High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy With Cardiovascular Deep Learning

IMPORTANCE

Early detection and characterization of increased left ventricular (LV) wall thickness can markedly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating causes of increased wall thickness, such as hypertrophy, cardiomyopathy, and cardiac amyloidosis.

OBJECTIVE

To assess the accuracy of a deep learning workflow in quantifying ventricular hypertrophy and predicting the cause of increased LV wall thickness.

DESIGN, SETTINGS, AND PARTICIPANTS

This cohort study included physician-curated cohorts from the Stanford Amyloid Center and Cedars-Sinai Medical Center (CSMC) Advanced Heart Disease Clinic for cardiac amyloidosis and the Stanford Center for Inherited Cardiovascular Disease and the CSMC Hypertrophic Cardiomyopathy Clinic for hypertrophic cardiomyopathy from January 1, 2008, to December 31, 2020. The deep learning algorithm was trained and tested on retrospectively obtained independent echocardiogram videos from Stanford Healthcare, CSMC, and the Unity Imaging Collaborative.

MAIN OUTCOMES AND MEASURES

The main outcome was the accuracy of the deep learning algorithm in measuring left ventricular dimensions and identifying patients with increased LV wall thickness diagnosed with hypertrophic cardiomyopathy and cardiac amyloidosis.

RESULTS

The study included 23 745 patients: 12 001 from Stanford Health Care (6509 [54.2%] female; mean [SD] age, 61.6 [17.4] years) and 1309 from CSMC (808 [61.7%] female; mean [SD] age, 62.8 [17.2] years) with parasternal long-axis videos and 8084 from Stanford Health Care (4201 [54.0%] female; mean [SD] age, 69.1 [16.8] years) and 2351 from CSMS (6509 [54.2%] female; mean [SD] age, 69.6 [14.7] years) with apical 4-chamber videos. The deep learning algorithm accurately measured intraventricular wall thickness (mean absolute error [MAE], 1.2 mm; 95% CI, 1.1-1.3 mm), LV diameter (MAE, 2.4 mm; 95% CI, 2.2-2.6 mm), and posterior wall thickness (MAE, 1.4 mm; 95% CI, 1.2-1.5 mm) and classified cardiac amyloidosis (area under the curve [AUC], 0.83) and hypertrophic cardiomyopathy (AUC, 0.98) separately from other causes of LV hypertrophy. In external data sets from independent domestic and international health care systems, the deep learning algorithm accurately quantified ventricular parameters (domestic: R2, 0.96; international: R2, 0.90). For the domestic data set, the MAE was 1.7 mm (95% CI, 1.6-1.8 mm) for intraventricular septum thickness, 3.8 mm (95% CI, 3.5-4.0 mm) for LV internal dimension, and 1.8 mm (95% CI, 1.7-2.0 mm) for LV posterior wall thickness. For the international data set, the MAE was 1.7 mm (95% CI, 1.5-2.0 mm) for intraventricular septum thickness, 2.9 mm (95% CI, 2.4-3.3 mm) for LV internal dimension, and 2.3 mm (95% CI, 1.9-2.7 mm) for LV posterior wall thickness. The deep learning algorithm accurately detected cardiac amyloidosis (AUC, 0.79) and hypertrophic cardiomyopathy (AUC, 0.89) in the domestic external validation site.

CONCLUSIONS AND RELEVANCE

In this cohort study, the deep learning model accurately identified subtle changes in LV wall geometric measurements and the causes of hypertrophy. Unlike with human experts, the deep learning workflow is fully automated, allowing for reproducible, precise measurements, and may provide a foundation for precision diagnosis of cardiac hypertrophy.

Automated Left Ventricular Dimension Assessment Using Artificial Intelligence Developed and Validated by a UK-Wide Collaborative

BACKGROUND

requires training and validation to standards expected of humans. We developed an online platform and established the Unity Collaborative to build a dataset of expertise from 17 hospitals for training, validation, and standardization of such techniques.

