Towards automatic diagnosis of rheumatic heart disease on echocardiographic exams through video-based deep learning

Machine learning and artificial intelligence within pediatric autoimmune diseases: applications, challenges, future perspective

INTRODUCTION

Autoimmune disorders affect 4.5% to 9.4% of children, significantly reducing their quality of life. The diagnosis and prognosis of autoimmune diseases are uncertain because of the variety of onset and development. Machine learning can identify clinically relevant patterns from vast amounts of data. Hence, its introduction has been beneficial in the diagnosis and management of patients.

AREAS COVERED

This narrative review was conducted through searching various electronic databases, including PubMed, Scopus, and Web of Science. This study thoroughly explores the current knowledge and identifies the remaining gaps in the applications of machine learning specifically in the context of pediatric autoimmune and related diseases.

EXPERT OPINION

Machine learning algorithms have the potential to completely change how pediatric autoimmune disorders are identified, treated, and managed. Machine learning can assist physicians in making more precise and fast judgments, identifying new biomarkers and therapeutic targets, and personalizing treatment strategies for each patient by utilizing massive datasets and powerful analytics.

Combination of Tele-Cardiology Tools for Cardiovascular Risk Stratification in Primary Care: Data from the PROVAR+ Study

BACKGROUND

Tele-cardiology tools are valuable strategies to improve risk stratification.

OBJECTIVE

We aimed to evaluate the accuracy of tele-electrocardiography (ECG) to predict abnormalities in screening echocardiography (echo) in primary care (PC).

METHODS

In 17 months, 6 health providers at 16 PC units were trained on simplified handheld echo protocols. Tele-ECGs were recorded for final diagnosis by a cardiologist. Consented patients with major ECG abnormalities by the Minnesota code, and a 1:5 sample of normal individuals underwent clinical questionnaire and screening echo interpreted remotely. Major heart disease was defined as moderate/severe valve disease, ventricular dysfunction/hypertrophy, pericardial effusion, or wall-motion abnormalities. Association between major ECG and echo abnormalities was assessed by logistic regression as follows: 1) unadjusted model; 2) model 1 adjusted for age/sex; 3) model 2 plus risk factors (hypertension/diabetes); 4) model 3 plus history of cardiovascular disease (Chagas/rheumatic heart disease/ischemic heart disease/stroke/heart failure). P-values < 0.05 were considered significant.

RESULTS

A total 1,411 patients underwent echo; 1,149 (81%) had major ECG abnormalities. Median age was 67 (IQR 60 to 74) years, and 51.4% were male. Major ECG abnormalities were associated with a 2.4-fold chance of major heart disease on echo in bivariate analysis (OR = 2.42 [95% CI 1.76 to 3.39]), and remained significant after adjustments in models (p < 0.001) 2 (OR = 2.57 [95% CI 1.84 to 3.65]), model 3 (OR = 2.52 [95% CI 1.80 to3.58]), and model 4 (OR = 2.23 [95%CI 1.59 to 3.19]). Age, male sex, heart failure, and ischemic heart disease were also independent predictors of major heart disease on echo.

CONCLUSIONS

Tele-ECG abnormalities increased the likelihood of major heart disease on screening echo, even after adjustments for demographic and clinical variables.

2023 World Heart Federation guidelines for the echocardiographic diagnosis of rheumatic heart disease

Rheumatic heart disease (RHD) is an important and preventable cause of morbidity and mortality among children and young adults in low-income and middle-income countries, as well as among certain at-risk populations living in high-income countries. The 2012 World Heart Federation echocardiographic criteria provided a standardized approach for the identification of RHD and facilitated an improvement in early case detection. The 2012 criteria were used to define disease burden in numerous epidemiological studies, but researchers and clinicians have since highlighted limitations that have prompted a revision. In this updated version of the guidelines, we incorporate evidence from a scoping review, an expert panel and end-user feedback and present an approach for active case finding for RHD, including the use of screening and confirmatory criteria. These guidelines also introduce a new stage-based classification for RHD to identify the risk of disease progression. They describe the latest evidence and recommendations on population-based echocardiographic active case finding and risk stratification. Secondary antibiotic prophylaxis, echocardiography equipment and task sharing for RHD active case finding are also discussed. These World Heart Federation 2023 guidelines provide a concise and updated resource for clinical and research applications in RHD-endemic regions.

