Key result
Multi-channel causal variational autoencoder improves drug-induced TdP risk classification versus independent models.
Why the study?
Determining the causal relationships between ionic current blockades, in-silico electrophysiological and mechanical biomarkers, and torsadogenic indices for drug-induced TdP-risk assessment remains challenging.
Does a Multi-Channel Causal Variational Autoencoder improve the characterization and classification of drug-induced TdP risk compared to single-channel models?
Does a Multi-Channel Causal Variational Autoencoder improve the characterization and classification of drug-induced TdP risk compared to single-channel models?
A novel Multi-Channel Causal Variational Autoencoder successfully identifies causal relationships between ionic blockades, electrophysiological biomarkers, and torsadogenic indices, improving in-silico classification of drug-induced Torsade de pointes risk.
Drug-induced Torsade de pointes (TdP) is a critical arrhythmia that can lead to sudden cardiac death.Besides ionic current blockades, in-silico electrophysiological and mechanical biomarkers can provide mechanistic proarrhythmic information for TdP-risk assessment, and specific torsadogenic indices have been developed for that purpose, yet, determining the causal relationships between these variables is challenging.This study aims to employ a novel Multi-Channel Causal Variational Autoencoder (MC 2 VAE), to identify causal relationships between ionic current blockades, electrophysiological biomarkers, and torsadogenic indices, considered as three distinct sources of information (channels) for drug-induced TdP risk.Our approach interestingly suggests the existence of latent causal relationships between the considered channels, allowing for a better reconstruction of all observed features.Further, MC 2 VAE can quantify the strengths of the identified causal relationships, opening up a viable avenue for actionable interventions on the established causal graph.Finally, we consider the downstream task of drug classification for TdP risk on the latent channels and show a clear improvement in classification performances when combining the three considered channels.Overall, our results provide a strong rationale for causally combining multi-channels biomarkers in TdP-risk characterization.
No takes yet. Share an insight, caveat, or question.
Al-Ali et al. (2024) studied Drug-induced Torsade de pointes (TdP) (n=109). Multi-Channel Causal Variational Autoencoder (MC2VAE) vs. Independent VAEs per channel or fewer channels was evaluated on Drug TdP-risk classification performance and data reconstruction (MSE). A novel Multi-Channel Causal Variational Autoencoder combining ionic current blockades, electrophysiological biomarkers, and torsadogenic indices improved the classification of drug-induced Torsade de pointes risk.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: