PROTEUS Study: A Prospective Randomized Controlled Trial Evaluating the Use of Artificial Intelligence in Stress Echocardiography.

BACKGROUND: Stress echocardiography (SE) is one of the most commonly used diagnostic imaging tests for coronary artery disease (CAD) but requires clinicians to visually assess scans to identify patients who may benefit from invasive investigation and treatment. EchoGo Pro provides an automated interpretation of SE based on artificial intelligence (AI) image analysis. In reader studies, use of EchoGo Pro when making clinical decisions improves diagnostic accuracy and confidence. Prospective evaluation in real world practice is now important to understand the impact of EchoGo Pro on the patient pathway and outcome. METHODS: PROTEUS is a randomized, multicenter, 2-armed, noninferiority study aiming to recruit 2,500 participants from National Health Service (NHS) hospitals in the UK referred to SE clinics for investigation of suspected CAD. All participants will undergo a stress echocardiogram protocol as per local hospital policy. Participants will be randomized 1:1 to a control group, representing current practice, or an intervention group, in which clinicians will receive an AI image analysis report (EchoGo Pro, Ultromics Ltd, Oxford, UK) to use during image interpretation, indicating the likelihood of severe CAD. The primary outcome will be appropriateness of clinician decision to refer for coronary angiography. Secondary outcomes will assess other health impacts including appropriate use of other clinical management approaches, impact on variability in decision making, patient and clinician qualitative experience and a health economic analysis. DISCUSSION: This will be the first study to assess the impact of introducing an AI medical diagnostic aid into the standard care pathway of patients with suspected CAD being investigated with SE. TRIAL REGISTRATION: Clinicaltrials.gov registration number NCT05028179, registered on 31 August 2021; ISRCTN: ISRCTN15113915; IRAS ref: 293515; REC ref: 21/NW/0199.

Automated Echocardiographic Detection of Heart Failure With Preserved Ejection Fraction Using Artificial Intelligence.

Background: Detection of heart failure with preserved ejection fraction (HFpEF) involves integration of multiple imaging and clinical features which are often discordant or indeterminate. Objectives: The authors applied artificial intelligence (AI) to analyze a single apical 4-chamber transthoracic echocardiogram video clip to detect HFpEF. Methods: A 3-dimensional convolutional neural network was developed and trained on apical 4-chamber video clips to classify patients with HFpEF (diagnosis of heart failure, ejection fraction ≥50%, and echocardiographic evidence of increased filling pressure; cases) vs without HFpEF (ejection fraction ≥50%, no diagnosis of heart failure, normal filling pressure; controls). Model outputs were classified as HFpEF, no HFpEF, or nondiagnostic (high uncertainty). Performance was assessed in an independent multisite data set and compared to previously validated clinical scores. Results: Training and validation included 2,971 cases and 3,785 controls (validation holdout, 16.8% patients), and demonstrated excellent discrimination (area under receiver-operating characteristic curve: 0.97 [95% CI: 0.96-0.97] and 0.95 [95% CI: 0.93-0.96] in training and validation, respectively). In independent testing (646 cases, 638 controls), 94 (7.3%) were nondiagnostic; sensitivity (87.8%; 95% CI: 84.5%-90.9%) and specificity (81.9%; 95% CI: 78.2%-85.6%) were maintained in clinically relevant subgroups, with high repeatability and reproducibility. Of 701 and 776 indeterminate outputs from the Heart Failure Association-Pretest Assessment, Echocardiographic and Natriuretic Peptide Score, Functional Testing (HFA-PEFF), and Final Etiology and Heavy, Hypertensive, Atrial Fibrillation, Pulmonary Hypertension, Elder, and Filling Pressure (H2FPEF) scores, the AI HFpEF model correctly reclassified 73.5% and 73.6%, respectively. During follow-up (median: 2.3 [IQR: 0.5-5.6] years), 444 (34.6%) patients died; mortality was higher in patients classified as HFpEF by AI (HR: 1.9 [95% CI: 1.5-2.4]). Conclusions: An AI HFpEF model based on a single, routinely acquired echocardiographic video demonstrated excellent discrimination of patients with vs without HFpEF, more often than clinical scores, and identified patients with higher mortality.