Deep learning from latent spatiotemporal information of the heart: Identifying advanced bioimaging markers from echocardiograms

A key strength of echocardiography lies in its integration of comprehensive spatiotemporal cardiac imaging data in real-time, to aid frontline or bedside patient risk stratification and management. Nonetheless, its acquisition, processing, and interpretation are known to all be subject to heterogeneity from its reliance on manual and subjective human tracings, which challenges workflow and protocol standardization and final interpretation accuracy. In the era of advanced computational power, utilization of machine learning algorithms for big data analytics in echocardiography promises reduction in cost, cognitive errors, and intra- and inter-observer variability. Novel spatiotemporal deep learning (DL) models allow the integration of temporal arm information based on unlabeled pixel echocardiographic data for convolution of an adaptive semantic spatiotemporal calibration to construct personalized 4D heart meshes, assess global and regional cardiac function, detect early valve pathology, and differentiate uncommon cardiovascular disorders. Meanwhile, data visualization on spatiotemporal DL prediction models helps extract latent temporal imaging features to develop advanced imaging biomarkers in early disease stages and advance our understanding of pathophysiology to support the development of personalized prevention or treatment strategies. Since portable echocardiograms have been increasingly used as point-of-care imaging tools to aid rural care delivery, the application of these new spatiotemporal DL techniques show the potentials in streamlining echocardiographic acquisition, processing, and data analysis to improve workflow standardization and efficiencies, and provide risk stratification and decision supporting tools in real-time, to prompt the building of new imaging diagnostic networks to enhance rural healthcare engagement.

Using Artificial Intelligence for Rheumatic Heart Disease Detection by Echocardiography: Focus on Mitral Regurgitation

BACKGROUND

Identification of children with latent rheumatic heart disease (RHD) by echocardiography, before onset of symptoms, provides an opportunity to initiate secondary prophylaxis and prevent disease progression. There have been limited artificial intelligence studies published assessing the potential of machine learning to detect and analyze mitral regurgitation or to detect the presence of RHD on standard portable echocardiograms.

METHODS AND RESULTS

We used 511 echocardiograms in children, focusing on color Doppler images of the mitral valve. Echocardiograms were independently reviewed by an expert adjudication panel. Among 511 cases, 229 were normal, and 282 had RHD. Our automated method included harmonization of echocardiograms to localize the left atrium during systole using convolutional neural networks and RHD detection using mitral regurgitation jet analysis and deep learning models with an attention mechanism. We identified the correct view with an average accuracy of 0.99 and the correct systolic frame with an average accuracy of 0.94 (apical) and 0.93 (parasternal long axis). It localized the left atrium with an average Dice coefficient of 0.88 (apical) and 0.9 (parasternal long axis). Maximum mitral regurgitation jet measurements were similar to expert manual measurements (P value=0.83) and a 9-feature mitral regurgitation analysis showed an area under the receiver operating characteristics curve of 0.93, precision of 0.83, recall of 0.92, and F1 score of 0.87. Our deep learning model showed an area under the receiver operating characteristics curve of 0.84, precision of 0.78, recall of 0.98, and F1 score of 0.87.

CONCLUSIONS

Artificial intelligence has the potential to detect RHD as accurately as expert cardiologists and to improve with more data. These innovative approaches hold promise to scale echocardiography screening for RHD.

