Learning epistatic polygenic phenotypes with Boolean interactions.

Detecting epistatic drivers of human phenotypes is a considerable challenge. Traditional approaches use regression to sequentially test multiplicative interaction terms involving pairs of genetic variants. For higher-order interactions and genome-wide large-scale data, this strategy is computationally intractable. Moreover, multiplicative terms used in regression modeling may not capture the form of biological interactions. Building on the Predictability, Computability, Stability (PCS) framework, we introduce the epiTree pipeline to extract higher-order interactions from genomic data using tree-based models. The epiTree pipeline first selects a set of variants derived from tissue-specific estimates of gene expression. Next, it uses iterative random forests (iRF) to search training data for candidate Boolean interactions (pairwise and higher-order). We derive significance tests for interactions, based on a stabilized likelihood ratio test, by simulating Boolean tree-structured null (no epistasis) and alternative (epistasis) distributions on hold-out test data. Finally, our pipeline computes PCS epistasis p-values that probabilisticly quantify improvement in prediction accuracy via bootstrap sampling on the test set. We validate the epiTree pipeline in two case studies using data from the UK Biobank: predicting red hair and multiple sclerosis (MS). In the case of predicting red hair, epiTree recovers known epistatic interactions surrounding MC1R and novel interactions, representing non-linearities not captured by logistic regression models. In the case of predicting MS, a more complex phenotype than red hair, epiTree rankings prioritize novel interactions surrounding HLA-DRB1, a variant previously associated with MS in several populations. Taken together, these results highlight the potential for epiTree rankings to help reduce the design space for follow up experiments.

Novel Techniques in Imaging Congenital Heart Disease: JACC Scientific Statement.

Recent years have witnessed exponential growth in cardiac imaging technologies, allowing better visualization of complex cardiac anatomy and improved assessment of physiology. These advances have become increasingly important as more complex surgical and catheter-based procedures are evolving to address the needs of a growing congenital heart disease population. This state-of-the-art review presents advances in echocardiography, cardiac magnetic resonance, cardiac computed tomography, invasive angiography, 3-dimensional modeling, and digital twin technology. The paper also highlights the integration of artificial intelligence with imaging technology. While some techniques are in their infancy and need further refinement, others have found their way into clinical workflow at well-resourced centers. Studies to evaluate the clinical value and cost-effectiveness of these techniques are needed. For techniques that enhance the value of care for congenital heart disease patients, resources will need to be allocated for education and training to promote widespread implementation.

Epistasis regulates genetic control of cardiac hypertrophy.

The combinatorial effect of genetic variants is often assumed to be additive. Although genetic variation can clearly interact non-additively, methods to uncover epistatic relationships remain in their infancy. We develop low-signal signed iterative random forests to elucidate the complex genetic architecture of cardiac hypertrophy. We derive deep learning-based estimates of left ventricular mass from the cardiac MRI scans of 29,661 individuals enrolled in the UK Biobank. We report epistatic genetic variation including variants close to CCDC141, IGF1R, TTN, and TNKS. Several loci not prioritized by univariate genome-wide association analysis are identified. Functional genomic and integrative enrichment analyses reveal a complex gene regulatory network in which genes mapped from these loci share biological processes and myogenic regulatory factors. Through a network analysis of transcriptomic data from 313 explanted human hearts, we show that these interactions are preserved at the level of the cardiac transcriptome. We assess causality of epistatic effects via RNA silencing of gene-gene interactions in human induced pluripotent stem cell-derived cardiomyocytes. Finally, single-cell morphology analysis using a novel high-throughput microfluidic system shows that cardiomyocyte hypertrophy is non-additively modifiable by specific pairwise interactions between CCDC141 and both TTN and IGF1R. Our results expand the scope of genetic regulation of cardiac structure to epistasis.

Epistasis regulates genetic control of cardiac hypertrophy.

The combinatorial effect of genetic variants is often assumed to be additive. Although genetic variation can clearly interact non-additively, methods to uncover epistatic relationships remain in their infancy. We develop low-signal signed iterative random forests to elucidate the complex genetic architecture of cardiac hypertrophy. We derive deep learning-based estimates of left ventricular mass from the cardiac MRI scans of 29,661 individuals enrolled in the UK Biobank. We report epistatic genetic variation including variants close to CCDC141, IGF1R, TTN, and TNKS. Several loci not prioritized by univariate genome-wide association analysis are identified. Functional genomic and integrative enrichment analyses reveal a complex gene regulatory network in which genes mapped from these loci share biological processes and myogenic regulatory factors. Through a network analysis of transcriptomic data from 313 explanted human hearts, we show that these interactions are preserved at the level of the cardiac transcriptome. We assess causality of epistatic effects via RNA silencing of gene-gene interactions in human induced pluripotent stem cell-derived cardiomyocytes. Finally, single-cell morphology analysis using a novel high-throughput microfluidic system shows that cardiomyocyte hypertrophy is non-additively modifiable by specific pairwise interactions between CCDC141 and both TTN and IGF1R. Our results expand the scope of genetic regulation of cardiac structure to epistasis.

