Access to MRI in Patients With Cardiac Implantable Electronic Devices is Variable and an Issue in Australia.

AIMS: This study aimed to characterise the level of access to magnetic resonance imaging (MRI) in Australian hospitals for patients with MR-conditional and non-MR-conditional cardiac implantable electronic devices (CIED), and to identify any barriers impeding this access. METHODS: All Australian Tertiary Referral Public Hospitals (n=38) were surveyed with a mixed qualitative and quantitative questionnaire. Provision of MRI to patients with MR-conditional and non-MR-conditional CIEDs; patient monitoring strategies during scan and personnel in attendance; barriers impeding MRI access. RESULTS: Of the 35 (92%) hospitals that completed the survey, a majority (85.7%) scan MR-conditional CIEDs, while a minority (8.6%) scan non-MR-conditional CIEDs. MR-conditional device scanning is often limited to non-pacing dependent patients, excluding implantable cardioverter-defibrillators. In total, 21% of sites exclude thoracic MR scans for CIED patients. Although most centres scan on 1.5 Tesla (T) machines (59%), 10% scan at 3T and 31% scan at both strengths. Sites vary in patient monitoring strategies and personnel in attendance; 80% require staff with Advanced Cardiac Life Support to be present. Barriers to service expansion include an absence of national guidelines, formal training, and logistical device support. CONCLUSIONS: Most surveyed Australian hospitals offer MRI for patients with MR-conditional CIEDs, however many still have exclusions for particular patient groups or scan requests. Only three surveyed sites offer MRI for patients with non-MR-conditional CIEDs in Australia. A national effort is needed to address the identified barriers including the development of national guidelines, formal training, and logistical support.

Echocardiographic estimation of pulmonary artery wedge pressure: invasive derivation, validation, and prognostic association beyond diastolic dysfunction grading.

AIMS: Grading of diastolic function can be useful, but indeterminate classifications are common. We aimed to invasively derive and validate a quantitative echocardiographic estimation of pulmonary artery wedge pressure (PAWP) and to compare its prognostic performance to diastolic dysfunction grading. METHODS AND RESULTS: Echocardiographic measures were used to derive an estimated PAWP (ePAWP) using multivariable linear regression in patients undergoing right heart catheterization (RHC). Prognostic associations were analysed in the National Echocardiography Database of Australia (NEDA). In patients who had undergone both RHC and echocardiography within 2 h (n = 90), ePAWP was derived using left atrial volume index, mitral peak early velocity (E), and pulmonary vein systolic velocity (S). In a separate external validation cohort (n = 53, simultaneous echocardiography and RHC), ePAWP showed good agreement with invasive PAWP (mean ± standard deviation difference 0.5 ± 5.0 mmHg) and good diagnostic accuracy for estimating PAWP >15 mmHg [area under the curve (95% confidence interval) 0.94 (0.88-1.00)]. Among patients in NEDA [n = 38,856, median (interquartile range) follow-up 4.8 (2.3-8.0) years, 2756 cardiovascular deaths], ePAWP was associated with cardiovascular death even after adjustment for age, sex, and diastolic dysfunction grading [hazard ratio (HR) 1.08 (1.07-1.09) per mmHg] and provided incremental prognostic information to diastolic dysfunction grading (improved C-statistic from 0.65 to 0.68, P < 0.001). Increased ePAWP was associated with worse prognosis across all grades of diastolic function [HR normal, 1.07 (1.06-1.09); indeterminate, 1.08 (1.07-1.09); abnormal, 1.08 (1.07-1.09), P < 0.001 for all]. CONCLUSION: Echocardiographic ePAWP is an easily acquired continuous variable with good accuracy that associates with prognosis beyond diastolic dysfunction grading.

Vascular aging and cardiovascular disease: pathophysiology and measurement in the coronary arteries.

Age is a key risk factor for cardiovascular disease, including atherosclerosis. However, pathophysiological disease processes in the arteries are not an inevitable feature of aging. Large cohort studies with arterial phenotyping along with clinical and demographic data are essential to better understand factors related to the susceptibility or resilience to age-related vascular pathophysiology in humans. This review explores the mechanisms by which vascular structure and function alters with age, and how these changes relate to cardiovascular pathophysiology and disease. Features of vascular aging in the coronary arteries have historically been difficult to quantify pre-mortem due to their size and location. However, non-invasive imaging modalities including CT Coronary Angiogram are now being used to assess coronary vascular age, and further advances in imaging analysis such as the CT Fat Attenuation Index will help provide further measurement of features associated with coronary vascular aging. Currently, markers of vascular aging are not used as therapeutic targets in routine clinical practice, but non-pharmacological interventions including aerobic exercise and low salt diet, as well as anti-hypertensives have been demonstrated to reduce arterial stiffness. Advances in imaging technology, both in acquisition and advanced analysis, as well as harmonisation of measurements for researchers across the globe will be invaluable in understanding what constitutes healthy vascular aging and in identifying features of vascular aging that are associated with coronary artery disease and its adverse outcomes. Assessing such images in large cohorts can facilitate improved definitions of resilient and susceptible phenotypes to vascular aging in the coronary arteries. This is a critical step in identifying further risk factors and biomarkers within these groups and driving forward the development of novel therapies aimed at slowing or stopping age-related vascular changes in the coronary arteries.

Lifestyle changes and quality of life a year after attending Rapid Access Cardiology Clinics: an observational study.

We examined behavioural risk factors and quality of life (QoL) in women and men, younger and older adults 12 months after a Rapid Access Cardiology Clinic (RACC) visit. Routine clinical care data were collected in person from three Sydney hospitals between 2017 and 2018 and followed up by questionnaire at 365 days. 1491 completed the baseline survey, at 1 year, 1092 provided follow-up data on lifestyle changes, and 811 completed the EQ-5D-5L (QoL) survey. 666 (44.7%) were women, and 416 (27.9%) were older than 60 years of age. Almost 50% of participants reported improving physical activity and diet a year after their RACC visit. These changes were less likely in women and older participants.

Prognostic utility and characterization of left ventricular hypertrophy using global thickness.

Cardiovascular magnetic resonance (CMR) can accurately measure left ventricular (LV) mass, and several measures related to LV wall thickness exist. We hypothesized that prognosis can be used to select an optimal measure of wall thickness for characterizing LV hypertrophy. Subjects having undergone CMR were studied (cardiac patients, n = 2543; healthy volunteers, n = 100). A new measure, global wall thickness (GT, GTI if indexed to body surface area) was accurately calculated from LV mass and end-diastolic volume. Among patients with follow-up (n = 1575, median follow-up 5.4 years), the most predictive measure of death or hospitalization for heart failure was LV mass index (LVMI) (hazard ratio (HR)[95% confidence interval] 1.16[1.12-1.20], p < 0.001), followed by GTI (HR 1.14[1.09-1.19], p < 0.001). Among patients with normal findings (n = 326, median follow-up 5.8 years), the most predictive measure was GT (HR 1.62[1.35-1.94], p < 0.001). GT and LVMI could characterize patients as having a normal LV mass and wall thickness, concentric remodeling, concentric hypertrophy, or eccentric hypertrophy, and the three abnormal groups had worse prognosis than the normal group (p < 0.05 for all). LV mass is highly prognostic when mass is elevated, but GT is easily and accurately calculated, and adds value and discrimination amongst those with normal LV mass (early disease).

Challenges and opportunities for early career medical professionals in cardiovascular magnetic resonance (CMR) imaging: a white paper from the Society for Cardiovascular Magnetic Resonance.

The early career professionals in the field of Cardiovascular Magnetic Resonance (CMR) face unique challenges and hurdles while establishing their careers in the field. The Society for Cardiovascular Magnetic Resonance (SCMR) has expanded the role of the early career section within the society to foster the careers of future CMR leaders. This paper aims to describe the obstacles and available opportunities for the early career CMR professionals worldwide. Societal opportunities and actions targeted at the professional advancement of the early career CMR imagers are needed to ensure continuous growth of CMR as an imaging modality globally.

Heart failure among Indigenous and non-Indigenous Australians in remote Central Australia.

BACKGROUND: There is a paucity of data on the burden of heart failure (HF) in Central Australia, the most populous Indigenous region in the country. AIMS: To characterize Indigenous and non-Indigenous Australians with HF in Central Australia. METHODS: Consecutive patients with HF and reduced ejection fraction <50% were included for the period 2019 to 2021. Clinical, echocardiographic and major adverse cardiovascular events (MACE) data were collected. RESULTS: Four hundred twenty-four patients with HF were included (70% Indigenous, 59% male; follow-up 2.2 ± 0.5 years). Indigenous Australians were younger (53 ± 15 vs 68 ± 13 years, P < 0.001) with higher rates of rheumatic heart disease (18% vs 1%, P < 0.001), diabetes (63% vs 33%, P < 0.001) and severe chronic kidney disease (CKD; 32% vs 7%, P < 0.001). HF was more prevalent among Indigenous (138 [95% confidence interval (CI), 123-155] per 10 000) compared with non-Indigenous Australians (53 [95% CI, 44-63] per 10 000), particularly among younger individuals and females. There were similar HF aetiologies between groups. Guideline-directed medical therapy (GDMT) was suboptimal and similar between the groups: angiotensin-converting enzyme inhibitor/angiotensin receptor blocker (64% vs 67%, P = 0.47) and ß-blockers (68% vs 71%, P = 0.47). Indigenous Australians had a significantly higher rate of MACE (54% vs 28%, P < 0.001) and death from any cause (24% vs 13%, P = 0.013). CONCLUSIONS: HF is more than two times as prevalent among Indigenous Central Australians, particularly among younger individuals and females. Despite similar HF aetiologies and GDMT, MACE and mortality outcomes are higher in Indigenous individuals with HF. These data have implications for efforts to close the Indigenous gap in morbidity and mortality.

Prognostic association supports indexing size measures in echocardiography by body surface area.

Body surface area (BSA) is the most commonly used metric for body size indexation of echocardiographic measures, but its use in patients who are underweight or obese is questioned (body mass index (BMI) < 18.5 kg/m2 or ≥ 30 kg/m2, respectively). We aim to use survival analysis to identify an optimal body size indexation metric for echocardiographic measures that would be a better predictor of survival than BSA regardless of BMI. Adult patients with no prior valve replacement were selected from the National Echocardiography Database Australia. Survival analysis was performed for echocardiographic measures both unindexed and indexed to different body size metrics, with 5-year cardiovascular mortality as the primary endpoint. Indexation of echocardiographic measures (left ventricular end-diastolic diameter [n = 230,109] and mass [n = 224,244], left atrial volume [n = 150,540], aortic sinus diameter [n = 90,805], right atrial area [n = 59,516]) by BSA had better prognostic performance vs unindexed measures (underweight: C-statistic 0.655 vs 0.647; normal weight/overweight: average C-statistic 0.666 vs 0.625; obese: C-statistic 0.627 vs 0.613). Indexation by other body size metrics (lean body mass, height, and/or weight raised to different powers) did not improve prognostic performance versus BSA by a clinically relevant magnitude (average C-statistic increase ≤ 0.02), with smaller differences in other BMI subgroups. Indexing measures of cardiac and aortic size by BSA improves prognostic performance regardless of BMI, and no other body size metric has a clinically meaningful better performance.

Decreased diastolic hydraulic forces incrementally associate with survival beyond conventional measures of diastolic dysfunction.

Decreased hydraulic forces during diastole contribute to reduced left ventricular (LV) filling and heart failure with preserved ejection fraction. However, their association with diastolic function and patient outcomes are unknown. The aim of this retrospective, cross-sectional study was to determine the mechanistic association between diastolic hydraulic forces, estimated by echocardiography as the atrioventricular area difference (AVAD), and both diastolic function and survival. Patients (n = 5176, median [interquartile range] 5.5 [5.0-6.1] years follow-up, 1213 events) were selected from the National Echo Database Australia (NEDA) based on the presence of relevant transthoracic echocardiographic measures, LV ejection fraction (LVEF) ≥ 50%, heart rate 50-100 beats/minute, the absence of moderate or severe valvular disease, and no prior prosthetic valve surgery. NEDA contains echocardiographic and linked national death index mortality outcome data from 1985 to 2019. AVAD was calculated as the cross-sectional area difference between the LV and left atrium. LV diastolic dysfunction was graded according to 2016 guidelines. AVAD was weakly associated with E/e', left atrial volume index, and LVEF (multivariable global R2 = 0.15, p < 0.001), and not associated with e' and peak tricuspid regurgitation velocity. Decreased AVAD was independently associated with poorer survival, and demonstrated improved model discrimination after adjustment for diastolic function grading (C-statistic [95% confidence interval] 0.644 [0.629-0.660] vs 0.606 [0.592-0.621], p < 0.001) and E/e' (0.649 [0.635-0.664] vs 0.634 [0.618-0.649], p < 0.001), respectively. Therefore, decreased hydraulic forces, estimated by AVAD, are weakly associated with diastolic dysfunction and demonstrate an incremental prognostic association with survival beyond conventional measures used to grade diastolic dysfunction.

Rapid access chest pain clinics in Australia and New Zealand.

Chest pain is the second most common reason for adult emergency department presentations. Most patients have low or intermediate risk chest pain, which historically has led to inpatient admission for further evaluation. Rapid access chest pain clinics represent an innovative outpatient pathway for these low and intermediate risk patients, and have been shown to be safe and reduce hospital costs. Despite variations in rapid access chest pain clinic models, there are limited data to determine the most effective approach. Developing a national framework could be beneficial to provide sites with evidence, possible models, and business cases. Multicentre data analysis could enhance understanding and monitoring of the service.

Health Economic Analysis of CMR: A Systematic Review.

INTRODUCTION: Uptake of cardiac magnetic resonance (CMR) in Australia has been limited by issues of cost and access. There is a need to inform future application of CMR by evaluating pertinent health economic literature. We sought to perform a systematic review on the health economic data as it pertains to CMR. METHODS: Eight databases (biomedical/health economic) were searched for relevant articles highlighting economic evaluations of CMR. Following screening, studies that reported health economic outcomes (e.g., dollars saved, quality adjusted life years [QALY] and cost effectiveness ratios) were included. Data on cost effectiveness, clinical/disease characteristics, type of modelling were extracted and summarised. RESULTS: Thirty-eight (38) articles informed the systematic review. Health economic models used to determine cost effectiveness included both trial-based studies (n=14) and Markov modelling (n=24). Comparative strategies ranged from nuclear imaging, stress echocardiography and invasive angiography. The disease states examined included coronary artery disease (23/38), acute coronary syndrome (3/38), heart failure (5/38) and miscellaneous (7/38). The majority of studies (n=29/38) demonstrated CMR as a strategy which is either economically dominant, cost-effective or cost-saving. CONCLUSION: This systematic review demonstrates that CMR is cost-effective depending on diagnostic strategy, population and disease state. The lack of standardised protocols for application of CMR, economic models used and outcomes reported limits the ability to meta-analyse the available health economic data.

Increased cardiac involvement in Fabry disease using blood-corrected native T1 mapping.

Fabry disease (FD) is a rare lysosomal storage disorder resulting in myocardial sphingolipid accumulation which is detectable by cardiovascular magnetic resonance as low native T1. However, myocardial T1 contains signal from intramyocardial blood which affects variability and consequently measurement precision and accuracy. Correction of myocardial T1 by blood T1 increases precision. We therefore deployed a multicenter study of FD patients (n = 218) and healthy controls (n = 117) to investigate if blood-correction of myocardial native T1 increases the number of FD patients with low T1, and thus reclassifies FD patients as having cardiac involvement. Cardiac involvement was defined as a native T1 value 2 standard deviations below site-specific means in healthy controls for both corrected and uncorrected measures. Overall low T1 was 135/218 (62%) uncorrected vs. 145/218 (67%) corrected (p = 0.02). With blood-correction, 13/83 previously normal patients were reclassified to low T1. This reclassification appears clinically relevant as 6/13 (46%) of reclassified had focal late gadolinium enhancement or left ventricular hypertrophy as signs of cardiac involvement. Blood-correction of myocardial native T1 increases the proportion of FD subjects with low myocardial T1, with blood-corrected results tracking other markers of cardiac involvement. Blood-correction may potentially offer earlier detection and therapy initiation, but merits further prospective studies.

Stress perfusion cardiovascular magnetic resonance imaging: a guide for the general cardiologist.

Stress cardiovascular magnetic resonance (CMR) is an emerging non-invasive imaging technique for the assessment of known or suspected ischaemic heart disease (IHD). Stress CMR provides information on myocardial perfusion, wall motion, ventricular dimensions and volumes, as well as late gadolinium enhancement (LGE) scar imaging in a single test without ionising radiation. Data from numerous multicentre randomised studies show high diagnostic and prognostic utility, its efficacy as a gatekeeper to invasive coronary angiography and use for guiding coronary revascularisation decisions. Stress CMR is cost-effective across multiple healthcare settings, yet its uptake and usage varies worldwide and is an underutilised technology. New developments include rapid acquisition protocols, automated quantification of perfusion and myocardial blood flow, and artificial intelligence-aided automated analysis and reporting. Stress CMR is becoming more accessible and standardised around the globe and is ready for 'prime time' use in the non-invasive assessment of patients with suspected IHD.

Competency based curriculum for cardiovascular magnetic resonance: A position statement of the Society for Cardiovascular Magnetic Resonance.

This position statement guides cardiovascular magnetic resonance (CMR) imaging program directors and learners on the key competencies required for Level II and III CMR practitioners, whether trainees come from a radiology or cardiology background. This document is built upon existing curricula and was created and vetted by an international panel of cardiologists and radiologists on behalf of the Society for Cardiovascular Magnetic Resonance (SCMR).

Society for Cardiovascular Magnetic Resonance 2022 Cases of SCMR case series.

"Cases of SCMR" is a case series on the SCMR website (https://www.scmr.org) for the purpose of education. The cases reflect the clinical presentation, and the use of cardiovascular magnetic resonance (CMR) in the diagnosis and management of cardiovascular disease. The 2022 digital collection of cases are presented in this manuscript.

Improved evaluation of left ventricular hypertrophy using the spatial QRS-T angle by electrocardiography.

Electrocardiographic (ECG) signs of left ventricular hypertrophy (LVH) lack sensitivity. The aim was to identify LVH based on an abnormal spatial peaks QRS-T angle, evaluate its diagnostic performance compared to conventional ECG criteria for LVH, and its prognostic performance. This was an observational study with four cohorts with a QRS duration < 120 ms. Based on healthy volunteers (n = 921), an abnormal spatial peaks QRS-T angle was defined as ≥ 40° for females and ≥ 55° for males. In other healthy volunteers (n = 461), the specificity of the QRS-T angle to detect LVH was 96% (females) and 98% (males). In patients with at least moderate LVH by cardiac imaging (n = 225), the QRS-T angle had a higher sensitivity than conventional ECG criteria (93-97% vs 13-56%, p < 0.001 for all). In clinical consecutive patients (n = 783), of those who did not have any LVH, 238/556 (43%) had an abnormal QRS-T angle. There was an association with hospitalization for heart failure or all-cause death in univariable and multivariable analysis. An abnormal QRS-T angle rarely occurred in healthy volunteers, was a mainstay of moderate or greater LVH, was common in clinical patients without LVH but with cardiac co-morbidities, and associated with outcomes.

Cardiovascular magnetic resonance characteristics and clinical outcomes of patients with ST-elevation myocardial infarction and no standard modifiable risk factors-A DANAMI-3 substudy.

Introduction: A higher 30-day mortality has been observed in patients with first-presentation ST elevation myocardial infarction (STEMI) who have no standard modifiable cardiovascular risk factors (SMuRFs), i. e., diabetes, hypertension, hyperlipidemia, and current smoker. In this study, we evaluate the clinical outcomes and CMR imaging characteristics of patients with and without SMuRFs who presented with first-presentation STEMI. Methods: Patients from the Third DANish Study of Acute Treatment of Patients With ST-Segment Elevation Myocardial Infarction (DANAMI-3) with first-presentation STEMI were classified into those with no SMuRFs vs. those with at least one SMuRF. Results: We identified 2,046 patients; 283 (14%) SMuRFless and 1,763 (86%) had >0 SMuRF. SMuRFless patients were older (66 vs. 61 years, p < 0.001) with more males (84 vs. 74%, p < 0.001), more likely to have left anterior descending artery (LAD) as the culprit artery (50 vs. 42%, p = 0.009), and poor pre-PCI (percutaneous coronary intervention) TIMI (thrombolysis in myocardial infarction) flow ≤1 (78 vs. 64%; p < 0.001). There was no difference in all-cause mortality, non-fatal reinfarction, or hospitalization for heart failure at 30 days or at long-term follow-up. CMR imaging was performed on 726 patients. SMuRFless patients had larger acute infarct size (17 vs. 13%, p = 0.04) and a smaller myocardial salvage index (42 vs. 50%, p = 0.02). These differences were attenuated when the higher LAD predominance and/or TIMI 0-1 flow were included in the model. Conclusion: Despite no difference in 30-day mortality, SMuRFless patients had a larger infarct size and a smaller myocardial salvage index following first-presentation STEMI. This association was mediated by a larger proportion of LAD culprits and poor TIMI flow pre-PCI. Clinical trial registration: clinicaltrials.gov, unique identifier: NCT01435408 (DANAMI 3-iPOST and DANAMI 3-DEFER) and NCT01960933 (DANAMI 3-PRIMULTI).

Clinical Outcomes in Patients With ST-Segment Elevation MI and No Standard Modifiable Cardiovascular Risk Factors.

