A deep learning platform to assess drug proarrhythmia risk.

Journal: Cell stem cell
PMID: 36563695

Abstract

Drug safety initiatives have endorsed human iPSC-derived cardiomyocytes (hiPSC-CMs) as an in vitro model for predicting drug-induced cardiac arrhythmia. However, the extent to which human-defined features of in vitro arrhythmia predict actual clinical risk has been much debated. Here, we trained a convolutional neural network classifier (CNN) to learn features of in vitro action potential recordings of hiPSC-CMs that are associated with lethal Torsade de Pointes arrhythmia. The CNN classifier accurately predicted the risk of drug-induced arrhythmia in people. The risk profile of the test drugs was similar across hiPSC-CMs derived from different healthy donors. In contrast, pathogenic mutations that cause arrhythmogenic cardiomyopathies in patients significantly increased the proarrhythmic propensity to certain intermediate and high-risk drugs in the hiPSC-CMs. Thus, deep learning can identify in vitro arrhythmic features that correlate with clinical arrhythmia and discern the influence of patient genetics on the risk of drug-induced arrhythmia.

Authors

  • Ricardo Serrano
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Dries A M Feyen
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Arne A N Bruyneel
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Anna P Hnatiuk
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Michelle M Vu
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Prashila L Amatya
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Isaac Perea-Gil
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Cardiothoracic Surgery, Stanford University, Stanford, CA 94305, USA.
  • Maricela Prado
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Cardiothoracic Surgery, Stanford University, Stanford, CA 94305, USA.
  • Timon Seeger
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA.
  • Joseph C Wu
  • Ioannis Karakikes
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Cardiothoracic Surgery, Stanford University, Stanford, CA 94305, USA.
  • Mark Mercola
    Stanford Cardiovascular Institute, Stanford University, Stanford, CA 94305, USA; Department of Medicine, Division of Cardiovascular Medicine, Stanford University, Stanford, CA 94305, USA. Electronic address: mmercola@stanford.edu.

Keywords

External Resources

Popular Topics
Recent Journals