TY - JOUR
T1 - Machine learning approach to evaluate TdP risk of drugs using cardiac electrophysiological model including inter-individual variability
AU - Fuadah, Yunendah Nur
AU - Qauli, Ali Ikhsanul
AU - Marcellinus, Aroli
AU - Pramudito, Muhammad Adnan
AU - Lim, Ki Moo
N1 - Publisher Copyright:
Copyright © 2023 Fuadah, Qauli, Marcellinus, Pramudito and Lim.
PY - 2023
Y1 - 2023
N2 - 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. (Formula presented.) and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features ((Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), 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.
AB - 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. (Formula presented.) and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features ((Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), (Formula presented.), 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.
KW - drug risk assessment
KW - explainable AI
KW - grid search
KW - in silico features
KW - machine learning
KW - torsade de pointes
UR - http://www.scopus.com/inward/record.url?scp=85174595674&partnerID=8YFLogxK
U2 - 10.3389/fphys.2023.1266084
DO - 10.3389/fphys.2023.1266084
M3 - Article
AN - SCOPUS:85174595674
SN - 1664-042X
VL - 14
JO - Frontiers in Physiology
JF - Frontiers in Physiology
M1 - 1266084
ER -