Machine learning plus optical flow: a simple and sensitive method to detect cardioactive drugs

Using induced pluripotent stem cells for drug discovery in arrhythmias

INTRODUCTION

Arrhythmias are disturbances in the normal rhythm of the heart and account for significant cardiovascular morbidity and mortality worldwide. Historically, preclinical research has been anchored in animal models, though physiological differences between these models and humans have limited their clinical translation. The discovery of human induced pluripotent stem cells (iPSC) and subsequent differentiation into cardiomyocyte has led to the development of new in vitro models of arrhythmias with the hope of a new pathway for both exploration of pathogenic variants and novel therapeutic discovery.

AREAS COVERED

The authors describe the latest two-dimensional in vitro models of arrhythmias, several examples of the use of these models in drug development, and the role of gene editing when modeling diseases. They conclude by discussing the use of three-dimensional models in the study of arrythmias and the integration of computational technologies and machine learning with experimental technologies.

EXPERT OPINION

Human iPSC-derived cardiomyocytes models have significant potential to augment disease modeling, drug discovery, and toxicity studies in preclinical development. While there is initial success with modeling arrhythmias, the field is still in its nascency and requires advances in maturation, cellular diversity, and readouts to emulate arrhythmias more accurately.

The use of artificial intelligence in induced pluripotent stem cell-based technology over 10-year period: A systematic scoping review

BACKGROUND

Stem cell research, particularly in the domain of induced pluripotent stem cell (iPSC) technology, has shown significant progress. The integration of artificial intelligence (AI), especially machine learning (ML) and deep learning (DL), has played a pivotal role in refining iPSC classification, monitoring cell functionality, and conducting genetic analysis. These enhancements are broadening the applications of iPSC technology in disease modelling, drug screening, and regenerative medicine. This review aims to explore the role of AI in the advancement of iPSC research.

METHODS

In December 2023, data were collected from three electronic databases (PubMed, Web of Science, and Science Direct) to investigate the application of AI technology in iPSC processing.

RESULTS

This systematic scoping review encompassed 79 studies that met the inclusion criteria. The number of research studies in this area has increased over time, with the United States emerging as a leading contributor in this field. AI technologies have been diversely applied in iPSC technology, encompassing the classification of cell types, assessment of disease-specific phenotypes in iPSC-derived cells, and the facilitation of drug screening using iPSC. The precision of AI methodologies has improved significantly in recent years, creating a foundation for future advancements in iPSC-based technologies.

CONCLUSIONS

Our review offers insights into the role of AI in regenerative and personalized medicine, highlighting both challenges and opportunities. Although still in its early stages, AI technologies show significant promise in advancing our understanding of disease progression and development, paving the way for future clinical applications.

Role of Machine Learning and Artificial Intelligence in Arrhythmias and Electrophysiology

Machine learning (ML), a subset of artificial intelligence (AI) centered on machines learning from extensive datasets, stands at the forefront of a technological revolution shaping various facets of society. Cardiovascular medicine has emerged as a key domain for ML applications, with considerable efforts to integrate these innovations into routine clinical practice. Within cardiac electrophysiology, ML applications, especially in the automated interpretation of electrocardiograms, have garnered substantial attention in existing literature. However, less recognized are the diverse applications of ML in cardiac electrophysiology and arrhythmias, spanning basic science research on arrhythmia mechanisms, both experimental and computational, as well as contributions to enhanced techniques for mapping cardiac electrical function and translational research related to arrhythmia management. This comprehensive review delves into various ML applications within the scope of this journal, organized into 3 parts. The first section provides a fundamental understanding of general ML principles and methodologies, serving as a foundational resource for readers interested in exploring ML applications in arrhythmia research. The second part offers an in-depth review of studies in arrhythmia and electrophysiology that leverage ML methodologies, showcasing the broad potential of ML approaches. Each subject is thoroughly outlined, accompanied by a review of notable ML research advancements. Finally, the review delves into the primary challenges and future perspectives surrounding ML-driven cardiac electrophysiology and arrhythmias research.