Left ventricular assessment with artificial intelligence increases the diagnostic accuracy of stress echocardiography.

Aims: To evaluate whether left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), automatically calculated by artificial intelligence (AI), increases the diagnostic performance of stress echocardiography (SE) for coronary artery disease (CAD) detection. Methods and results: SEs from 512 participants who underwent a clinically indicated SE (with or without contrast) for the evaluation of CAD from seven hospitals in the UK and US were studied. Visual wall motion scoring (WMS) was performed to identify inducible ischaemia. In addition, SE images at rest and stress underwent AI contouring for automated calculation of AI-LVEF and AI-GLS (apical two and four chamber images only) with Ultromics EchoGo Core 1.0. Receiver operator characteristic curves and multivariable risk models were used to assess accuracy for identification of participants subsequently found to have CAD on angiography. Participants with significant CAD were more likely to have abnormal WMS, AI-LVEF, and AI-GLS values at rest and stress (all P < 0.001). The areas under the receiver operating characteristics for WMS index, AI-LVEF, and AI-GLS at peak stress were 0.92, 0.86, and 0.82, respectively, with cut-offs of 1.12, 64%, and -17.2%, respectively. Multivariable analysis demonstrated that addition of peak AI-LVEF or peak AI-GLS to WMS significantly improved model discrimination of CAD [C-statistic (bootstrapping 2.5th, 97.5th percentile)] from 0.78 (0.69-0.87) to 0.83 (0.74-0.91) or 0.84 (0.75-0.92), respectively. Conclusion: AI calculation of LVEF and GLS by contouring of contrast-enhanced and unenhanced SEs at rest and stress is feasible and independently improves the identification of obstructive CAD beyond conventional WMSI.

Human versus Artificial Intelligence-Based Echocardiographic Analysis as a Predictor of Outcomes: An Analysis from the World Alliance Societies of Echocardiography COVID Study.

BACKGROUND: Transthoracic echocardiography is the leading cardiac imaging modality for patients admitted with COVID-19, a condition of high short-term mortality. The aim of this study was to test the hypothesis that artificial intelligence (AI)-based analysis of echocardiographic images could predict mortality more accurately than conventional analysis by a human expert. METHODS: Patients admitted to 13 hospitals for acute COVID-19 who underwent transthoracic echocardiography were included. Left ventricular ejection fraction (LVEF) and left ventricular longitudinal strain (LVLS) were obtained manually by multiple expert readers and by automated AI software. The ability of the manual and AI analyses to predict all-cause mortality was compared. RESULTS: In total, 870 patients were enrolled. The mortality rate was 27.4% after a mean follow-up period of 230 ± 115 days. AI analysis had lower variability than manual analysis for both LVEF (P = .003) and LVLS (P = .005). AI-derived LVEF and LVLS were predictors of mortality in univariable and multivariable regression analysis (odds ratio, 0.974 [95% CI, 0.956-0.991; P = .003] for LVEF; odds ratio, 1.060 [95% CI, 1.019-1.105; P = .004] for LVLS), but LVEF and LVLS obtained by manual analysis were not. Direct comparison of the predictive value of AI versus manual measurements of LVEF and LVLS showed that AI was significantly better (P = .005 and P = .003, respectively). In addition, AI-derived LVEF and LVLS had more significant and stronger correlations to other objective biomarkers of acute disease than manual reads. CONCLUSIONS: AI-based analysis of LVEF and LVLS had similar feasibility as manual analysis, minimized variability, and consequently increased the statistical power to predict mortality. AI-based, but not manual, analyses were a significant predictor of in-hospital and follow-up mortality.

Real-world performance and accuracy of stress echocardiography: the EVAREST observational multi-centre study.