BACKGROUND: The author recently reported ∼50% excess early mortality in patients with first-presentation ST-segment elevation myocardial infarction (STEMI) without standard modifiable cardiovascular risk factors (SMuRFs); the cause of this is not clear. OBJECTIVES: The aim of this study was to examine differences in infarct characteristics and clinical outcomes in patients with versus without SMuRFs (dyslipidemia, hypertension, diabetes mellitus, and smoking). METHODS: Individual-level data were pooled from 10 randomized percutaneous intervention (PCI) trials in which infarct size was measured within 1 month by either cardiac magnetic resonance or technetium-99m sestamibi single-photon emission computed tomography imaging. First-presentation STEMI was classified into 2 groups according to the presence or absence of at least 1 SMuRF. RESULTS: Among 2,862 patients, 524 (18.3%) were SMuRF-less. After adjusting for study effect, SMuRF-less patients had more frequent poor pre-PCI flow Thrombolysis In Myocardial Infarction 0/1 compared with patients with at least 1 SMuRF (72.0% vs 64.1%; OR: 1.35; 95% CI: 1.08-1.70). There were no independent associations between the presence or absence of SMuRFs at baseline and infarct size (estimate = -0.35; 95% CI: -1.93 to 1.23), left ventricular ejection fraction (estimate = -0.06; 95% CI: -1.33 to 1.20), or mortality at 30 days (HR: 0.46; 95% CI: 0.19-1.07) and 1 year (HR: 0.74; 95% CI: 0.43-1.29). CONCLUSIONS: First-presentation STEMI patients with no identifiable baseline SMuRFs had a higher risk of Thrombolysis In Myocardial Infarction flow grade 0/1 pre-PCI. However, after adjustment, there were no significant associations between SMuRF-less status and infarct size, left ventricle ejection fraction, or mortality.

Non-invasive Imaging in Women With Heart Failure - Diagnosis and Insights Into Disease Mechanisms.

PURPOSE OF REVIEW: To summarise the role of different imaging techniques for diagnosis and investigation of heart failure in women. RECENT FINDINGS: Although sex differences in heart failure are well recognised, and the scope of imaging techniques is expanding, there are currently no specific guidelines for imaging of heart failure in women. Diagnosis and stratification of heart failure is generally performed first line using transthoracic echocardiography. Understanding the aetiology of heart failure is central to ongoing management, and with non-ischaemic causes more common in women, a multimodality approach is generally required using advanced imaging techniques including cardiovascular magnetic resonance imaging, nuclear imaging techniques, and cardiac computed tomography. There are specific considerations for imaging in women including radiation risks and challenges during pregnancy, highlighting the clear unmet need for cardiology and imaging societies to provide imaging guidelines specifically for women with heart failure.

Precision measurement of cardiac structure and function in cardiovascular magnetic resonance using machine learning.

BACKGROUND: Measurement of cardiac structure and function from images (e.g. volumes, mass and derived parameters such as left ventricular (LV) ejection fraction [LVEF]) guides care for millions. This is best assessed using cardiovascular magnetic resonance (CMR), but image analysis is currently performed by individual clinicians, which introduces error. We sought to develop a machine learning algorithm for volumetric analysis of CMR images with demonstrably better precision than human analysis. METHODS: A fully automated machine learning algorithm was trained on 1923 scans (10 scanner models, 13 institutions, 9 clinical conditions, 60,000 contours) and used to segment the LV blood volume and myocardium. Performance was quantified by measuring precision on an independent multi-site validation dataset with multiple pathologies with n = 109 patients, scanned twice. This dataset was augmented with a further 1277 patients scanned as part of routine clinical care to allow qualitative assessment of generalization ability by identifying mis-segmentations. Machine learning algorithm ('machine') performance was compared to three clinicians ('human') and a commercial tool (cvi42, Circle Cardiovascular Imaging). FINDINGS: Machine analysis was quicker (20 s per patient) than human (13 min). Overall machine mis-segmentation rate was 1 in 479 images for the combined dataset, occurring mostly in rare pathologies not encountered in training. Without correcting these mis-segmentations, machine analysis had superior precision to three clinicians (e.g. scan-rescan coefficients of variation of human vs machine: LVEF 6.0% vs 4.2%, LV mass 4.8% vs. 3.6%; both P < 0.05), translating to a 46% reduction in required trial sample size using an LVEF endpoint. CONCLUSION: We present a fully automated algorithm for measuring LV structure and global systolic function that betters human performance for speed and precision.