Advances in cardiac tissue engineering and heart-on-a-chip

Recent advances in both cardiac tissue engineering and hearts-on-a-chip are grounded in new biomaterial development as well as the employment of innovative fabrication techniques that enable precise control of the mechanical, electrical, and structural properties of the cardiac tissues being modelled. The elongated structure of cardiomyocytes requires tuning of substrate properties and application of biophysical stimuli to drive its mature phenotype. Landmark advances have already been achieved with induced pluripotent stem cell-derived cardiac patches that advanced to human testing. Heart-on-a-chip platforms are now commonly used by a number of pharmaceutical and biotechnology companies. Here, we provide an overview of cardiac physiology in order to better define the requirements for functional tissue recapitulation. We then discuss the biomaterials most commonly used in both cardiac tissue engineering and heart-on-a-chip, followed by the discussion of recent representative studies in both fields. We outline significant challenges common to both fields, specifically: scalable tissue fabrication and platform standardization, improving cellular fidelity through effective tissue vascularization, achieving adult tissue maturation, and ultimately developing cryopreservation protocols so that the tissues are available off the shelf.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

Automated Dual-Mode Cell Monitoring To Simultaneously Explore Calcium Dynamics and Contraction-Relaxation Kinetics within Drug-Treated Stem Cell-Derived Cardiomyocytes

This manuscript proposes a new dual-mode cell imaging system for studying the relationships between calcium dynamics and the contractility process of cardiomyocytes derived from human-induced pluripotent stem cells. Practically, this dual-mode cell imaging system provides simultaneously both live cell calcium imaging and quantitative phase imaging based on digital holographic microscopy. Specifically, thanks to the development of a robust automated image analysis, simultaneous measurements of both intracellular calcium, a key player of excitation-contraction coupling, and the quantitative phase image-derived dry mass redistribution, reflecting the effective contractility, namely, the contraction and relaxation processes, were achieved. Practically, the relationships between calcium dynamics and the contraction-relaxation kinetics were investigated in particular through the application of two drugs─namely, isoprenaline and E-4031─known to act precisely on calcium dynamics. Specifically, this new dual-mode cell imaging system enabled us to establish that calcium regulation can be divided into two phases, an early phase influencing the occurrence of the relaxation process followed by a late phase, which although not having a significant influence on the relaxation process affects significantly the beat frequency. In combination with cutting-edge technologies allowing the generation of human stem cell-derived cardiomyocytes, this dual-mode cell monitoring approach therefore represents a very promising technique, particularly in the fields of drug discovery and personalized medicine, to identify compounds likely to act more selectively on specific steps that compose the cardiomyocyte contractility.

Intersection of stem cell biology and engineering towards next generation in vitro models of human fibrosis

Human fibrotic diseases constitute a major health problem worldwide. Fibrosis involves significant etiological heterogeneity and encompasses a wide spectrum of diseases affecting various organs. To date, many fibrosis targeted therapeutic agents failed due to inadequate efficacy and poor prognosis. In order to dissect disease mechanisms and develop therapeutic solutions for fibrosis patients, in vitro disease models have gone a long way in terms of platform development. The introduction of engineered organ-on-a-chip platforms has brought a revolutionary dimension to the current fibrosis studies and discovery of anti-fibrotic therapeutics. Advances in human induced pluripotent stem cells and tissue engineering technologies are enabling significant progress in this field. Some of the most recent breakthroughs and emerging challenges are discussed, with an emphasis on engineering strategies for platform design, development, and application of machine learning on these models for anti-fibrotic drug discovery. In this review, we discuss engineered designs to model fibrosis and how biosensor and machine learning technologies combine to facilitate mechanistic studies of fibrosis and pre-clinical drug testing.