AIMS: Stress echocardiography is widely used to identify obstructive coronary artery disease (CAD). High accuracy is reported in expert hands but is dependent on operator training and image quality. The EVAREST study provides UK-wide data to evaluate real-world performance and accuracy of stress echocardiography. METHODS AND RESULTS: Participants undergoing stress echocardiography for CAD were recruited from 31 hospitals. Participants were followed up through health records which underwent expert adjudication. Cardiac outcome was defined as anatomically or functionally significant stenosis on angiography, revascularization, medical management of ischaemia, acute coronary syndrome, or cardiac-related death within 6 months. A total of 5131 patients (55% male) participated with a median age of 65 years (interquartile range 57-74). 72.9% of studies used dobutamine and 68.5% were contrast studies. Inducible ischaemia was present in 19.3% of scans. Sensitivity and specificity for prediction of a cardiac outcome were 95.4% and 96.0%, respectively, with an accuracy of 95.9%. Sub-group analysis revealed high levels of predictive accuracy across a wide range of patient and protocol sub-groups, with the presence of a resting regional wall motion abnormalitiy significantly reducing the performance of both dobutamine (P < 0.01) and exercise (P < 0.05) stress echocardiography. Overall accuracy remained consistently high across all participating hospitals. CONCLUSION: Stress echocardiography has high accuracy across UK-based hospitals and thus indicates stress echocardiography is being delivered effectively in real-world practice, reinforcing its role as a first-line investigation in the assessment of patients with stable chest pain.

Automated Echocardiographic Detection of Severe Coronary Artery Disease Using Artificial Intelligence.

OBJECTIVES: The purpose of this study was to establish whether an artificially intelligent (AI) system can be developed to automate stress echocardiography analysis and support clinician interpretation. BACKGROUND: Coronary artery disease is the leading global cause of mortality and morbidity and stress echocardiography remains one of the most commonly used diagnostic imaging tests. METHODS: An automated image processing pipeline was developed to extract novel geometric and kinematic features from stress echocardiograms collected as part of a large, United Kingdom-based prospective, multicenter, multivendor study. An ensemble machine learning classifier was trained, using the extracted features, to identify patients with severe coronary artery disease on invasive coronary angiography. The model was tested in an independent U.S. STUDY: How availability of an AI classification might impact clinical interpretation of stress echocardiograms was evaluated in a randomized crossover reader study. RESULTS: Acceptable classification accuracy for identification of patients with severe coronary artery disease in the training data set was achieved on cross-fold validation based on 31 unique geometric and kinematic features, with a specificity of 92.7% and a sensitivity of 84.4%. This accuracy was maintained in the independent validation data set. The use of the AI classification tool by clinicians increased inter-reader agreement and confidence as well as sensitivity for detection of disease by 10% to achieve an area under the receiver-operating characteristic curve of 0.93. CONCLUSIONS: Automated analysis of stress echocardiograms is possible using AI and provision of automated classifications to clinicians when reading stress echocardiograms could improve accuracy, inter-reader agreement, and reader confidence.

Prenatal and Postnatal Cardiac Development in Offspring of Hypertensive Pregnancies.

Background Pregnancy complications such as preterm birth and fetal growth restriction are associated with altered prenatal and postnatal cardiac development. We studied whether there were changes related specifically to pregnancy hypertension. Methods and Results Left and right ventricular volumes, mass, and function were assessed at birth and 3 months of age by echocardiography in 134 term-born infants. Fifty-four had been born to mothers who had normotensive pregnancy and 80 had a diagnosis of preeclampsia or pregnancy-induced hypertension. Differences between groups were interpreted, taking into account severity of pregnancy disorder, sex, body size, and blood pressure. Left and right ventricular mass indexed to body surface area (LVMI and RVMI) were similar in both groups at birth (LVMI 20.9±3.7 versus 20.6±4.0 g/m2, P=0.64, RVMI 17.5±3.7 versus 18.1±4.7 g/m2, P=0.57). However, right ventricular end diastolic volume index was significantly smaller in those born to hypertensive pregnancy (16.8±5.3 versus 12.7±4.7 mL/m2, P=0.001), persisting at 3 months of age (16.4±3.2 versus 14.4±4.8 mL/m2, P=0.04). By 3 months of age these infants also had significantly greater LVMI and RVMI (LVMI 24.9±4.6 versus 26.8±4.9 g/m2, P=0.04; RVMI 17.1±4.2 versus 21.1±3.9 g/m2, P<0.001). Differences in RVMI and right ventricular end diastolic volume index at 3 months, but not left ventricular measures, correlated with severity of the hypertensive disorder. No differences in systolic or diastolic function were evident. Conclusions Infants born at term to a hypertensive pregnancy have evidence of both prenatal and postnatal differences in cardiac development, with right ventricular changes proportional to the severity of the pregnancy disorder. Whether differences persist long term as well as their underlying cause and relationship to increased cardiovascular risk requires further study.

