Mitral Annular Disjunction: An Under-Recognized Entity in Pediatrics.

Mitral annular disjunction (MAD) is a rare and under-recognized entity in the pediatric population. We present 2 cases of MAD in previously healthy pediatric patients and highlight clinical scenarios where MAD should be suspected.

Interstitial Fibrosis and Arrhythmic Mitral Valve Prolapse: Unravelling Sex-Based Differences.

Background: Interstitial fibrosis as quantified by cardiac magnetic resonance (CMR) has been demonstrated in arrhythmic mitral valve prolapse (MVP), a condition with known female predominance. However, prior studies included only MVP cases with significant mitral regurgitation (MR) or mitral annular disjunction (MAD). We sought to evaluate the association between interstitial fibrosis and complex ventricular ectopy (ComVE) in MVPs unselected for MAD or severe MR, and to investigate the contribution of sex to this association. Methods: We performed contrast CMR in consecutive individuals with MVP between 2020 and 2022. Extracellular volume fraction (ECV%), a surrogate marker for interstitial fibrosis, was quantified using T 1 mapping. Replacement fibrosis was assessed using late gadolinium enhancement (LGE). ComVE, defined as frequent premature ventricular contractions and/or non-sustained/sustained ventricular tachycardia (VT), was detected using ambulatory ECG monitoring. Results: We identified 59 MVP cases without severe MR (49% women, 80% with mild or less MR) and available ECV% measurement. Among these, 23 (39%) had ComVE, including a case of aborted ventricular fibrillation (VF) and one with sudden arrhythmic death, both females. Global ECV% was significantly greater in ComVE versus non-ComVE (31%[27-33] vs 27%[23-30], p=0.002). In MVP-ComVE, higher segmental ECV% was not limited to the inferolateral/inferior LV wall, but was also demonstrated in atypical segments including the anterior/anterolateral wall (p<0.05). The association between ComVE and ECV% was driven by female sex (32%[30-33] vs 28%[26-30], p=0.003 in females; 31%[25-33] vs 26%[23-30], p=0.22 in males). ECV% remained independently associated with an increased risk of ComVE, including VT/VF, after adjustment for cardiovascular risk factors, MAD, and LGE (p<0.01). Conclusion: In MVP without significant MR, interstitial fibrosis by CMR is associated with an increased risk of ComVE, suggesting a primary myopathic process. The stronger association between interstitial fibrosis and ComVE in females may explain why severe arrhythmic complications are more prevalent among women.

Cannabis use and incident atrial fibrillation in a longitudinal cohort.

BACKGROUND: Cannabis use is increasing worldwide. While prior studies have reported an association between cannabis use and a higher risk of atrial fibrillation (AF), most were cross-sectional and generally relied on diagnostic coding to identify cannabis users, which may not be representative of the typical recreational cannabis user. OBJECTIVE: The purpose of this study was to examine the association between recreational cannabis use and lifetime AF risk. METHODS: We evaluated the AF risk of participants of the UK Biobank cohort who completed the cannabis use lifestyle questionnaire. Cannabis exposure was categorized as "Occasional Use" for less than 100 times used, "Frequent Use" for more than 100 times used, and "Never" users. AF events were identified using International Classification of Diseases codes. Cox models were used to estimate the hazard ratios (HRs) between cannabis use and incident AF and were subsequently adjusted for age, sex, race, alcohol, coffee, smoking, education, and baseline cardiovascular comorbidities. RESULTS: A total of 150,554 participants (mean age 63.4 ± 7.7 years; 86,487 (57.4%) female; and 33,442 (22.2%) using cannabis at least once) were followed for a mean period of 6.1 ± 0.6 years. After multivariable adjustment, there were no statistically significant differences in incident AF among occasional users (HR 0.98; 95% confidence interval 0.89-1.08) nor frequent users (HR 1.03; 95% confidence interval 0.81-1.32) as compared with never users. CONCLUSION: In a large prospective cohort study, there was no evidence that cannabis use was associated with a higher risk of incident AF. An evaluation of cannabis ingestion methods and quantification was not possible using the current data set.