Deep learning for automated left ventricular outflow tract diameter measurements in 2D echocardiography

BACKGROUND

Measurement of the left ventricular outflow tract diameter (LVOTd) in echocardiography is a common source of error when used to calculate the stroke volume. The aim of this study is to assess whether a deep learning (DL) model, trained on a clinical echocardiographic dataset, can perform automatic LVOTd measurements on par with expert cardiologists.

METHODS

Data consisted of 649 consecutive transthoracic echocardiographic examinations of patients with coronary artery disease admitted to a university hospital. 1304 LVOTd measurements in the parasternal long axis (PLAX) and zoomed parasternal long axis views (ZPLAX) were collected, with each patient having 1-6 measurements per examination. Data quality control was performed by an expert cardiologist, and spatial geometry data was preserved for each LVOTd measurement to convert DL predictions into metric units. A convolutional neural network based on the U-Net was used as the DL model.

RESULTS

The mean absolute LVOTd error was 1.04 (95% confidence interval [CI] 0.90-1.19) mm for DL predictions on the test set. The mean relative LVOTd errors across all data subgroups ranged from 3.8 to 5.1% for the test set. Generally, the DL model had superior performance on the ZPLAX view compared to the PLAX view. DL model precision for patients with repeated LVOTd measurements had a mean coefficient of variation of 2.2 (95% CI 1.6-2.7) %, which was comparable to the clinicians for the test set.

CONCLUSION

DL for automatic LVOTd measurements in PLAX and ZPLAX views is feasible when trained on a limited clinical dataset. While the DL predicted LVOTd measurements were within the expected range of clinical inter-observer variability, the robustness of the DL model requires validation on independent datasets. Future experiments using temporal information and anatomical constraints could improve valvular identification and reduce outliers, which are challenges that must be addressed before clinical utilization.

Tertiary prevention and treatment of rheumatic heart disease: a National Heart, Lung, and Blood Institute working group summary

Although entirely preventable, rheumatic heart disease (RHD), a disease of poverty and social disadvantage resulting in high morbidity and mortality, remains an ever-present burden in low-income and middle-income countries (LMICs) and rural, remote, marginalised and disenfranchised populations within high-income countries. In late 2021, the National Heart, Lung, and Blood Institute convened a workshop to explore the current state of science, to identify basic science and clinical research priorities to support RHD eradication efforts worldwide. This was done through the inclusion of multidisciplinary global experts, including cardiovascular and non-cardiovascular specialists as well as health policy and health economics experts, many of whom also represented or closely worked with patient-family organisations and local governments. This report summarises findings from one of the four working groups, the Tertiary Prevention Working Group, that was charged with assessing the management of late complications of RHD, including surgical interventions for patients with RHD. Due to the high prevalence of RHD in LMICs, particular emphasis was made on gaining a better understanding of needs in the field from the perspectives of the patient, community, provider, health system and policy-maker. We outline priorities to support the development, and implementation of accessible, affordable and sustainable interventions in low-resource settings to manage RHD and related complications. These priorities and other interventions need to be adapted to and driven by local contexts and integrated into health systems to best meet the needs of local communities.

The Role of Artificial Intelligence in Echocardiography

Echocardiography is an integral part of the diagnosis and management of cardiovascular disease. The use and application of artificial intelligence (AI) is a rapidly expanding field in medicine to improve consistency and reduce interobserver variability. AI can be successfully applied to echocardiography in addressing variance during image acquisition and interpretation. Furthermore, AI and machine learning can aid in the diagnosis and management of cardiovascular disease. In the realm of echocardiography, accurate interpretation is largely dependent on the subjective knowledge of the operator. Echocardiography is burdened by the high dependence on the level of experience of the operator, to a greater extent than other imaging modalities like computed tomography, nuclear imaging, and magnetic resonance imaging. AI technologies offer new opportunities for echocardiography to produce accurate, automated, and more consistent interpretations. This review discusses machine learning as a subfield within AI in relation to image interpretation and how machine learning can improve the diagnostic performance of echocardiography. This review also explores the published literature outlining the value of AI and its potential to improve patient care.