Variations in Cardiovascular Structure, Function, and Geometry in Midlife Associated With a History of Hypertensive Pregnancy.

Hypertensive pregnancy is associated with increased maternal cardiovascular risk in later life. A range of cardiovascular adaptations after pregnancy have been reported to partly explain this risk. We used multimodality imaging to identify whether, by midlife, any pregnancy-associated phenotypes were still identifiable and to what extent they could be explained by blood pressure. Participants were identified by review of hospital maternity records 5 to 10 years after pregnancy and invited to a single visit for detailed cardiovascular imaging phenotyping. One hundred seventy-three women (age, 42±5 years, 70 after normotensive and 103 after hypertensive pregnancy) underwent magnetic resonance imaging of the heart and aorta, echocardiography, and vascular assessment, including capillaroscopy. Women with a history of hypertensive pregnancy had a distinct cardiac geometry with higher left ventricular mass index (49.9±7.1 versus 46.0±6.5 g/m2; P=0.001) and ejection fraction (65.6±5.4% versus 63.7±4.3%; P=0.03) but lower global longitudinal strain (-18.31±4.46% versus -19.94±3.59%; P=0.02). Left atrial volume index was also increased (40.4±9.2 versus 37.3±7.3 mL/m2; P=0.03) and E:A reduced (1.34±0.35 versus 1.52±0.45; P=0.003). Aortic compliance (0.240±0.053 versus 0.258±0.063; P=0.046) and functional capillary density (105.4±23.0 versus 115.2±20.9 capillaries/mm2; P=0.01) were reduced. Only differences in functional capillary density, left ventricular mass, and atrial volume indices remained after adjustment for blood pressure (P<0.01, P=0.01, and P=0.04, respectively). Differences in cardiac structure and geometry, as well as microvascular rarefaction, are evident in midlife after a hypertensive pregnancy, independent of blood pressure. To what extent these phenotypic patterns contribute to cardiovascular disease progression or provide additional measures to improve risk stratification requires further study.

Neonatal autonomic function after pregnancy complications and early cardiovascular development.

BACKGROUND: Heart rate variability (HRV) has emerged as a predictor of later cardiac risk. This study tested whether pregnancy complications that may have long-term offspring cardiac sequelae are associated with differences in HRV at birth, and whether these HRV differences identify abnormal cardiovascular development in the postnatal period. METHODS: Ninety-eight sleeping neonates had 5-min electrocardiogram recordings at birth. Standard time and frequency domain parameters were calculated and related to cardiovascular measures at birth and 3 months of age. RESULTS: Increasing prematurity, but not maternal hypertension or growth restriction, was associated with decreased HRV at birth, as demonstrated by a lower root mean square of the difference between adjacent NN intervals (rMSSD) and low (LF) and high-frequency power (HF), with decreasing gestational age (p < 0.001, p = 0.009 and p = 0.007, respectively). We also demonstrated a relative imbalance between sympathetic and parasympathetic tone, compared to the term infants. However, differences in autonomic function did not predict cardiovascular measures at either time point. CONCLUSIONS: Altered cardiac autonomic function at birth relates to prematurity rather than other pregnancy complications and does not predict cardiovascular developmental patterns during the first 3 months post birth. Long-term studies will be needed to understand the relevance to cardiovascular risk.

