Match!

Deep Learning-Based Proarrhythmia Analysis Using Field Potentials Recorded From Human Pluripotent Stem Cells Derived Cardiomyocytes

Published on 2019in IEEE Journal of Translational Engineering in Health and Medicine
· DOI :10.1109/JTEHM.2019.2907945
Zeinab Golgooni (Sharif University of Technology), Sara Mirsadeghi1
Estimated H-index: 1
(Royan Institute)
+ 4 AuthorsHamid R. Rabiee17
Estimated H-index: 17
(Sharif University of Technology)
Cite
Abstract
An early characterization of drug-induced cardiotoxicity may be possible by combining comprehensive in vitro proarrhythmia assay and deep learning techniques. We aimed to develop a method to automatically detect irregular beating rhythm of field potentials recorded from human pluripotent stem cells (hPSC) derived cardiomyocytes (hPSC-CM) by multi-electrode array (MEA) system. We included field potentials from 380 experiments, which were labeled as normal or arrhythmic by electrophysiology experts. Convolutional and recurrent neural networks (CNN and RNN) were employed for automatic classification of field potential recordings. A preparation phase was initially applied to split 60-s long recordings into a series of 5-s windows. Subsequently, the classification phase comprising of two main steps was designed and applied. The first step included the classification of 5-s windows by using a designated CNN. While, the results of 5-s window assessments were used as the input sequence to an RNN that aggregates these results in the second step. The output was then compared to electrophysiologist-level arrhythmia detection, resulting in 0.83 accuracy, 0.93 sensitivity, 0.70 specificity, and 0.80 precision. In summary, this paper introduces a novel method for automated analysis of “irregularity” in an in vitro model of cardiotoxicity experiments. Thus, our method may overcome the drawbacks of using predesigned features that restricts the classification performance to the comprehensiveness and the quality of the designed features. Furthermore, automated analysis may facilitate the quality control experiments through the procedure of drug development with respect to cardiotoxicity and avoid late drug attrition from market.
  • References (46)
  • Citations (0)
Cite
References46
Newest
Published on Jan 1, 2018in Clinical Pharmacology & Therapeutics6.34
José L. Vicente12
Estimated H-index: 12
,
Jose Vicente17
Estimated H-index: 17
+ 10 AuthorsJiang Liu5
Estimated H-index: 5
The Comprehensive in vitro Proarrhythmia Assay (CiPA) initiative is developing and validating a mechanistic-based assessment of proarrhythmic risk of drugs. CiPA proposes to assess a drug's effect on multiple ion channels and integrate the effects in a computer model of the human cardiomyocyte to predict proarrhythmic risk. Unanticipated or missed effects will be assessed with human stem cell derived cardiomyocytes and electrocardiogram (ECG) analysis in early phase 1 clinical trials. This paper...
Published on Dec 1, 2017in Medical Image Analysis8.88
Geert J. S. Litjens20
Estimated H-index: 20
(Radboud University Nijmegen),
Thijs Kooi5
Estimated H-index: 5
(Radboud University Nijmegen)
+ 6 AuthorsClara I. Sánchez23
Estimated H-index: 23
(Radboud University Nijmegen)
Abstract Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per ap...
Published on Dec 1, 2017in Scientific Reports4.01
Serkan Kiranyaz13
Estimated H-index: 13
(Qatar University),
Turker Ince16
Estimated H-index: 16
(IUE: İzmir University of Economics),
Moncef Gabbouj41
Estimated H-index: 41
(TUT: Tampere University of Technology)
Each year more than 7 million people die from cardiac arrhythmias. Yet no robust solution exists today to detect such heart anomalies right at the moment they occur. The purpose of this study was to design a personalized health monitoring system that can detect early occurrences of arrhythmias from an individual’s electrocardiogram (ECG) signal. We first modelled the common causes of arrhythmias in the signal domain as a degradation of normal ECG beats to abnormal beats. Using the degradation mo...
Published on Dec 1, 2017in British Journal of Pharmacology6.58
Xavier Ligneau27
Estimated H-index: 27
,
Rashmi R. Shah12
Estimated H-index: 12
+ 7 AuthorsJean-Charles Schwartz77
Estimated H-index: 77
Background and Purpose We evaluated the concordance of results from two sets of nonclinical cardiovascular safety studies on pitolisant. Experimental Approach Nonclinical studies envisaged both in the International Conference on Harmonization (ICH) S7B guideline and Comprehensive in vitro Pro-arrhythmia Assay (CiPA) initiative were undertaken. The CiPA initiative included in vitro ion channels, stem cell-derived human ventricular myocytes, and in silico modelling to simulate human ventricular el...