METHODS

The training dataset consisted of 2056 individual frames drawn at random from 1265 parasternal long-axis video-loops of patients undergoing clinical echocardiography in 2015 to 2016. Nine experts labeled these images using our online platform. From this, we trained a convolutional neural network to identify keypoints. Subsequently, 13 experts labeled a validation dataset of the end-systolic and end-diastolic frame from 100 new video-loops, twice each. The 26-opinion consensus was used as the reference standard. The primary outcome was precision SD, the SD of the differences between AI measurement and expert consensus.

RESULTS

In the validation dataset, the AI's precision SD for left ventricular internal dimension was 3.5 mm. For context, precision SD of individual expert measurements against the expert consensus was 4.4 mm. Intraclass correlation coefficient between AI and expert consensus was 0.926 (95% CI, 0.904-0.944), compared with 0.817 (0.778-0.954) between individual experts and expert consensus. For interventricular septum thickness, precision SD was 1.8 mm for AI (intraclass correlation coefficient, 0.809; 0.729-0.967), versus 2.0 mm for individuals (intraclass correlation coefficient, 0.641; 0.568-0.716). For posterior wall thickness, precision SD was 1.4 mm for AI (intraclass correlation coefficient, 0.535 [95% CI, 0.379-0.661]), versus 2.2 mm for individuals (0.366 [0.288-0.462]). We present all images and annotations. This highlights challenging cases, including poor image quality and tapered ventricles.

CONCLUSIONS

Experts at multiple institutions successfully cooperated to build a collaborative AI. This performed as well as individual experts. Future echocardiographic AI research should use a consensus of experts as a reference. Our collaborative welcomes new partners who share our commitment to publish all methods, code, annotations, and results openly.

The Right Heart International Network (RIGHT-NET): Rationale, Objectives, Methodology, and Clinical Implications

The Right Heart International Network is a multicenter international study aiming to prospectively collect exercise Doppler echocardiography tests of the right heart pulmonary circulation unit (RHPCU) in large cohorts of healthy subjects, elite athletes, and individuals at risk of or with overt pulmonary hypertension. It is going to provide standardization of exercise stress echocardiography of RHPCU and explore the full physiopathologic response.

A manifesto for cardiovascular imaging: addressing the human factor

Our use of modern cardiovascular imaging tools has not kept pace with their technological development. Diagnostic errors are common but seldom investigated systematically. Rather than more impressive pictures, our main goal should be more precise tests of function which we select because their appropriate use has therapeutic implications which in turn have a beneficial impact on morbidity or mortality. We should practise analytical thinking, use checklists to avoid diagnostic pitfalls, and apply strategies that will reduce biases and avoid overdiagnosis. We should develop normative databases, so that we can apply diagnostic algorithms that take account of variations with age and risk factors and that allow us to calculate pre-test probability and report the post-test probability of disease. We should report the imprecision of a test, or its confidence limits, so that reference change values can be considered in daily clinical practice. We should develop decision support tools to improve the quality and interpretation of diagnostic imaging, so that we choose the single best test irrespective of modality. New imaging tools should be evaluated rigorously, so that their diagnostic performance is established before they are widely disseminated; this should be a shared responsibility of manufacturers with clinicians, leading to cost-effective implementation. Trials should evaluate diagnostic strategies against independent reference criteria. We should exploit advances in machine learning to analyse digital data sets and identify those features that best predict prognosis or responses to treatment. Addressing these human factors will reap benefit for patients, while technological advances continue unpredictably.

Clinical practice of contrast echocardiography: recommendation by the European Association of Cardiovascular Imaging (EACVI) 2017

Contrast echocardiography is widely used in cardiology. It is applied to improve image quality, reader confidence and reproducibility both for assessing left ventricular (LV) structure and function at rest and for assessing global and regional function in stress echocardiography. The use of contrast in echocardiography has now extended beyond cardiac structure and function assessment to evaluation of perfusion both of the myocardium and of the intracardiac structures. Safety of contrast agents have now been addressed in large patient population and these studies clearly established its excellent safety profile. This document, based on clinical trials, randomized and multicentre studies and published clinical experience, has established clear recommendations for the use of contrast in various clinical conditions with evidence-based protocols.