Reasons for disagreement between screening and standard echocardiography in primary care: data from the PROVAR + study : Disagreement between screening and standard echo

We aimed to evaluate the reasons for disagreement between screening echocardiography (echo), acquired by nonexperts, and standard echo in the Brazilian primary care (PC). Over 20 months, 22 PC workers were trained on simplified handheld (GE VSCAN) echo protocols. Screening groups, consisting of patients aged 17-20, 35-40 and 60-65 years, and patients referred for clinical indications underwent focused echo. Studies were remotelyinterpreted in US and Brazil, and those diagnosed with major or severe HD were referred for standard echoperformed by an expert. Major HD was defined as moderate to severe valve disease, ventriculardysfunction/hypertrophy, pericardial effusion or wall-motion abnormalities. A random sample of exams wasselected for evaluation of variables accounting for disagreement. A sample of 768 patients was analyzed, 651(85%) in the referred group. Quality issues were reported in 5.8%, and the random Kappa for major HD between screening and standard echo was 0.51. The most frequent reasons for disagreement were: overestimation of mitral regurgitation (MR) (17.9%, N=138), left ventricular (LV) dysfunction (15.7%, N=121), aortic regurgitation (AR) (15.2%, N=117), LV hypertrophy (13.5%, N=104) and tricuspid regurgitation (12.7%, N=98). Misdiagnosis of mitral and aortic morphological abnormalities was observed in 12.4% and 3.0%, and underestimation of AR and MR occurred in 4.6% and 11.1%. Among 257 patients with suspected mild/moderate MR, 129 were reclassified to normal. In conclusion, although screening echo with task-shifting in PC is a promising tool in low-income areas, estimation of valve regurgitation and LV function and size account for considerable disagreement with standard exams.

Data harnessing to nurture the human mind for a tailored approach to the child

Big data in pediatrics is an ocean of structured and unstructured data. Big data analysis helps to dive into the ocean of data to filter out information that can guide pediatricians in their decision making, precision diagnosis, and targeted therapy. In addition, big data and its analysis have helped in the surveillance, prevention, and performance of the health system. There has been a considerable amount of work in pediatrics that we have tried to highlight in this review and some of it has been already incorporated into the health system. Work in specialties of pediatrics is still forthcoming with the creation of a common data model and amalgamation of the huge "omics" database. The physicians entrusted with the care of children must be aware of the outcome so that they can play a role to ensure that big data algorithms have a clinically relevant effect in improving the health of their patients. They will apply the outcome of big data and its analysis in patient care through clinical algorithms or with the help of embedded clinical support alerts from the electronic medical records. IMPACT: Big data in pediatrics include structured, unstructured data, waveform data, biological, and social data. Big data analytics has unraveled significant information from these databases. This is changing how pediatricians will look at the body of available evidence and translate it into their clinical practice. Data harnessed so far is implemented in certain fields while in others it is in the process of development to become a clinical adjunct to the physician. Common databases are being prepared for future work. Diagnostic and prediction models when incorporated into the health system will guide the pediatrician to a targeted approach to diagnosis and therapy.

Machine Learning for Pediatric Echocardiographic Mitral Regurgitation Detection

BACKGROUND

Echocardiography-based screening for valvular disease in at-risk asymptomatic children can result in early diagnosis. These screening programs, however, are resource intensive and may not be feasible in many resource-limited settings. Automated echocardiographic diagnosis may enable more widespread echocardiographic screening, early diagnosis, and improved outcomes. In this feasibility study, the authors sought to build a machine learning model capable of identifying mitral regurgitation (MR) on echocardiography.

