AUTHOR=Sanchez de la Nava Ana Maria , Arenal Ángel , Fernández-Avilés Francisco , Atienza Felipe 

TITLE=Artificial Intelligence-Driven Algorithm for Drug Effect Prediction on Atrial Fibrillation: An in silico Population of Models Approach

JOURNAL=Frontiers in Physiology

VOLUME=12

YEAR=2021

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2021.768468

DOI=10.3389/fphys.2021.768468

ISSN=1664-042X

ABSTRACT=<p><bold>Background:</bold> Antiarrhythmic drugs are the first-line treatment for atrial fibrillation (AF), but their effect is highly dependent on the characteristics of the patient. Moreover, anatomical variability, and specifically atrial size, have also a strong influence on AF recurrence.</p><p><bold>Objective:</bold> We performed a proof-of-concept study using artificial intelligence (AI) that enabled us to identify proarrhythmic profiles based on pattern identification from <italic>in silico</italic> simulations.</p><p><bold>Methods:</bold> A population of models consisting of 127 electrophysiological profiles with a variation of nine electrophysiological variables (G<sub><italic>Na</italic></sub>, I<sub><italic>NaK</italic></sub>, G<sub><italic>K</italic>1</sub>, G<sub><italic>CaL</italic></sub>, G<sub><italic>Kur</italic></sub>, I<sub><italic>KCa</italic></sub>, [Na]<sub><italic>ext</italic></sub>, and [K]<sub><italic>ext</italic></sub> and diffusion) was simulated using the Koivumaki atrial model on square planes corresponding to a normal (16 cm<sup>2</sup>) and dilated (22.5 cm<sup>2</sup>) atrium. The simple pore channel equation was used for drug implementation including three drugs (isoproterenol, flecainide, and verapamil). We analyzed the effect of every ionic channel combination to evaluate arrhythmia induction. A Random Forest algorithm was trained using the population of models and AF inducibility as input and output, respectively. The algorithm was trained with 80% of the data (<italic>N</italic> = 832) and 20% of the data was used for testing with a <italic>k</italic>-fold cross-validation (<italic>k</italic> = 5).</p><p><bold>Results:</bold> We found two electrophysiological patterns derived from the AI algorithm that was associated with proarrhythmic behavior in most of the profiles, where G<sub><italic>K</italic>1</sub> was identified as the most important current for classifying the proarrhythmicity of a given profile. Additionally, we found different effects of the drugs depending on the electrophysiological profile and a higher tendency of the dilated tissue to fibrillate (Small tissue: 80 profiles vs Dilated tissue: 87 profiles).</p><p><bold>Conclusion:</bold> Artificial intelligence algorithms appear as a novel tool for electrophysiological pattern identification and analysis of the effect of antiarrhythmic drugs on a heterogeneous population of patients with AF.</p>