Identifying Mitral Valve Prolapse at Risk for Arrhythmias and Fibrosis From Electrocardiograms Using Deep Learning.

BACKGROUND: Mitral valve prolapse (MVP) is a common valvulopathy, with a subset developing sudden cardiac death or cardiac arrest. Complex ventricular ectopy (ComVE) is a marker of arrhythmic risk associated with myocardial fibrosis and increased mortality in MVP. OBJECTIVES: The authors sought to evaluate whether electrocardiogram (ECG)-based machine learning can identify MVP at risk for ComVE, death and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging. METHODS: A deep convolutional neural network (CNN) was trained to detect ComVE using 6,916 12-lead ECGs from 569 MVP patients from the University of California-San Francisco between 2012 and 2020. A separate CNN was trained to detect late gadolinium enhancement (LGE) using 1,369 ECGs from 87 MVP patients with contrast CMR. RESULTS: The prevalence of ComVE was 28% (160/569). The area under the receiver operating characteristic curve (AUC) of the CNN to detect ComVE was 0.80 (95% CI: 0.77-0.83) and remained high after excluding patients with moderate-severe mitral regurgitation [0.80 (95% CI: 0.77-0.83)] or bileaflet MVP [0.81 (95% CI: 0.76-0.85)]. AUC to detect all-cause mortality was 0.82 (95% CI: 0.77-0.87). ECG segments relevant to ComVE prediction were related to ventricular depolarization/repolarization (early-mid ST-segment and QRS from V1, V3, and III). LGE in the papillary muscles or basal inferolateral wall was present in 24% patients with available CMR; AUC for detection of LGE was 0.75 (95% CI: 0.68-0.82). CONCLUSIONS: CNN-analyzed 12-lead ECGs can detect MVP at risk for ventricular arrhythmias, death and/or fibrosis and can identify novel ECG correlates of arrhythmic risk. ECG-based CNNs may help select those MVP patients requiring closer follow-up and/or a CMR.

Stroke in mitral valve prolapse: risk factors and left atrial function in cryptogenic versus non-cryptogenic ischemic subtypes.

Background and purpose: Mitral valve prolapse (MVP) has been associated with an increased risk of ischemic stroke. Older age, thicker mitral leaflets, and significant mitral regurgitation (MR) leading to atrial fibrillation have been traditionally considered risk factors for ischemic stroke in MVP. However, specific risk factors for MVP-stroke subtypes are not well defined. The aim of this study is to evaluate clinical and echocardiographic parameters, including left atrial (LA) function, in MVP with cryptogenic (C) vs. non-cryptogenic (NC) stroke. Methods: In this case-control matched study, MVPs were identified in consecutive echocardiograms obtained after a stroke from January 2013 to December2016 at the University of California, San Francisco. MVP was defined as leaflet displacement ≥2 mm in the parasternal long-axis view at end-systole. Age/gender matched MVPs without stroke and healthy controls without MVP were also identified. We analyzed LA end-systolic/diastolic volume index, emptying fraction (LAEF), function index (LAFI), and global longitudinal strain in all MVPs and controls. We also measured left ventricular (LV) volume indexes, mass index, ejection fraction (EF), degree of MR and leaflet thickness. Results: We identified a total of 30 MVPs (age 70 ± 12, 50% females) with stroke (11 with C- and 19 with NC-stroke), 20 age/gender matched MVPs without a stroke and 16 controls. MVPs without stroke had lower BMI, less hypertension but more MR (≥moderate in 45% vs. 17%), more abnormal LA function (lower LAEF, LAFI) and larger LV volumes/mass (all p < 0.05) when compared to MVPs with stroke. Leaflet thickness was overall mild (<3 mm) and similar in the 2 groups. Within the MVP stroke group, NC-stroke had higher BMI, more hypertension and more atrial fibrillation compared to C-stroke. In the variables tested, patients with C-stroke did not differ from controls. Conclusions: MVP-related MR may be protective against stroke despite abnormal LA function. Risk of NC-stroke in MVP is related to common stroke risk factors rather than mitral valve leaflet thickness. The etiology of C-stroke in MVP warrants further studies.

