risk from human ether-à-go-go-related gene (hERG) and a few other ion channel block data. The TMS was useful to predict low TdP risks of drugs blocking Na+ (ranolazine) and Ca2+ (verapamil) channels as well as the hERG channel. However, Mistry asserted that the simple linear metric, Bnet reflecting net blockade of a few influential ion channels has similar predictive power. Here we compared the predictability of Bnet and TMS for the 12 training and 16 validation CiPA drugs which were pre-classified into three categories according to the known TdP risks (low, intermediate, and high risk) by CiPA. Bnet at 5×Cmax (Bnet5×Cmax) was calculated using the ion-channel IC50 and Hill coefficients of CiPA drugs collected from previous reports by the CiPA team and others. The receiver operating characteristic curve area under curve (ROC AUC) values for TMS and Bnet5×Cmax as performance metrics in discerning low versus intermediate/high risk categories for the 28 CiPA drugs were similar. However, Bnet5×Cmax was much inferior to TMS at discerning between intermediate- and high-risk drugs. Dynamic Bnet, which used in silico hERG dynamic parameters unlike conventional Bnet, improved the misspecification. Thus, we propose that Bnet5×Cmax is used for quick screening of TdP risks of drug candidates and if the "intermediate/high" risk is predicted by Bnet5×Cmax, in silico approaches, such as dynamic Bnet or TMS, may be further considered.

Global Sensitivity Analysis of Ventricular Myocyte Model-Derived Metrics for Proarrhythmic Risk Assessment

Multiscale computational models of the heart are being extensively investigated for improved assessment of drug-induced torsades de pointes (TdP) risk, a fatal side effect of many drugs. Model-derived metrics such as action potential duration and net charge carried by ionic currents (qNet) have been proposed as potential candidates for TdP risk stratification after being tested on small datasets. Unlike purely statistical approaches, model-derived metrics are thought to provide mechanism-based classification. In particular, qNet has been recently proposed as a surrogate metric for early afterdepolarizations (EADs), which are known to be cellular triggers of TdP. Analysis of critical model components and of the ion channels that have major impact on model-derived metrics can lead to improvements in the confidence of the prediction. In this paper, we analyze large populations of virtual drugs to systematically examine the influence of different ion channels on model-derived metrics that have been proposed for proarrhythmic risk assessment. We demonstrate via global sensitivity analysis (GSA) that model-derived metrics are most sensitive to different sets of input parameters. Similarly, important differences in sensitivity to specific channel blocks are highlighted when classifying drugs into different risk categories by either qNet or a metric directly based on simulated EADs. In particular, the higher sensitivity of qNet to the block of the late sodium channel might explain why its classification accuracy is better than that of the EAD-based metric, as shown for a small set of known drugs. Our results highlight the need for a better mechanistic interpretation of promising metrics like qNet based on a formal analysis of models. GSA should, therefore, constitute an essential component of the in silico workflow for proarrhythmic risk assessment, as an improved understanding of the structure of model-derived metrics could increase confidence in model-predicted risk.

Predicting critical drug concentrations and torsadogenic risk using a multiscale exposure-response simulator

Torsades de pointes is a serious side effect of many drugs that can trigger sudden cardiac death, even in patients with structurally normal hearts. Torsadogenic risk has traditionally been correlated with the blockage of a specific potassium channel and a prolonged recovery period in the electrocardiogram. However, the precise mechanisms by which single channel block translates into heart rhythm disorders remain incompletely understood. Here we establish a multiscale exposure-response simulator that converts block-concentration characteristics from single cell recordings into three-dimensional excitation profiles and electrocardiograms to rapidly assess torsadogenic risk. For the drug dofetilide, we characterize the QT interval and heart rate at different drug concentrations and identify the critical concentration at the onset of torsades de pointes: For dofetilide concentrations of 2x, 3x, and 4x, as multiples of the free plasma concentration Cmax = 2.1 nM, the QT interval increased by +62.0%, +71.2%, and +82.3% compared to baseline, and the heart rate changed by -21.7%, -23.3%, and +88.3%. The last number indicates that, at the critical concentration of 4x, the heart spontaneously developed an episode of a torsades-like arrhythmia. Strikingly, this critical drug concentration is higher than the concentration estimated from early afterdepolarizations in single cells and lower than in one-dimensional cable models. Our results highlight the importance of whole heart modeling and explain, at least in part, why current regulatory paradigms often fail to accurately quantify the pro-arrhythmic potential of a drug. Our exposure-response simulator could provide a more mechanistic assessment of pro-arrhythmic risk and help establish science-based guidelines to reduce rhythm disorders, design safer drugs, and accelerate drug development.

Quantitative Systems Pharmacology Models for a New International Cardiac Safety Regulatory Paradigm: An Overview of the Comprehensive In Vitro Proarrhythmia Assay In Silico Modeling Approach

As a relatively new discipline, quantitative systems pharmacology has seen a significant increase in the application and utility of drug development. One area that could greatly benefit from such an approach is in the proarrhythmia assessment of new drugs. The Comprehensive In Vitro Proarrhythmia Assay (CiPA) Initiative is a global public-private partnership project that has developed an integrated approach using mechanistic in silico models for proarrhythmia risk prediction. Progress to date has led to the formation of the International Council on Harmonisation Implementation Working Group to revise regulatory guidelines via the Questions-and-Answers process to address the best practices for proarrhythmia models and how they can impact clinical drug development. This article reviews the CiPA in silico model-development process, focusing on its unique development and validation strategy, and summarizes the lessons learned as consideration points for the ongoing implementation of CiPA-like in silico models in drug development.

Impact of disease state on arrhythmic event detection by action potential modelling in cardiac safety pharmacology

INTRODUCTION

The use of in silico cardiac action potential simulations is one of the pillars of the CiPA initiative (Comprehensive in vitro Proarrhythmia Assay) currently under evaluation designed to detect more accurately proarrhythmic liabilities of new drug candidate. In order to take into account the variability of clinical situations, we propose to improve this method by studying the impact of various disease states on arrhythmic events induced by 30 torsadogenic or non-torsadogenic compounds.

METHOD

In silico modelling was done on the human myocytes using the Dutta revised O'Hara-Rudy algorithm. Results were analysed using a new metric based on the compound IC_50s against the seven cardiac ionic currents considered to be the most important by the CiPA initiative (I_Kr, I_Ks, I_Na, I_NaL, I_K1, I_to, I_CaL) and the minimal rate of action potential voltage decrease calculated at the early-afterdepolarization (EAD) take-off membrane voltage (V_min).

RESULTS

The specific threshold at which each torsadogenic compounds induced EAD, was exacerbated by the presence of cardiac risk factors ranked as follows: congestive heart failure > hypertrophic cardiomyopathy > cardiac pause > no risk factor. Non-torsadogenic compounds induced no EAD even in the presence of cardiac risk factors.

DISCUSSION

The present study highlighted the impact of pre-existing cardiovascular disease on arrhythmic event detection suggesting that disease state modelling may need to be incorporated in order to fully realize the goal of the CiPA paradigm in a more accurate predictability of proarrhythmic liabilities of new drug candidate.