Search

Patient-specific induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) offer an attractive experimental platform to investigate cardiac diseases and therapeutic outcome. In this study, iPSC-CMs were utilized to study their calcium transient signals and drug effects by means of machine learning, a central part of artificial intelligence. Drug effects were assessed in six iPSC-lines carrying different mutations causing catecholaminergic polymorphic ventricular tachycardia (CPVT), a highly malignant inherited arrhythmogenic disorder. The antiarrhythmic effect of dantrolene, an inhibitor of sarcoplasmic calcium release, was studied in iPSC-CMs after adrenaline, an adrenergic agonist, stimulation by machine learning analysis of calcium transient signals. First, beats of transient signals were identified with our peak recognition algorithm previously developed. Then 12 peak variables were computed for every identified peak of a signal and by means of this data signals were classified into different classes corresponding to those affected by adrenaline or, thereafter, affected by a drug, dantrolene. The best classification accuracy was approximately 79% indicating that machine learning methods can be utilized in analysis of iPSC-CM drug effects. In the future, data analysis of iPSC-CM drug effects together with machine learning methods can create a very valuable and efficient platform to individualize medication in addition to drug screening and cardiotoxicity studies.

Background Modeling human cardiac diseases with induced pluripotent stem cells not only enables to study disease pathophysiology and develop therapies but also, as we have previously showed, it can offer a tool for disease diagnostics. We previously observed that a few genetic cardiac diseases can be separated from each other and healthy controls by applying machine learning to Ca2+ transient signals measured from iPSC-derived cardiomyocytes (CMs). Objectives For the current research, 419 hypertrophic cardiomyopathy (HCM) transient signals and 228 long QT syndrome (LQTS) transient signals were measured. HCM signals included data recorded from iPSC-CMs carrying either α-tropomyosin, i.e., TPM1 (HCMT) or MYBPC3 or myosin-binding protein C (HCMM) mutation and LQTS signals included data recorded from iPSC-CMs carrying potassium voltage-gated channel subfamily Q member 1 (KCNQ1) mutation (long QT syndrome 1 [LQT1]) or KCNH2 mutation (long QT syndrome 2 [LQT2]). The main objective was to study whether and how effectively HCMM and HCMT can be separated from each other as well as LQT1 from LQT2. Methods After preprocessing those Ca2+ signals where we computed peak waveforms we then classified the two mutations of both disease pairs by using several different machine learning methods. Results We obtained excellent classification accuracies of 89% for HCM and even 100% for LQT at their best. Conclusion The results indicate that the methods applied would be efficient for the identification of these genetic cardiac diseases.

Human induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) have been shown to be useful to improve techniques that are developed for the study of cardiac disease. Abnormalities in Ca2+ transients are commonly present in iPSC-CMs derived from individuals with a cardiac disease. We previously observed that Ca2+ transient signals of healthy CMs can be distinguished from transients of CMs derived from individuals having different genetic cardiac diseases. Machine learning was used to distinguish different diseases from each other as well as from controls. We wanted further to investigate whether we are able to separate iPSC-CM Ca2+ signals of any genetic cardiac disease as one group from those of healthy individuals by utilizing machine learning methods. A total number of 593 CM transient signals from healthy individuals and from patients were analyzed. We obtained a best classification accuracy of 87% between the disease group and controls. This finding provides evidence that machine learning methods are efficient for identifying iPSC-CMs derived from individuals with a disease phenotype, and that iPSC-CMs may be useful to identify individuals at risk for a cardiac event. Keywords: Calcium transient profiles, Genetic cardiac diseases, Machine learning, Differentiation of the diseased from controls

Background Cardiomyocytes differentiated from human induced pluripotent stem cells (iPSC-CMs) can be used to study genetic cardiac diseases. In patients these diseases are manifested e.g. with impaired contractility and fatal cardiac arrhythmias, and both of these can be due to abnormal calcium transients in cardiomyocytes. Here we classify different genetic cardiac diseases using Ca2+ transient data and different machine learning algorithms. Methods By studying calcium cycling of disease-specific iPSC-CMs and by using calcium transients measured from these cells it is possible to classify diseases from each other and also from healthy controls by applying machine learning computation on the basis of peak attributes detected from calcium transient signals. Results In the current research we extend our previous study having Ca-transient data from four different genetic diseases by adding data from two additional diseases (dilated cardiomyopathy and long QT Syndrome 2). We also study, in the light of the current data, possible differences and relations when machine learning modelling and classification accuracies were computed by using either leave-one-out test or 10-fold cross-validation. Conclusions Despite more complex classification tasks compared to our earlier research and having more different genetic cardiac diseases in the analysis, it is still possible to attain good disease classification results. As excepted, leave-one-out test and 10-fold cross-validation achieved virtually equal results.

Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) have revolutionized cardiovascular research. Abnormalities in Ca2+ transients have been evident in many cardiac disease models. We have shown earlier that, by exploiting computational machine learning methods, normal Ca2+ transients corresponding to healthy CMs can be distinguished from diseased CMs with abnormal transients. Here our aim was to study whether it is possible to separate different genetic cardiac diseases (CPVT, LQT, HCM) on the basis of Ca2+ transients using machine learning methods. Classification accuracies of up to 87% were obtained for these three diseases, indicating that Ca2+ transients are disease-specific. By including healthy controls in the classifications, the best classification accuracy obtained was still high: approximately 79%. In conclusion, we demonstrate as the proof of principle that the computational machine learning methodology appears to be a powerful means to accurately categorize iPSC-CMs and could provide effective methods for diagnostic purposes in the future.

Mutations in the cardiac ryanodine receptor (RYR2) are the leading cause for catecholaminergic polymorphic ventricular tachycardia (CPVT). In this study, we evaluated antiarrhythmic efficacy of carvedilol and flecainide in CPVT patient-specific induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) carrying different mutations in RYR2. iPSC-CMs were generated from skin biopsies of CPVT patients carrying exon 3 deletion and L4115 or V4653F mutation in RYR2 and of a healthy individual. Ca2+ kinetics and drug effects were studied with Fluo-4 AM indicator. Carvedilol abolished Ca2+ abnormalities in 31% of L4115F, 36% of V4653F, and 46% of exon 3 deletion carrying CPVT cardiomyocytes and flecainide 33%, 30%, and 52%, respectively. Both drugs lowered the intracellular Ca2+ level and beating rate of the cardiomyocytes significantly. Moreover, flecainide caused abnormal Ca2+ transients in 61% of controls compared to 26% of those with carvedilol. Carvedilol and flecainide were equally effective in CPVT iPSC-CMs. However, flecainide induced arrhythmias in 61% of control cells. CPVT cardiomyocytes carrying the exon 3 deletion had the most severe Ca2+ abnormalities, but they had the best response to drug therapies. According to this study, the arrhythmia-abolishing effect of neither of the drugs is optimal. iPSC-CMs provide a unique platform for testing drugs for CPVT.

Aims Spontaneous Ca2+ release leads to afterdepolarizations and triggered arrhythmia in catecholaminergic polymorphic ventricular tachycardia (CPVT). Irregular Ca2+ release is hypothesized to manifest as slowed depolarization and irregular repolarization. Our goal was to study depolarization and repolarization abnormalities in CPVT, as they remain largely uninvestigated. Methods and results We studied intracellular Ca2+ handling and action potentials (APs) in an induced pluripotent stem cell (iPSC) model of CPVT. Induced pluripotent stem cell cardiomyocytes from a RyR2-P2328S patient showed increased non-alternating variability of Ca2+ transients in response to isoproterenol. β-Agonists decreased AP upslope velocity in CPVT cells and in monophasic AP recordings of CPVT patients. We compared 24 h electrocardiograms (ECGs) of 19 CPVT patients carrying RyR2 mutations and 19 healthy controls. Short-term variability (STV) of the QT interval was 6.9 ± 0.5 ms in CPVT patients vs. 5.5 ± 0.4 ms in controls ( P < 0.05) and associated with a history of arrhythmic events. Mean T-wave alternans (TWA) was 25 ± 1.4 µV in CPVT patients vs. 31 ± 2.0 µV in controls ( P < 0.05). Older CPVT patients showed lower maximal upslope velocity of the ECG R-spike than control patients. Conclusion Catecholaminergic polymorphic ventricular tachycardia patients show higher STV of repolarization but lower TWA on the 24 h ECG than control patients, which is likely to reflect increased non-alternating variability of Ca2+ release by mutant RyR2s as observed in vitro . β-Agonists slow depolarization in RyR2-mutant cells and in CPVT patients. These findings may constitute a marker of arrhythmogenicity.