Published on Nov 13, 2017in The FASEB Journal5.39
Sara Pahlavan6
Estimated H-index: 6
(Academic Center for Education, Culture and Research),
Marziyeh Shalchi Tousi1
Estimated H-index: 1
(Academic Center for Education, Culture and Research)
+ 4 AuthorsHossein Baharvand42
Estimated H-index: 42
(University of Science and Culture)
Cardiac arrhythmias are major life-threatening conditions. The landmark discovery of induced pluripotent stem cells has provided a promising in vitro system for modeling hereditary cardiac arrhythmias as well as drug development and toxicity testing. Nowadays, nutraceuticals are frequently used as supplements for cardiovascular therapy. Here we studied the cardiac effects of hawthorn (Crataegus pentagyna) leaf extract using cardiomyocytes (CMs) differentiated from healthy human embryonic stem ce...
Published on Nov 1, 2017in Journal of Electrocardiology1.17
Jose Vicente17
Estimated H-index: 17
(CDER: Center for Drug Evaluation and Research),
Meisam Hosseini3
Estimated H-index: 3
(CDER: Center for Drug Evaluation and Research)
+ 1 AuthorsDavid G. Strauss26
Estimated H-index: 26
(CDER: Center for Drug Evaluation and Research)
Abstract The ECG plays a critical role in the thorough QT study. This clinical study is part of the assessment of proarrhythmic potential of drugs under the current regulatory paradigm. While the current paradigm has been successful in preventing drugs with unexpected QT prolongation or torsade risk from reaching the market, the focus on QT prolongation has likely resulted in potentially beneficial compounds with minimal torsade risk being dropped from development. The Comprehensive in vitro Pro...
Published on Aug 1, 2017in Regulatory Toxicology and Pharmacology3.00
Yumiko Nozaki3
Estimated H-index: 3
,
Yayoi Honda6
Estimated H-index: 6
+ 19 AuthorsHiroshi Iwasaki2
Estimated H-index: 2
(Taisho Pharmaceutical Co.)
Abstract With the aim of reconsidering ICH S7B and E14 guidelines, a new in vitro assay system has been subjected to worldwide validation to establish a better prediction platform for potential drug-induced QT prolongation and the consequent TdP in clinical practice. In Japan, CSAHi HEART team has been working on hiPS-CMs in the MEA (hiPS-CMs/MEA) under a standardized protocol and found no inter-facility or lot-to-lot variability for proarrhythmic risk assessment of 7 reference compounds. In thi...
Published on Jul 1, 2017in Cell Stem Cell21.46
Gary A. Gintant20
Estimated H-index: 20
,
Bernard Fermini12
Estimated H-index: 12
+ 1 AuthorsDavid G. Strauss26
Estimated H-index: 26
(CDER: Center for Drug Evaluation and Research)
Nonclinical studies of drug effects with human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) provide new possibilities for evaluating drug safety and efficacy. The Comprehensive In Vitro Proarrhythmia Assay (CiPA) paradigm provides lessons from the cardiac field that also apply to drug studies with other stem cell-based assays.
Published on May 12, 2017in Journal of Visualized Experiments1.11
Luca Sala4
Estimated H-index: 4
(LUMC: Leiden University Medical Center),
Dorien Ward-van Oostwaard23
Estimated H-index: 23
(LUMC: Leiden University Medical Center)
+ 2 AuthorsMilena Bellin19
Estimated H-index: 19
(LUMC: Leiden University Medical Center)
Cardiomyocytes can now be derived with high efficiency from both human embryonic and human induced-Pluripotent Stem Cells (hPSC). hPSC-derived cardiomyocytes (hPSC-CMs) are increasingly recognized as having great value for modeling cardiovascular diseases in humans, especially arrhythmia syndromes. They have also demonstrated relevance as in vitro systems for predicting drug responses, which makes them potentially useful for drug-screening and discovery, safety pharmacology and perhaps eventuall...
Published on Jan 30, 2017in eLife7.55
Francesca Stillitano8
Estimated H-index: 8
(ISMMS: Icahn School of Medicine at Mount Sinai),
Jens Hansen6
Estimated H-index: 6
(ISMMS: Icahn School of Medicine at Mount Sinai)
+ 15 AuthorsYannick Valogne1
Estimated H-index: 1
Common medications can disturb the electrical signals that cause the heart to beat, potentially resulting in sudden death. Many of the drugs that have these “cardiotoxic” effects were not designed to affect the heart, and include anti-allergenics and anti-vomiting drugs. In general, only a small proportion of individuals treated with these drugs will be at risk of fatal side effects; this risk variation is thought to be due to genetic differences. If these people could be reliably identified, th...
Cited By0
Newest
View next paperA Deep Learning Framework for Classification of in vitro Multi-Electrode Array Recordings.