Two-Dimensional Echocardiography Estimates of Fetal Ventricular Mass throughout Gestation.

BACKGROUND: Two-dimensional (2D) ultrasound quality has improved in recent years. Quantification of cardiac dimensions is important to screen and monitor certain fetal conditions. We assessed the feasibility and reproducibility of fetal ventricular measures using 2D echocardiography, reported normal ranges in our cohort, and compared estimates to other modalities. METHODS: Mass and end-diastolic volume were estimated by manual contouring in the four-chamber view using TomTec Image Arena 4.6 in end diastole. Nomograms were created from smoothed centiles of measures, constructed using fractional polynomials after log transformation. The results were compared to those of previous studies using other modalities. RESULTS: A total of 294 scans from 146 fetuses from 15+0 to 41+6 weeks of gestation were included. Seven percent of scans were unanalysable and intraobserver variability was good (intraclass correlation coefficients for left and right ventricular mass 0.97 [0.87-0.99] and 0.99 [0.95-1.0], respectively). Mass and volume increased exponentially, showing good agreement with 3D mass estimates up to 28 weeks of gestation, after which our measurements were in better agreement with neonatal cardiac magnetic resonance imaging. There was good agreement with 4D volume estimates for the left ventricle. CONCLUSION: Current state-of-the-art 2D echocardiography platforms provide accurate, feasible, and reproducible fetal ventricular measures across gestation, and in certain circumstances may be the modality of choice.

Disproportionate cardiac hypertrophy during early postnatal development in infants born preterm.

BackgroundAdults born very preterm have increased cardiac mass and reduced function. We investigated whether a hypertrophic phenomenon occurs in later preterm infants and when this occurs during early development.MethodsCardiac ultrasound was performed on 392 infants (33% preterm at mean gestation 34±2 weeks). Scans were performed during fetal development in 137, at birth and 3 months of postnatal age in 200, and during both fetal and postnatal development in 55. Cardiac morphology and function was quantified and computational models created to identify geometric changes.ResultsAt birth, preterm offspring had reduced cardiac mass and volume relative to body size with a more globular heart. By 3 months, ventricular shape had normalized but both left and right ventricular mass relative to body size were significantly higher than expected for postmenstrual age (left 57.8±41.9 vs. 27.3±29.4%, P<0.001; right 39.3±38.1 vs. 16.6±40.8, P=0.002). Greater changes were associated with lower gestational age at birth (left P<0.001; right P=0.001).ConclusionPreterm offspring, including those born in late gestation, have a disproportionate increase in ventricular mass from birth up to 3 months of postnatal age. These differences were not present before birth. Early postnatal development may provide a window for interventions relevant to long-term cardiovascular health.

Data-driven shape parameterization for segmentation of the right ventricle from 3D+t echocardiography.

Model-based segmentation facilitates the accurate measurement of geometric properties of anatomy from ultrasound images. Regularization of the model surface is typically necessary due to the presence of noisy and incomplete boundaries. When simple regularizers are insufficient, linear basis shape models have been shown to be effective. However, for problems such as right ventricle (RV) segmentation from 3D+t echocardiography, where dense consistent landmarks and complete boundaries are absent, acquiring accurate training surfaces in dense correspondence is difficult. As a solution, this paper presents a framework which performs joint segmentation of multiple 3D+t sequences while simultaneously optimizing an underlying linear basis shape model. In particular, the RV is represented as an explicit continuous surface, and segmentation of all frames is formulated as a single continuous energy minimization problem. Shape information is automatically shared between frames, missing boundaries are implicitly handled, and only coarse surface initializations are necessary. The framework is demonstrated to successfully segment both multiple-view and multiple-subject collections of 3D+t echocardiography sequences, and the results confirm that the linear basis shape model is an effective model constraint. Furthermore, the framework is shown to achieve smaller segmentation errors than a state-of-art commercial semi-automatic RV segmentation package.