Background Long QT syndrome (LQTS) is associated with increased risk of ventricular arrhythmias and cardiac arrest. LQTS type 1 (LQT1), the most prevalent subtype of LQTS, is caused by defects of slow delayed rectifier potassium current (I Ks ) that lead to abnormal cardiac repolarization. Here we used pluripotent stem cell (iPSC)-technology to investigate both the electrophysiological and also for the first time the mechanical beating behavior of genetically defined, LQT1 specific cardiomyocytes (CMs) carrying different mutations. Methods We established in vitro models for LQT1 caused by two mutations (G589D or ivs7-2A>G). LQT1 specific CMs were derived from patient specific iPSCs and characterized for their electrophysiology using a current clamp and Ca 2+ -imaging. Their mechanical beating characteristics were analyzed with video-image analysis method. Results and conclusions Both LQT1-CM-types showed prolonged repolarization, but only those with G589D presented early after-depolarizations at baseline. Increased amounts of abnormal Ca 2+ transients were detected in both types of LQT1-CMs. Surprisingly, also the mechanical beating behavior demonstrated clear abnormalities and additionally the abnormalities were different with the two mutations: prolonged contraction was seen in G589D-CMs while impaired relaxation was observed in ivs7-2A>G-CMs. The CMs carrying two different LQT1 specific mutations (G589D or ivs7-2A>G) presented clear differences in their electrical properties as well as in their mechanical beating behavior. Results from different methods correlated well with each other suggesting that simply mechanical beating behavior of CMs could be used for screening of diseased CMs and possibly for diagnostic purposes in the future.

Catecholaminergic polymorphic ventricular tachycardia (CPVT) is a highly malignant inherited arrhythmogenic disorder. Type 1 CPVT (CPVT1) is caused by cardiac ryanodine receptor (RyR2) gene mutations resulting in abnormal calcium release from sarcoplasmic reticulum. Dantrolene, an inhibitor of sarcoplasmic Ca(2+) release, has been shown to rescue this abnormal Ca(2+) release in vitro. We assessed the antiarrhythmic efficacy of dantrolene in six patients carrying various RyR2 mutations causing CPVT. The patients underwent exercise stress test before and after dantrolene infusion. Dantrolene reduced the number of premature ventricular complexes (PVCs) on average by 74% (range 33-97) in four patients with N-terminal or central mutations in the cytosolic region of the RyR2 protein, while dantrolene had no effect in two patients with mutations in or near the transmembrane domain. Induced pluripotent stem cells (iPSCs) were generated from all the patients and differentiated into spontaneously beating cardiomyocytes (CMs). The antiarrhythmic effect of dantrolene was studied in CMs after adrenaline stimulation by Ca(2+) imaging. In iPSC derived CMs with RyR2 mutations in the N-terminal or central region, dantrolene suppressed the Ca(2+) cycling abnormalities in 80% (range 65-97) of cells while with mutations in or near the transmembrane domain only in 23 or 32% of cells. In conclusion, we demonstrate that dantrolene given intravenously shows antiarrhythmic effects in a portion of CPVT1 patients and that iPSC derived CM models replicate these individual drug responses. These findings illustrate the potential of iPSC models to individualize drug therapy of inherited diseases.Trial Registration: EudraCT Clinical Trial Registry 2012-005292-14.

Induced pluripotent stem cell (iPSC) lines derived from skin fibroblasts of patients suffering from cardiac disorders were differentiated to cardiomyocytes and used to generate a data set of Ca(2+) transients of 136 recordings. The objective was to separate normal signals for later medical research from abnormal signals. We constructed a signal analysis procedure to detect peaks representing calcium cycling in signals and another procedure to classify them into either normal or abnormal peaks. Using machine learning methods we classified signals into normal or abnormal signals on the basis of peak findings in them. We compared classification results obtained to those made visually by an expert biotechnologist who assessed the signals independent of the computer method. Classification accuracies of around 85% indicated high congruence between two modes denoting the high capability and usefulness of computer based processing for the present data.