Integrating nonlinear analysis and machine learning for human induced pluripotent stem cell-based drug cardiotoxicity testing

Utilizing recent advances in human induced pluripotent stem cell (hiPSC) technology, nonlinear analysis and machine learning we can create novel tools to evaluate drug-induced cardiotoxicity on human cardiomyocytes. With cardiovascular disease remaining the leading cause of death globally it has become imperative to create effective and modern tools to test the efficacy and toxicity of drugs to combat heart disease. The calcium transient signals recorded from hiPSC-derived cardiomyocytes (hiPSC-CMs) are highly complex and dynamic with great degrees of response characteristics to various drug treatments. However, traditional linear methods often fail to capture the subtle variation in these signals generated by hiPSC-CMs. In this work, we integrated nonlinear analysis, dimensionality reduction techniques and machine learning algorithms for better classifying the contractile signals from hiPSC-CMs in response to different drug exposure. By utilizing extracted parameters from a commercially available high-throughput testing platform, we were able to distinguish the groups with drug treatment from baseline controls, determine the drug exposure relative to IC50 values, and classify the drugs by its unique cardiac responses. By incorporating nonlinear parameters computed by phase space reconstruction, we were able to improve our machine learning algorithm's ability to predict cardiotoxic levels and drug classifications. We also visualized the effects of drug treatment and dosages with dimensionality reduction techniques, t-distributed stochastic neighbor embedding (t-SNE). We have shown that integration of nonlinear analysis and artificial intelligence has proven to be a powerful tool for analyzing cardiotoxicity and classifying toxic compounds through their mechanistic action.

Beyond pharmaceuticals: Fit-for-purpose new approach methodologies for environmental cardiotoxicity testing

Environmental factors play a substantial role in determining cardiovascular health, but data informing the risks presented by environmental toxicants is insufficient. In vitro new approach methodologies (NAMs) offer a promising approach with which to address the limitations of traditional in vivo and in vitro assays for assessing cardiotoxicity. Driven largely by the needs of pharmaceutical toxicity testing, considerable progress in developing NAMs for cardiotoxicity analysis has already been made. As the scientific and regulatory interest in NAMs for environmental chemicals continues to grow, a thorough understanding of the unique features of environmental cardiotoxicants and their associated cardiotoxicities is needed. Here, we review the key characteristics of as well as important regulatory and biological considerations for fit-for-purpose NAMs for environmental cardiotoxicity. By emphasizing the challenges and opportunities presented by NAMs for environmental cardiotoxicity we hope to accelerate their development, acceptance, and application.

Induced Pluripotent Stem Cell-Based Drug Screening by Use of Artificial Intelligence

Induced pluripotent stem cells (iPSCs) are terminally differentiated somatic cells that differentiate into various cell types. iPSCs are expected to be used for disease modeling and for developing novel treatments because differentiated cells from iPSCs can recapitulate the cellular pathology of patients with genetic mutations. However, a barrier to using iPSCs for comprehensive drug screening is the difficulty of evaluating their pathophysiology. Recently, the accuracy of image analysis has dramatically improved with the development of artificial intelligence (AI) technology. In the field of cell biology, it has become possible to estimate cell types and states by examining cellular morphology obtained from simple microscopic images. AI can evaluate disease-specific phenotypes of iPS-derived cells from label-free microscopic images; thus, AI can be utilized for disease-specific drug screening using iPSCs. In addition to image analysis, various AI-based methods can be applied to drug development, including phenotype prediction by analyzing genomic data and virtual screening by analyzing structural formulas and protein-protein interactions of compounds. In the future, combining AI methods may rapidly accelerate drug discovery using iPSCs. In this review, we explain the details of AI technology and the application of AI for iPSC-based drug screening.

Moving Towards Induced Pluripotent Stem Cell-based Therapies with Artificial Intelligence and Machine Learning

The advent of induced pluripotent stem cell (iPSC) technology, which allows to transform one cell type into another, holds the promise to produce therapeutic cells and organs on demand. Realization of this objective is contingent on the ability to demonstrate quality and safety of the cellular product for its intended use. Bottlenecks and backlogs to the clinical use of iPSCs have been fully outlined and a need has emerged for safer and standardized protocols to trigger cell reprogramming and functional differentiation. Amidst great challenges, in particular associated with lengthy culture time and laborious cell characterization, a demand for faster and more accurate methods for the validation of cell identity and function at different stages of the iPSC manufacturing process has risen. Artificial intelligence-based methods are proving helpful for these complex tasks and might revolutionize the way iPSCs are managed to create surrogate cells and organs. Here, we briefly review recent progress in artificial intelligence approaches for evaluation of iPSCs and their derivatives in experimental studies.