Focused cardiac ultrasound by unselected residents-the challenges

Background

Focus Cardiac Ultrasound (FoCUS) performed by internal medicine residents on call with 2 h of training can provide a means for ruling out cardiac disease, but with poor sensitivity. The purpose of the present study was to evaluate diagnostic usefulness as well as diagnostic accuracy of FoCUS following 4 h of training.

Methods

All residents on call were given a 4-h training course with an additional one-hour training course after 6 months. They were asked to provide a pre- and post-FoCUS diagnosis, with the final diagnosis at discharge as reference.

Results

During a 7 month period 113 FoCUS examinations were reported; after 53 were excluded this left 60 for evaluation with a standard echocardiogram performed on average 11.5 h after FoCUS. Examinations were performed on the basis of chest pain and dyspnoea/edema. The best sensitivity was found in terms of the detection of reduced left ventricular (LV) ejection fraction (EF) (92%), LV dilatation (85%) and pericardial effusion (100%). High values were noted for negative predictive values, although false positives were seen. A kappa > 0.6 was observed for reduced LVEF, right ventricular area fraction and dilatation of LV and left atrium. In 48% of patients pre- and post-FoCUS diagnoses were identical and concordant with the final diagnosis. Importantly, in 30% examinations FoCUS correctly changed the pre-FoCUS diagnosis.

Conclusions

A FoCUS protocol with a 4-h training program gained clinical usefulness in one third of examinations. False positive findings represented the major challenge.

Pocket-size imaging device as a screening tool for aortic stenosis

AIM

The aim of this study was to assess the usefulness of a pocket-size imaging device in the hands of a noncardiologist as a screening tool for diagnosing aortic stenosis in individuals with newly discovered systolic murmur.

METHODS AND RESULTS

A total of 200 consecutive patients with systolic murmur were included; a limited focused cardiac ultrasound was performed with a pocket-size imaging device and compared to standard echocardiography. It was performed by a noncardiologist with no formal training in echocardiography. In all, 150 patients had morphological changes on the aortic valve, 77 had more than mild aortic stenosis, 30 had more than mild mitral regurgitation, 64 patients had more than moderate hypertrophy, 113 had more than moderately enlarged left atriums, and 3 had severely enlarged left ventricles. There were no significant difference in recognizing severe changes between Vscan focused cardiac ultrasound and comprehensive echocardiography.

CONCLUSION

Pocket-size ultrasound imaging devices without continuous and pulse wave Doppler modalities can, even in the hands of a noncardiologist with limited cardiac ultrasound instructions with high sensitivity and specificity, be a useful tool for detecting more than mild aortic stenosis and more than mild mitral regurgitation. As such a focused cardiac ultrasound can be an extension of physical examinations for patients with newly discovered systolic murmur.

Stress-echocardiography is underused in clinical practice: a nationwide survey in Austria

BACKGROUND

The wide area of application, including coronary artery disease, valvular heart disease, or pulmonary hypertension makes stress echocardiography (SE) a powerful, cost-effective imaging modality in cardiology. The role of this technique in clinical practice in Austria is unknown.

METHODS

A nationwide survey included all departments for cardiology and/or internal medicine in the years 2008 and 2013. By electronic questionnaire demographics, indication for the test, the numbers of examined cases per year, operators, and various applied techniques of SE were interrogated and completed by telephone interviews.

RESULTS

Data could be obtained from all 117 departments. In the year 2007 in 58 (50%) and in 2012 57 (49%) departments SE was available in Austrian hospitals. More than 100 SEs per year were performed by only four (7%) units in the year 2007 and by five (8%) in 2012. Physical exercise, dobutamine, and dipyridamole SE were available in 27 (46%), 52 (90%), and six (10%) units in 2007, and in 15 (27%), 52 (91%), and five (9%) units in 2012, respectively. In 2007 41 (71%) and in 2012 26 (46%) echo-labs administered contrast agents during SE. Transesophageal SE and 3D-echo was performed in one (2%) and three (5%) units in 2007, and in six (10%) and four (7%) echo-labs in 2012.

CONCLUSIONS

This representative survey demonstrates the underuse of SE in clinical practice in Austria. Even in established application fields performance is low, examination frequencies as recommended by the cardiology societies are fulfilled only by a minority of institutions.