Principles for Health Information Collection, Sharing, and Use: A Policy Statement From the American Heart Association.

The evolution of the electronic health record, combined with advances in data curation and analytic technologies, increasingly enables data sharing and harmonization. Advances in the analysis of health-related and health-proxy information have already accelerated research discoveries and improved patient care. This American Heart Association policy statement discusses how broad data sharing can be an enabling driver of progress by providing data to develop, test, and benchmark innovative methods, scalable insights, and potential new paradigms for data storage and workflow. Along with these advances come concerns about the sensitive nature of some health data, equity considerations about the involvement of historically excluded communities, and the complex intersection of laws attempting to govern behavior. Data-sharing principles are therefore necessary across a wide swath of entities, including parties who collect health information, funders, researchers, patients, legislatures, commercial companies, and regulatory departments and agencies. This policy statement outlines some of the key equity and legal background relevant to health data sharing and responsible management. It then articulates principles that will guide the American Heart Association's engagement in public policy related to data collection, sharing, and use to continue to inform its work across the research enterprise, as well as specific examples of how these principles might be applied in the policy landscape. The goal of these principles is to improve policy to support the use or reuse of health information in ways that are respectful of patients and research participants, equitable in impact in terms of both risks and potential benefits, and beneficial across broad and demographically diverse communities in the United States.

Proceedings of the NHLBI Workshop on Artificial Intelligence in Cardiovascular Imaging: Translation to Patient Care.

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

ChatGPT Helped Me Write This Talk Title, but Can It Read an Echocardiogram?

While multidisciplinary collaboration in echocardiography is not new, machine learning has the potential to further improve it. In this transcript of the ASE 2023 Annual Feigenbaum lecture, advancements in foundation models are discussed, including their advantages, current disadvantages, and future potential for echocardiography.

ENRICHing medical imaging training sets enables more efficient machine learning.

OBJECTIVE: Deep learning (DL) has been applied in proofs of concept across biomedical imaging, including across modalities and medical specialties. Labeled data are critical to training and testing DL models, but human expert labelers are limited. In addition, DL traditionally requires copious training data, which is computationally expensive to process and iterate over. Consequently, it is useful to prioritize using those images that are most likely to improve a model's performance, a practice known as instance selection. The challenge is determining how best to prioritize. It is natural to prefer straightforward, robust, quantitative metrics as the basis for prioritization for instance selection. However, in current practice, such metrics are not tailored to, and almost never used for, image datasets. MATERIALS AND METHODS: To address this problem, we introduce ENRICH-Eliminate Noise and Redundancy for Imaging Challenges-a customizable method that prioritizes images based on how much diversity each image adds to the training set. RESULTS: First, we show that medical datasets are special in that in general each image adds less diversity than in nonmedical datasets. Next, we demonstrate that ENRICH achieves nearly maximal performance on classification and segmentation tasks on several medical image datasets using only a fraction of the available images and without up-front data labeling. ENRICH outperforms random image selection, the negative control. Finally, we show that ENRICH can also be used to identify errors and outliers in imaging datasets. CONCLUSIONS: ENRICH is a simple, computationally efficient method for prioritizing images for expert labeling and use in DL.

Domain-guided data augmentation for deep learning on medical imaging.

While domain-specific data augmentation can be useful in training neural networks for medical imaging tasks, such techniques have not been widely used to date. Our objective was to test whether domain-specific data augmentation is useful for medical imaging using a well-benchmarked task: view classification on fetal ultrasound FETAL-125 and OB-125 datasets. We found that using a context-preserving cut-paste strategy, we could create valid training data as measured by performance of the resulting trained model on the benchmark test dataset. When used in an online fashion, models trained on this hybrid data performed similarly to those trained using traditional data augmentation (FETAL-125 F-score 85.33 ± 0.24 vs 86.89 ± 0.60, p-value 0.014; OB-125 F-score 74.60 ± 0.11 vs 72.43 ± 0.62, p-value 0.004). Furthermore, the ability to perform augmentations during training time, as well as the ability to apply chosen augmentations equally across data classes, are important considerations in designing a bespoke data augmentation. Finally, we provide open-source code to facilitate running bespoke data augmentations in an online fashion. Taken together, this work expands the ability to design and apply domain-guided data augmentations for medical imaging tasks.