Machine Learning Techniques to Classify Healthy and Diseased Cardiomyocytes by Contractility Profile

Cardiomyocytes derived from human induced pluripotent stem (iPS) cells enable the study of cardiac physiology and the developmental testing of new therapeutic drugs in a human setting. In parallel, machine learning methods are being applied to biomedical science in unprecedented ways. Machine learning has been used to distinguish healthy from diseased cardiomyocytes using calcium (Ca²⁺) transient signals. Most Ca²⁺ transient signals are obtained via terminal assays that do not permit longitudinal studies, although some recently developed options can circumvent these concerns. Here, we describe the use of machine learning to identify healthy and diseased cardiomyocytes according to their contractility profiles, which are derived from brightfield videos. This noncontact, label-free approach allows for the continued cultivation of cells after they have been evaluated for use in other assays and can be readily extended to organs-on-chip. To demonstrate utility, we assessed contractility profiles of cardiomyocytes obtained from patients with Timothy Syndrome (TS), a long QT disease which can lead to fatal arrhythmias, and from healthy individuals. The videos were processed and classified using machine learning methods and their performance was evaluated according to several parameters. The trained algorithms were able to distinguish the TS cardiomyocytes from healthy controls and classify two different healthy controls. The proposed computational machine learning evaluation of human iPS cell-derived cardiomyocytes' contractility profiles has the potential to identify other genetic proarrhythmic events, screen therapeutic agents for inducing or suppressing long QT events, and predict drug-target interactions. The same approach could be readily extended to the evaluation of engineered cardiac tissues within single-tissue and multi-tissue organs-on-chip.

Cells/colony motion of oral keratinocytes determined by non-invasive and quantitative measurement using optical flow predicts epithelial regenerative capacity

Cells/colony motion determined by non-invasive, quantitative measurements using the optical flow (OF) algorithm can indicate the oral keratinocyte proliferative capacity in early-phase primary cultures. This study aimed to determine a threshold for the cells/colony motion index to detect substandard cell populations in a subsequent subculture before manufacturing a tissue-engineered oral mucosa graft and to investigate the correlation with the epithelial regenerative capacity. The distinctive proliferating pattern of first-passage [passage 1 (p1)] cells reveals the motion of p1 cells/colonies, which can be measured in a non-invasive, quantitative manner using OF with fewer full-screen imaging analyses and cell segmentations. Our results demonstrate that the motion index lower than 40 μm/h reflects cellular damages by experimental metabolic challenges although this value shall only apply in case of our culture system. Nonetheless, the motion index can be used as the threshold to determine the quality of cultured cells while it may be affected by any different culture conditions. Because the p1 cells/colony motion index is correlated with epithelial regenerative capacity, it is a reliable index for quality control of oral keratinocytes.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

Comprehensive Cardiac Safety Assessment using hiPS-cardiomyocytes (Consortium for Safety Assessment using Human iPS Cells: CSAHi)