Comprehensive functioning of Ca2+ cycling is crucial for excitation-contraction coupling of cardiomyocytes (CMs). Abnormal Ca2+ cycling is linked to arrhythmogenesis, which is associated with cardiac disorders and heart failure. Accordingly, we have generated spontaneously beating CMs from induced pluripotent stem cells (iPSC) derived from patients with catecholaminergic polymorphic ventricular tachycardia (CPVT), which is an inherited and severe cardiac disease. Ca2+ cycling studies have revealed substantial abnormalities in these CMs. Ca2+ transient analysis performed manually lacks accepted analysis criteria, and has both low throughput and high variability. To overcome these issues, we have developed a software tool, AnomalyExplorer based on interactive visualization, to assist in the classification of Ca2+ transient patterns detected in CMs. Here, we demonstrate the usability and capability of the software, and we also compare the analysis efficiency to manual analysis. We show that AnomalyExplorer is suitable for detecting normal and abnormal Ca2+ transients; furthermore, this method provides more defined and consistent information regarding the Ca2+ abnormality patterns and cell line specific differences when compared to manual analysis. This tool will facilitate and speed up the analysis of CM Ca2+ transients, making it both more accurate and user-independent. AnomalyExplorer can be exploited in Ca2+ cycling analysis to study basic disease pathology and the effects of different drugs. Public Library of Science open access

In this preliminary research we examine the suitability of hierarchical strategies of multi-class support vector machines for classification of induced pluripotent stem cell (iPSC) colony images. The iPSC technology gives incredible possibilities for safe and patient specific drug therapy without any ethical problems. However, growing of iPSCs is a sensitive process and abnormalities may occur during the growing process. These abnormalities need to be recognized and the problem returns to image classification. We have a collection of 80 iPSC colony images where each one of the images is prelabeled by an expert to class bad, good or semigood. We use intensity histograms as features for classification and we evaluate histograms from the whole image and the colony area only having two datasets. We perform two feature reduction procedures for both datasets. In classification we examine how different hierarchical constructions effect the classification. We perform thorough evaluation and the best accuracy was around 54% obtained with the linear kernel function. Between different hierarchical structures, in many cases there are no significant changes in results. As a result, intensity histograms are a good baseline for the classification of iPSC colony images but more sophisticated feature extraction and reduction methods together with other classification methods need to be researched in future.

We often encounter experimental results that are difficult to quantify although the visual recognition of a phenomenon is apparent. We are able to detect patterns and features with our vision that are complex to specify algorithmically. This is because our brain has evolved into a powerful pattern matching machine. One important class of measurement results in medical research are signals that describe a cycling pattern of some phenomenon. In this work, we developed a software tool, Anomaly Explorer, to assist in classification of Ca 2+ signals emitted by cardiomyocytes. Anomaly Explorer was designed and implemented to analyze and classify Ca 2+ signals with criteria similar to the criteria used by laboratory personnel. The software tool is based on interactive visualization with a direct manipulation user interface. Our Anomaly Explorer has proven to be a valuable tool as it makes the analysis faster, more accurate, and person-independent. The definition of signal anomalies in terms of visual properties is more flexible than numerical or analytical specification. Our approach is not limited to the Ca 2+ signal analysis. The anomaly types are domain-specific, but the interaction and visualization ideas can be applied in any signal analysis problem.

Ca2+ signaling plays major role in cardiac contractility. Alterations in Ca2+ signaling can be seen in arrhythmogenesis associated with cardiac disorders and heart failures. By analyzing the Ca2+ cycling of cardiomyocytes with the help of Ca2+ imaging, basic cardiac functionality, cardiac disorders and drug responses can be studied more thoroughly. We have generated spontaneously beating cardiomyocytes from induced pluripotent stem cell lines derived from patients with different cardiac disorders. Ca2+ cycling studies have revealed substantial defects and abnormalities in calcium signaling of these cardiomyocytes, presumably reflecting the cardiac phenotype observed in the patients. Ca2+ signaling abnormalities can be seen as variable frequency and amplitude and they can be categorized by their form. The analysis of these abnormalities is extremely important to study and understand different cardiac diseases and drug responses. So far this analysis has been done manually by researcher without any generally accepted analysis criteria's. However this way of analysis is subjective and slow and repeatability of analysis may be poor. To overcome these issues, we have developed Ca2+ data analysis software based on interactive visualization. The Ca2+ data analysis software allows to explore and distinguish different Ca2+ signal patterns from recordings and categorize the abnormalities objectively. It will speed up the analysis of cardiomyocyte Ca2+ signals and provide a specific analysis criteria's to analyze Ca2+ abnormalities in cardiomyocytes. This analysis software can be exploited to study basic disease pathology, to screen drugs, and to optimize drug therapy in a patient-specific manner.