Digital twin for sex-specific identification of class III antiarrhythmic drugs based on in vitro measurements, computer models, and machine learning tools

Figures

• 

  Fig 1. The classification framework with cardiac simulations and machine learning (ML) models. ① An atrial fibrillation (AF) population of cell models was constructed by generating various combinations of ionic currents based on ex vivo experimental data; ② A drug population was created by incorporating the blocking effects of Class III and Non-Class III antiarrhythmic drugs on ion channels into the AF population; ③ Fourteen biomarkers were extracted from the action potential (AP) and calcium transient (CT) of each sample to form a dataset for drug classification. ④ Six ML models were trained and validated using the 5-fold cross-validation technique; and ⑤ The classification performance was evaluated using six metrics. RMP - resting membrane potential; APD90 - AP duration at 90% of repolarization; CTA - CT amplitude; CTD90 - CT duration at 90% of repolarization; LR - Logistic Regression; SVM - Support Vector Machine; NB - Naive Bayes; XGB - Extreme Gradient Boosting; RF - Random Forest; KNN - K-Nearest Neighbors; and AUC - Area Under the Curve of Receiver Operating Characteristic.

• 

  Fig 2. Sex differences in the AF population of human atrial cell models (5,663 males and 6,184 females). (A) Traces of action potential (AP) and calcium transient (CT). (B) Sex differences in AP biomarkers (RMP, dV/dtmax, APA, APD20, APD40, APD50, APD90 and APDtri) (CTA, CTmax, CTD50, CTD90, CTDtri and CTD). The p-values are indicated and the stars *, **, *** indicate a p-value < 0.05, 0.01 and 0.001, respectively. ns indicates not significant.

• 

  Fig 3. Class differences in the drug population of human atrial cell models (31,842 in the Class III and 28,757 in the non-Class III). (A) Traces of action potential (AP) and calcium transient (CT). (B) Class differences in AP biomarkers and CT biomarkers. *** indicates a p-value < 0.001.

• 

  Fig 4. Sex differences in the drug population of human atrial cell models (28,967 males and 31,632 females). (A) Traces of action potential (AP) and calcium transient (CT). (B) Sex differences in AP biomarkers and CT biomarkers. *** indicates a p-value < 0.001.

• 

  Fig 5. The feature distributions in the training and testing sets are similar, but the feature distributions in the Class III and non-Class III categories are partly different. (A) Action potential features (ΔRMP, ΔdV/dtmax, ΔAPA, ΔAPD20, ΔAPD40, ΔAPD50, ΔAPD90 and ΔAPDtri). (B) Calcium transient features (ΔCTA, ΔCTmax, ΔCTD50, ΔCTD90, ΔCTDtri and ΔCTD).

• 

  Fig 6. Prediction performances of non-sex-specific classifiers. Receiver operating characteristic curves (left) and F1 scores (right) are shown. *p < 0.05.

• 

  Fig 7. Prediction performances of sex-specific classifiers. Receiver operating characteristic curves and F1 scores of male (A) and female classifiers (B) are shown. *p < 0.05 and ns indicates not significant.

• 

  Fig 8. Prediction performances of sex-biased classifiers. Female on Male, models are trained on a female dataset but tested on a male dataset, but Male on Female, models are trained on a male dataset but tested on a female dataset. ***p < 0.001, and ns, not significant.

• 

  Fig 9. Feature analysis of sex-specific classifiers. Feature importance for the male (A) and female (B) classifiers is measured by the SHAP value. Feature correlation analysis shows that the two key features have a high degree of negative correlation (C).

• 

  Fig 10. Parameter analysis of sex differences. (A) Sensitivity analysis via ion current parameters (x-axis) versus the model biomarkers (y-axis). (B) Boxplots of ion current parameters in males versus females. The p-values are indicated and the stars *, **, *** indicate a p-value < 0.05, 0.01 and 0.001 respectively. ns indicates not significant.