Current cardiac safety assessment platforms (in vitro hERG-centric, APD, and/or in vivo animal QT assays) are not fully predictive of drug-induced Torsades de Pointes (TdP) and do not address other mechanism-based arrhythmia, including ventricular tachycardia or ventricular fibrillation, or cardiac safety liabilities such as contractile and structural cardiotoxicity which are another growing safety concerns. We organized the Consortium for Safety Assessment using Human iPS cells (CSAHi; http://csahi.org/en/) in 2013, based on the Japan Pharmaceutical Manufacturers Association (JPMA), to verify the application of human iPS/ES cell-derived cardiomyocytes for drug safety evaluation. The CSAHi HEART team focused on comprehensive screening strategies to predict a diverse range of cardiotoxicities using recently introduced platforms such as the Multi-Electrode Array (MEA), cellular impedance, Motion Field Imaging (MFI), and optical imaging of Ca transient to identify strengths and weaknesses of each platform. Our study showed that hiPS-CMs used in these platforms could detect pharmacological responses that were more relevant to humans compared to existing hERG, APD, or Langendorff (MAPD/contraction) assays. Further, MEA and other methods such as impedance, MFI, and Ca transient assays provided paradigm changes of platforms for predicting drug-induced QT risk and/or arrhythmia or contractile dysfunctions. In contrast, since discordances such as overestimation (false positive) of arrhythmogenicity, oversight, or opposite conclusions in positive inotropic and negative chronotropic activities to some compounds were also confirmed, possibly due to their functional immaturity of hiPS-CMs, hiPS-CMs should be used in these platforms for cardiac safety assessment based upon their advantages and disadvantages.

Cardiac tissue engineering: state-of-the-art methods and outlook

The purpose of this review is to assess the state-of-the-art fabrication methods, advances in genome editing, and the use of machine learning to shape the prospective growth in cardiac tissue engineering. Those interdisciplinary emerging innovations would move forward basic research in this field and their clinical applications. The long-entrenched challenges in this field could be addressed by novel 3-dimensional (3D) scaffold substrates for cardiomyocyte (CM) growth and maturation. Stem cell-based therapy through genome editing techniques can repair gene mutation, control better maturation of CMs or even reveal its molecular clock. Finally, machine learning and precision control for improvements of the construct fabrication process and optimization in tissue-specific clonal selections with an outlook of cardiac tissue engineering are also presented.

SarcTrack

RATIONALE

Human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs) in combination with CRISPR/Cas9 genome editing provide unparalleled opportunities to study cardiac biology and disease. However, sarcomeres, the fundamental units of myocyte contraction, are immature and nonlinear in hiPSC-CMs, which technically challenge accurate functional interrogation of contractile parameters in beating cells. Furthermore, existing analysis methods are relatively low-throughput, indirectly assess contractility, or only assess well-aligned sarcomeres found in mature cardiac tissues.

OBJECTIVE

We aimed to develop an analysis platform that directly, rapidly, and automatically tracks sarcomeres in beating cardiomyocytes. The platform should assess sarcomere content, contraction and relaxation parameters, and beat rate.

METHODS AND RESULTS

We developed SarcTrack, a MatLab software that monitors fluorescently tagged sarcomeres in hiPSC-CMs. The algorithm determines sarcomere content, sarcomere length, and returns rates of sarcomere contraction and relaxation. By rapid measurement of hundreds of sarcomeres in each hiPSC-CM, SarcTrack provides large data sets for robust statistical analyses of multiple contractile parameters. We validated SarcTrack by analyzing drug-treated hiPSC-CMs, confirming the contractility effects of compounds that directly activate (CK-1827452) or inhibit (MYK-461) myosin molecules or indirectly alter contractility (verapamil and propranolol). SarcTrack analysis of hiPSC-CMs carrying a heterozygous truncation variant in the myosin-binding protein C ( MYBPC3) gene, which causes hypertrophic cardiomyopathy, recapitulated seminal disease phenotypes including cardiac hypercontractility and diminished relaxation, abnormalities that normalized with MYK-461 treatment.

CONCLUSIONS

SarcTrack provides a direct and efficient method to quantitatively assess sarcomere function. By improving existing contractility analysis methods and overcoming technical challenges associated with functional evaluation of hiPSC-CMs, SarcTrack enhances translational prospects for sarcomere-regulating therapeutics and accelerates interrogation of human cardiac genetic variants.