Gender-based time discrepancy in diagnosis of coronary artery disease based on data analytics of electronic medical records.

Background: Women continue to have worse Coronary Artery Disease (CAD) outcomes than men. The causes of this discrepancy have yet to be fully elucidated. The main objective of this study is to detect gender discrepancies in the diagnosis and treatment of CAD. Methods: We used data analytics to risk stratify ~32,000 patients with CAD of the total 960,129 patients treated at the UCSF Medical Center over an 8 year period. We implemented a multidimensional data analytics framework to trace patients from admission through treatment to create a path of events. Events are any medications or noninvasive and invasive procedures. The time between events for a similar set of paths was calculated. Then, the average waiting time for each step of the treatment was calculated. Finally, we applied statistical analysis to determine differences in time between diagnosis and treatment steps for men and women. Results: There is a significant time difference from the first time of admission to diagnostic Cardiac Catheterization between genders (p-value = 0.000119), while the time difference from diagnostic Cardiac Catheterization to CABG is not statistically significant. Conclusion: Women had a significantly longer interval between their first physician encounter indicative of CAD and their first diagnostic cardiac catheterization compared to men. Avoiding this delay in diagnosis may provide more timely treatment and a better outcome for patients at risk. Finally, we conclude by discussing the impact of the study on improving patient care with early detection and managing individual patients at risk of rapid progression of CAD.

Visualizing omicron: COVID-19 deaths vs. cases over time.

For most of the COVID-19 pandemic, the daily focus has been on the number of cases, and secondarily, deaths. The most recent wave was caused by the omicron variant, first identified at the end of 2021 and the dominant variant through the first part of 2022. South Africa, one of the first countries to experience and report data regarding omicron (variant 21.K), reported far fewer deaths, even as the number of reported cases rapidly eclipsed previous peaks. However, as the omicron wave has progressed, time series show that it has been markedly different from prior waves. To more readily visualize the dynamics of cases and deaths, it is natural to plot deaths per million against cases per million. Unlike the time-series plots of cases or deaths that have become daily features of pandemic updates during the pandemic, which have time as the x-axis, in a plot of deaths vs. cases, time is implicit, and is indicated in relation to the starting point. Here we present and briefly examine such plots from a number of countries and from the world as a whole, illustrating how they summarize features of the pandemic in ways that illustrate how, in most places, the omicron wave is very different from those that came before. Code for generating these plots for any country is provided in an automatically updating GitHub repository.

Development and Validation of a Deep Learning Strategy for Automated View Classification of Pediatric Focused Assessment With Sonography for Trauma.

OBJECTIVE: Pediatric focused assessment with sonography for trauma (FAST) is a sequence of ultrasound views rapidly performed by clinicians to diagnose hemorrhage. A technical limitation of FAST is the lack of expertise to consistently acquire all required views. We sought to develop an accurate deep learning view classifier using a large heterogeneous dataset of clinician-performed pediatric FAST. METHODS: We developed and conducted a retrospective cohort analysis of a deep learning view classifier on real-world FAST studies performed on injured children less than 18 years old in two pediatric emergency departments by 30 different clinicians. FAST was randomly distributed to training, validation, and test datasets, 70:20:10; each child was represented in only one dataset. The primary outcome was view classifier accuracy for video clips and still frames. RESULTS: There were 699 FAST studies, representing 4925 video clips and 1,062,612 still frames, performed by 30 different clinicians. The overall classification accuracy was 97.8% (95% confidence interval [CI]: 96.0-99.0) for video clips and 93.4% (95% CI: 93.3-93.6) for still frames. Per view still frames were classified with an accuracy: 96.0% (95% CI: 95.9-96.1) cardiac, 99.8% (95% CI: 99.8-99.8) pleural, 95.2% (95% CI: 95.0-95.3) abdominal upper quadrants, and 95.9% (95% CI: 95.8-96.0) suprapubic. CONCLUSION: A deep learning classifier can accurately predict pediatric FAST views. Accurate view classification is important for quality assurance and feasibility of a multi-stage deep learning FAST model to enhance the evaluation of injured children.

Mitral Valve Atlas for Artificial Intelligence Predictions of MitraClip Intervention Outcomes.