METHODS

Echocardiograms were labeled by clip for view and by frame for the presence of MR. The labeled data were used to build two convolutional neural networks to perform the stepwise tasks of classifying the clips (1) by view and (2) by the presence of any MR, including physiologic, in parasternal long-axis color Doppler views. The view classification model was developed using 66,330 frames, and model performance was evaluated using a hold-out testing data set with 45 echocardiograms (11,730 frames). The MR detection model was developed using 938 frames, and model performance was evaluated using a hold-out testing data set with 42 echocardiograms (182 frames). Metrics to evaluate model performance included accuracy, precision, recall, F1 score (average of precision and recall, ranging from 0 to 1, with 1 suggesting perfect precision and recall), and receiver operating characteristic analysis.

RESULTS

For the parasternal long-axis view with color Doppler, the view classification convolutional neural network achieved an F1 score of 0.97. The MR detection convolutional neural network achieved testing accuracy of 0.86 and an area under the receiver operating characteristic curve of 0.91.

CONCLUSIONS

A machine learning model is capable of discerning MR on transthoracic echocardiography. This is an encouraging step toward machine learning-based diagnosis of valvular heart disease on pediatric echocardiography.

An Automated View Classification Model for Pediatric Echocardiography Using Artificial Intelligence

BACKGROUND

View classification is a key step toward building a fully automated system for interpretation of echocardiograms. However, compared with adult echocardiograms, creating a view classification model for pediatric echocardiograms poses additional challenges, such as greater variation in anatomy, structure size, and views. The aim of this study was to develop a computer vision model to autonomously perform view classification on pediatric echocardiographic images.

METHODS

Using a training set of 12,067 echocardiographic images from patients aged 0 to 19 years, a convolutional neural network model was trained to identify 27 preselected standard pediatric echocardiographic views which included anatomic sweeps, color Doppler, and Doppler tracings. A validation set of 6,197 images was used for parameter tuning and model selection. A test set of 9,684 images from 100 different patients was then used to evaluate model accuracy. The model was also evaluated on a per study basis using a second test set consisting of 524 echocardiograms from children with leukemia to identify six preselected views pertinent to cardiac dysfunction surveillance.

RESULTS

The model identified the 27 preselected views with 90.3% accuracy. Accuracy was similar across age groups (89.3% for 0-4 years, 90.8% for 4-9 years, 90.0% for 9-14 years, and 91.2% for 14-19 years; P = .12). Examining the view subtypes, accuracy was 78.3% for the cine one location, 90.5% for sweeps with color Doppler, 82.2% for sweeps without color Doppler, and 91.1% for Doppler tracings. Among the leukemia cohort, the model identified the six preselected views on a per study basis with a positive predictive value of 98.7% to 99.2% and sensitivity of 76.9% to 94.8%.

CONCLUSIONS

A convolutional neural network model was constructed for view classification of pediatric echocardiograms that was accurate across the spectrum of ages and view types. This work lays the foundation for automated quantitative analysis and diagnostic support to promote efficient, accurate, and scalable analysis of pediatric echocardiograms.

Artificial Intelligence in Pediatric Cardiology: A Scoping Review

The evolution of AI and data science has aided in mechanizing several aspects of medical care requiring critical thinking: diagnosis, risk stratification, and management, thus mitigating the burden of physicians and reducing the likelihood of human error. AI modalities have expanded feet to the specialty of pediatric cardiology as well. We conducted a scoping review searching the Scopus, Embase, and PubMed databases covering the recent literature between 2002-2022. We found that the use of neural networks and machine learning has significantly improved the diagnostic value of cardiac magnetic resonance imaging, echocardiograms, computer tomography scans, and electrocardiographs, thus augmenting the clinicians' diagnostic accuracy of pediatric heart diseases. The use of AI-based prediction algorithms in pediatric cardiac surgeries improves postoperative outcomes and prognosis to a great extent. Risk stratification and the prediction of treatment outcomes are feasible using the key clinical findings of each CHD with appropriate computational algorithms. Notably, AI can revolutionize prenatal prediction as well as the diagnosis of CHD using the EMR (electronic medical records) data on maternal risk factors. The use of AI in the diagnostics, risk stratification, and management of CHD in the near future is a promising possibility with current advancements in machine learning and neural networks. However, the challenges posed by the dearth of appropriate algorithms and their nascent nature, limited physician training, fear of over-mechanization, and apprehension of missing the 'human touch' limit the acceptability. Still, AI proposes to aid the clinician tomorrow with precision cardiology, paving a way for extremely efficient human-error-free health care.