The influence of hERG1a and hERG1b isoforms on drug safety screening in iPSC-CMs

The human Ether-à-go-go Related Gene (hERG) encodes the pore forming subunit of the channel that conducts the rapid delayed rectifier potassium current I_Kr. I_Kr drives repolarization in the heart and when I_Kr is dysfunctional, cardiac repolarization delays, the QT interval on the electrocardiogram (ECG) prolongs and the risk of developing lethal arrhythmias such as Torsade de Pointes (TdP) increases. TdP risk is incorporated in drug safety screening for cardiotoxicity where hERG is the main target since the I_Kr channels appear highly sensitive to blockage. hERG block is also included as an important read-out in the Comprehensive in Vitro Proarrhythmia Assay (CiPA) initiative which aims to combine in vitro and in silico experiments on induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) to screen for cardiotoxicity. However, the hERG channel has some unique features to consider for drug safety screening, which we will discuss in this study. The hERG channel consists of different isoforms, hERG1a and hERG1b, which individually influence the kinetics of the channel and the drug response in the human heart and in iPSC-CMs. hERG1b is often underappreciated in iPSC-CM studies, drug screening assays and in silico models, and the fact that its contribution might substantially differ between iPSC-CM and healthy but also diseased human heart, adds to this problem. In this study we show that the activation kinetics in iPSC-CMs resemble hERG1b kinetics using Cs⁺ as a charge carrier. Not including hERG1b in drug safety testing might underestimate the actual role of hERG1b in repolarization and drug response, and might lead to inappropriate conclusions. We stress to focus more on including hERG1b in drug safety testing concerning I_Kr.

Manipulation-free cultures of human iPSC-derived cardiomyocytes offer a novel screening method for cardiotoxicity

Induced pluripotent stem cell (iPSC)-based cardiac regenerative medicine requires the efficient generation, structural soundness and proper functioning of mature cardiomyocytes, derived from the patient's somatic cells. The most important functional property of cardiomyocytes is the ability to contract. Currently available methods routinely used to test and quantify cardiomyocyte function involve techniques that are labor-intensive, invasive, require sophisticated instruments or can adversely affect cell vitality. We recently developed optical flow imaging method analyses and quantified cardiomyocyte contractile kinetics from video microscopic recordings without compromising cell quality. Specifically, our automated particle image velocimetry (PIV) analysis of phase-contrast video images captured at a high frame rate yields statistical measures characterizing the beating frequency, amplitude, average waveform and beat-to-beat variations. Thus, it can be a powerful assessment tool to monitor cardiomyocyte quality and maturity. Here we demonstrate the ability of our analysis to characterize the chronotropic responses of human iPSC-derived cardiomyocytes to a panel of ion channel modulators and also to doxorubicin, a chemotherapy agent with known cardiotoxic side effects. We conclude that the PIV-derived beat patterns can identify the elongation or shortening of specific phases in the contractility cycle, and the obtained chronotropic responses are in accord with known clinical outcomes. Hence, this system can serve as a powerful tool to screen the new and currently available pharmacological compounds for cardiotoxic effects.

Quantitatively characterizing drug-induced arrhythmic contractile motions of human stem cell-derived cardiomyocytes

Quantification of abnormal contractile motions of cardiac tissue has been a noteworthy challenge and significant limitation in assessing and classifying the drug-induced arrhythmias (i.e., Torsades de pointes). To overcome these challenges, researchers have taken advantage of computational image processing tools to measure contractile motion from cardiomyocytes derived from human induced pluripotent stem cells (hiPSC-CMs). However, the amplitude and frequency analysis of contractile motion waveforms does not produce sufficient information to objectively classify the degree of variations between two or more sets of cardiac contractile motions. In this paper, we generated contractile motion data from beating hiPSC-CMs using motion tracking software based on optical flow analysis, and then implemented a computational algorithm, phase space reconstruction (PSR), to derive parameters (embedding, regularity, and fractal dimensions) to further characterize the dynamic nature of the cardiac contractile motions. Application of drugs known to cause cardiac arrhythmia induced significant changes to these resultant dimensional parameters calculated from PSR analysis. Integrating this new computational algorithm with the existing analytical toolbox of cardiac contractile motions will allow us to expand current assessments of cardiac tissue physiology into an automated, high-throughput, and quantifiable manner which will allow more objective assessments of drug-induced proarrhythmias.