Severe mitral regurgitation (MR) is a cardiac disease that can lead to fatal consequences. MitraClip (MC) intervention is a percutaneous procedure whereby the mitral valve (MV) leaflets are connected along the edge using MCs. The outcomes of the MC intervention are not known in advance, i.e., the outcomes are quite variable. Artificial intelligence (AI) can be used to guide the cardiologist in selecting optimal MC scenarios. In this study, we describe an atlas of shapes as well as different scenarios for MC implantation for such an AI analysis. We generated the MV geometrical data from three different sources. First, the patients' 3-dimensional echo images were used. The pixel data from six key points were obtained from three views of the echo images. Using PyGem, an open-source morphing library in Python, these coordinates were used to create the geometry by morphing a template geometry. Second, the dimensions of the MV, from the literature were used to create data. Third, we used machine learning methods, principal component analysis, and generative adversarial networks to generate more shapes. We used the finite element (FE) software ABAQUS to simulate smoothed particle hydrodynamics in different scenarios for MC intervention. The MR and stresses in the leaflets were post-processed. Our physics-based FE models simulated the outcomes of MC intervention for different scenarios. The MR and stresses in the leaflets were computed by the FE models for a single clip at different locations as well as two and three clips. Results from FE simulations showed that the location and number of MCs affect subsequent residual MR, and that leaflet stresses do not follow a simple pattern. Furthermore, FE models need several hours to provide the results, and they are not applicable for clinical usage where the predicted outcomes of MC therapy are needed in real-time. In this study, we generated the required dataset for the AI models which can provide the results in a matter of seconds.

An ensemble of neural networks provides expert-level prenatal detection of complex congenital heart disease.

Congenital heart disease (CHD) is the most common birth defect. Fetal screening ultrasound provides five views of the heart that together can detect 90% of complex CHD, but in practice, sensitivity is as low as 30%. Here, using 107,823 images from 1,326 retrospective echocardiograms and screening ultrasounds from 18- to 24-week fetuses, we trained an ensemble of neural networks to identify recommended cardiac views and distinguish between normal hearts and complex CHD. We also used segmentation models to calculate standard fetal cardiothoracic measurements. In an internal test set of 4,108 fetal surveys (0.9% CHD, >4.4 million images), the model achieved an area under the curve (AUC) of 0.99, 95% sensitivity (95% confidence interval (CI), 84-99%), 96% specificity (95% CI, 95-97%) and 100% negative predictive value in distinguishing normal from abnormal hearts. Model sensitivity was comparable to that of clinicians and remained robust on outside-hospital and lower-quality images. The model's decisions were based on clinically relevant features. Cardiac measurements correlated with reported measures for normal and abnormal hearts. Applied to guideline-recommended imaging, ensemble learning models could significantly improve detection of fetal CHD, a critical and global diagnostic challenge.

Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review.

The role of physicians has always been to synthesize the data available to them to identify diagnostic patterns that guide treatment and follow response. Today, increasingly sophisticated machine learning algorithms may grow to support clinical experts in some of these tasks. Machine learning has the potential to benefit patients and cardiologists, but only if clinicians take an active role in bringing these new algorithms into practice. The aim of this review is to introduce clinicians who are not data science experts to key concepts in machine learning that will allow them to better understand the field and evaluate new literature and developments. The current published data in machine learning for cardiovascular disease is then summarized, using both a bibliometric survey, with code publicly available to enable similar analysis for any research topic of interest, and select case studies. Finally, several ways that clinicians can and must be involved in this emerging field are presented.

Best practices for authors of healthcare-related artificial intelligence manuscripts.

Since its inception in 2017, npj Digital Medicine has attracted a disproportionate number of manuscripts reporting on uses of artificial intelligence. This field has matured rapidly in the past several years. There was initial fascination with the algorithms themselves (machine learning, deep learning, convoluted neural networks) and the use of these algorithms to make predictions that often surpassed prevailing benchmarks. As the discipline has matured, individuals have called attention to aberrancies in the output of these algorithms. In particular, criticisms have been widely circulated that algorithmically developed models may have limited generalizability due to overfitting to the training data and may systematically perpetuate various forms of biases inherent in the training data, including race, gender, age, and health state or fitness level (Challen et al. BMJ Qual. Saf. 28:231-237, 2019; O'neil. Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy, Broadway Book, 2016). Given our interest in publishing the highest quality papers and the growing volume of submissions using AI algorithms, we offer a list of criteria that authors should consider before submitting papers to npj Digital Medicine.