Heart disease detection based on internet of things data using linear quadratic discriminant analysis and a deep graph convolutional neural network

Heart disease is an emerging health issue in the medical field, according to WHO every year around 10 billion people are affected with heart abnormalities. Arteries in the heart generate oxygenated blood to all body parts, however sometimes blood vessels become clogged or restrained due to cardiac issues. Past heart diagnosis applications are outdated and suffer from poor performance. Therefore, an intelligent heart disease diagnosis application design is required. In this research work, internet of things (IoT) sensor data with a deep learning-based heart diagnosis application is designed. The heart disease IoT sensor data is collected from the University of California Irvine machine learning repository free open-source dataset which is useful for training the deep graph convolutional network (DG_ConvoNet) deep learning network. The testing data has been collected from the Cleveland Clinic Foundation; it is a collection of 350 real-time clinical instances from heart patients through IoT sensors. The K-means technique is employed to remove noise in sensor data and clustered the unstructured data. The features are extracted to employ Linear Quadratic Discriminant Analysis. DG_ConvoNet is a deep learning process to classify and predict heart diseases. The diagnostic application achieves an accuracy of 96%, sensitivity of 80%, specificity of 73%, precision of 90%, F-Score of 79%, and area under the ROC curve of 75% implementing the proposed model.

Artificial intelligence for the echocardiographic assessment of valvular heart disease

Developments in artificial intelligence (AI) have led to an explosion of studies exploring its application to cardiovascular medicine. Due to the need for training and expertise, one area where AI could be impactful would be in the diagnosis and management of valvular heart disease. This is because AI can be applied to the multitude of data generated from clinical assessments, imaging and biochemical testing during the care of the patient. In the area of valvular heart disease, the focus of AI has been on the echocardiographic assessment and phenotyping of patient populations to identify high-risk groups. AI can assist image acquisition, view identification for review, and segmentation of valve and cardiac structures for automated analysis. Using image recognition algorithms, aortic and mitral valve disease states have been directly detected from the images themselves. Measurements obtained during echocardiographic valvular assessment have been integrated with other clinical data to identify novel aortic valve disease subgroups and describe new predictors of aortic valve disease progression. In the future, AI could integrate echocardiographic parameters with other clinical data for precision medical management of patients with valvular heart disease.

Impact of Technologic Innovation and COVID-19 Pandemic on Pediatric Cardiology Telehealth

Purpose of Review

Established telehealth practices in pediatrics and pediatric cardiology are evolving rapidly. This review examines several concepts in contemporary telemedicine in our field: recent changes in direct-to-consumer (DTC) pediatric telehealth (TH) and practice based on lessons learned from the pandemic, scientific data from newer technological innovations in pediatric cardiology, and how TH is shaping global pediatric cardiology practice.

Recent Findings

In 2020, the global pandemic of COVID-19 led to significant changes in healthcare delivery. The lockdown and social distancing guidelines accelerated smart adaptations and pivots to ensure continued pediatric care albeit in a virtual manner. Remote cardiac monitoring technology is continuing to advance at a rapid pace secondary to advances in the areas of Internet access, portable hand-held devices, and artificial intelligence.

Summary

TH should be approached programmatically by pediatric cardiac healthcare providers with careful selection of patients, technology platforms, infrastructure setup, documentation, and compliance. Payment parity with in-person visits should be advocated and legislated. Newer remote cardiac monitoring technology should be expanded for objective assessment and optimal outcomes. TH continues to be working beyond geographical boundaries in pediatric cardiology and should continue to expand and develop.