Human Induced Pluripotent Stem Cell-Derived Endothelial Cells for Three-Dimensional Microphysiological Systems

Microphysiological systems (MPS), or "organ-on-a-chip" platforms, aim to recapitulate in vivo physiology using small-scale in vitro tissue models of human physiology. While significant efforts have been made to create vascularized tissues, most reports utilize primary endothelial cells that hinder reproducibility. In this study, we report the use of human induced pluripotent stem cell-derived endothelial cells (iPS-ECs) in developing three-dimensional (3D) microvascular networks. We established a CDH5-mCherry reporter iPS cell line, which expresses the vascular endothelial (VE)-cadherin fused to mCherry. The iPS-ECs demonstrate physiological functions characteristic of primary endothelial cells in a series of in vitro assays, including permeability, response to shear stress, and the expression of endothelial markers (CD31, von Willibrand factor, and endothelial nitric oxide synthase). The iPS-ECs form stable, perfusable microvessels over the course of 14 days when cultured within 3D microfluidic devices. We also demonstrate that inhibition of TGF-β signaling improves vascular network formation by the iPS-ECs. We conclude that iPS-ECs can be a source of endothelial cells in MPS providing opportunities for human disease modeling and improving the reproducibility of 3D vascular networks.

Reflective lens-free imaging on high-density silicon microelectrode arrays for monitoring and evaluation of in vitro cardiac contractility

The high rate of drug attrition caused by cardiotoxicity is a major challenge for drug development. Here, we developed a reflective lens-free imaging (RLFI) approach to non-invasively record in vitro cell deformation in cardiac monolayers with high temporal (169 fps) and non-reconstructed spatial resolution (352 µm) over a field-of-view of maximally 57 mm². The method is compatible with opaque surfaces and silicon-based devices. Further, we demonstrated that the system can detect the impairment of both contractility and fast excitation waves in cardiac monolayers. Additionally, the RLFI device was implemented on a CMOS-based microelectrode array to retrieve multi-parametric information of cardiac cells, thereby offering more in-depth analysis of drug-induced (cardiomyopathic) effects for preclinical cardiotoxicity screening applications.

Generation of spatial-patterned early-developing cardiac organoids using human pluripotent stem cells

The creation of human induced pluripotent stem cells (hiPSCs) has provided an unprecedented opportunity to study tissue morphogenesis and organ development through 'organogenesis-in-a-dish'. Current approaches to cardiac organoid engineering rely on either direct cardiac differentiation from embryoid bodies (EBs) or generation of aligned cardiac tissues from predifferentiated cardiomyocytes from monolayer hiPSCs. To experimentally model early cardiac organogenesis in vitro, our protocol combines biomaterials-based cell patterning with stem cell organoid engineering. 3D cardiac microchambers are created from 2D hiPSC colonies; these microchambers approximate an early-development heart with distinct spatial organization and self-assembly. With proper training in photolithography microfabrication, maintenance of human pluripotent stem cells, and cardiac differentiation, a graduate student with guidance will likely be able to carry out this experimental protocol, which requires ∼3 weeks. We envisage that this in vitro model of human early heart development could serve as an embryotoxicity screening assay in drug discovery, regulation, and prescription for healthy fetal development. We anticipate that, when applied to hiPSC lines derived from patients with inherited diseases, this protocol can be used to study the disease mechanisms of cardiac malformations at an early stage of embryogenesis.

Machine learning in cardiovascular medicine: are we there yet?

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine.

Stem Cell-Based Methods to Predict Developmental Chemical Toxicity

Human pluripotent stem cells such as embryonic stem (ES) and induced pluripotent stem (iPS) cells, combined with sophisticated bioinformatics methods, are powerful tools to predict developmental chemical toxicity. Because cell differentiation is not necessary, these cells can facilitate cost-effective assays, thus providing a practical system for the toxicity assessment of various types of chemicals. Here we describe how to apply machine learning techniques to different types of data, such as qRT-PCRs, gene networks, and molecular descriptors, for toxic chemicals, as well as how to integrate these data to predict toxicity categories. Interestingly, our results using 20 chemical data for neurotoxins (NTs), genotoxic carcinogens (GCs), and nongenotoxic carcinogens (NGCs) demonstrated that the highest and most robust prediction performance was obtained by using gene networks as the input. We also observed that qRT-PCR and molecular descriptors tend to contribute to specific toxicity categories.

Machine Learning of Human Pluripotent Stem Cell-Derived Engineered Cardiac Tissue Contractility for Automated Drug Classification

Accurately predicting cardioactive effects of new molecular entities for therapeutics remains a daunting challenge. Immense research effort has been focused toward creating new screening platforms that utilize human pluripotent stem cell (hPSC)-derived cardiomyocytes and three-dimensional engineered cardiac tissue constructs to better recapitulate human heart function and drug responses. As these new platforms become increasingly sophisticated and high throughput, the drug screens result in larger multidimensional datasets. Improved automated analysis methods must therefore be developed in parallel to fully comprehend the cellular response across a multidimensional parameter space. Here, we describe the use of machine learning to comprehensively analyze 17 functional parameters derived from force readouts of hPSC-derived ventricular cardiac tissue strips (hvCTS) electrically paced at a range of frequencies and exposed to a library of compounds. A generated metric is effective for then determining the cardioactivity of a given drug. Furthermore, we demonstrate a classification model that can automatically predict the mechanistic action of an unknown cardioactive drug.

Plasma free reversible and irreversible microfluidic bonding

We demonstrate a facile, plasma free process to fabricate both reversibly and irreversibly sealed microfluidic chips using a PDMS-based adhesive polymer mixture. This is a versatile method that is compatible with current PDMS microfluidics processes. It allows for easier fabrication of multilayer microfluidic devices and is compatible with micropatterning of proteins for cell culturing. When combined with our Shrinky-Dink microfluidic prototyping, complete microfluidic device fabrication can be performed without the need for any capital equipment, making microfluidics accessible to the classroom.

High throughput physiological screening of iPSC-derived cardiomyocytes for drug development

Cardiac drug discovery is hampered by the reliance on non-human animal and cellular models with inadequate throughput and physiological fidelity to accurately identify new targets and test novel therapeutic strategies. Similarly, adverse drug effects on the heart are challenging to model, contributing to costly failure of drugs during development and even after market launch. Human induced pluripotent stem cell derived cardiac tissue represents a potentially powerful means to model aspects of heart physiology relevant to disease and adverse drug effects, providing both the human context and throughput needed to improve the efficiency of drug development. Here we review emerging technologies for high throughput measurements of cardiomyocyte physiology, and comment on the promises and challenges of using iPSC-derived cardiomyocytes to model disease and introduce the human context into early stages of drug discovery. This article is part of a Special Issue entitled: Cardiomyocyte biology: Integration of Developmental and Environmental Cues in the Heart edited by Marcus Schaub and Hughes Abriel.

Methods for in vitro functional analysis of iPSC derived cardiomyocytes - Special focus on analyzing the mechanical beating behavior

A rapidly increasing number of papers describing novel iPSC models for cardiac diseases are being published. To be able to understand the disease mechanisms in more detail, we should also take the full advantage of the various methods for analyzing these cell models. The traditionally and commonly used electrophysiological analysis methods have been recently accompanied by novel approaches for analyzing the mechanical beatingbehavior of the cardiomyocytes. In this review, we provide first a concise overview on the methodology for cardiomyocyte functional analysis and then concentrate on the video microscopy, which provides a promise for a new faster yet reliable method for cardiomyocyte functional analysis. We also show how analysis conditions may affect the results. Development of the methodology not only serves the basic research on the disease models, but could also provide the much needed efficient early phase screening method for cardiac safety toxicology. This article is part of a Special Issue entitled: Cardiomyocyte Biology: Integration of Developmental and Environmental Cues in the Heart edited by Marcus Schaub and Hughes Abriel.