Mechanical Dispersion Discriminates between Arrhythmic and Non-Arrhythmic Sudden Death: From the POST SCD Study.

Background: Global longitudinal strain (GLS) and mechanical dispersion (MD) by speckle-tracking echocardiography can predict sudden cardiac death (SCD) beyond left ventricular ejection fraction (LVEF) alone. However, prior studies have presumed cardiac cause from EMS records or death certificates rather than gold-standard autopsies. Objectives: We sought to investigate whether abnormal GLS and MD, reflective of underlying myocardial fibrosis, are associated with autopsy-defined sudden arrhythmic death (SAD) in a comprehensive postmortem study. Methods: We identified and autopsied all World Health Organization-defined (presumed) SCDs ages 18-90 via active surveillance of out of hospital deaths in the ongoing San Francisco POstmortem Systematic InvesTigation of Sudden Cardiac Death (POST SCD) Study to refine presumed SCDs to true cardiac causes. We retrieved all available pre-mortem echocardiograms and assessed LVEF, LV-GLS, and MD. The extent of LV myocardial fibrosis was assessed and quantified histologically. Results: Of 652 autopsied subjects, 65 (10%) had echocardiograms available for primary review, obtained at a mean 1.5 years before SCD. Of these, 37 (56%) were SADs and 29 (44%) were non-SADs; fibrosis was quantified in 38 (58%). SADs were predominantly male, but had similar age, race, baseline comorbidities, and LVEF compared to non-SADs (all p>0.05). SADs had significantly reduced LV-GLS (median: -11.4% versus -18.5%, p=0.008) and increased MD (median: 14.8 ms versus 9.4 ms, p=0.006) compared to non-SADs. MD was associated with total LV fibrosis by linear regression in SADs (r=0.58, p=0.002). Conclusion: In this countywide postmortem study of all sudden deaths, autopsy-confirmed arrhythmic deaths had significantly lower LV-GLS and increased MD than non-arrhythmic sudden deaths. Increased MD correlated with higher histologic levels of LV fibrosis in SADs. These findings suggest that increased MD, which is a surrogate for the extent of myocardial fibrosis, may improve risk stratification and specification for SAD beyond LVEF. PERSPECTIVES: Competency in medical knowledge: Mechanical dispersion derived from speckle tracking echocardiography provides better discrimination between autopsy-defined arrhythmic vs non-arrhythmic sudden death than LVEF or LV-GLS. Histological ventricular fibrosis correlates with increased mechanical dispersion in SAD.Translational outlook: Speckle tracking echocardiography parameters, in particular mechanical dispersion, may be considered as a non-invasive surrogate marker for myocardial fibrosis and risk stratification in SCD.

Abnormal Mechanics Relate to Myocardial Fibrosis and Ventricular Arrhythmias in Patients With Mitral Valve Prolapse.

BACKGROUND: The relation between ventricular arrhythmia and fibrosis in mitral valve prolapse (MVP) is reported, but underlying valve-induced mechanisms remain unknown. We evaluated the association between abnormal MVP-related mechanics and myocardial fibrosis, and their association with arrhythmia. METHODS: We studied 113 patients with MVP with both echocardiogram and gadolinium cardiac magnetic resonance imaging for myocardial fibrosis. Two-dimensional and speckle-tracking echocardiography evaluated mitral regurgitation, superior leaflet and papillary muscle displacement with associated exaggerated basal myocardial systolic curling, and myocardial longitudinal strain. Follow-up assessed arrhythmic events (nonsustained or sustained ventricular tachycardia or ventricular fibrillation). RESULTS: Myocardial fibrosis was observed in 43 patients with MVP, predominantly in the basal-midventricular inferior-lateral wall and papillary muscles. Patients with MVP with fibrosis had greater mitral regurgitation, prolapse, and superior papillary muscle displacement with basal curling and more impaired inferior-posterior basal strain than those without fibrosis (P<0.001). An abnormal strain pattern with distinct peaks pre-end-systole and post-end-systole in inferior-lateral wall was frequent in patients with fibrosis (81 versus 26%, P<0.001) but absent in patients without MVP with basal inferior-lateral wall fibrosis (n=20). During median follow-up of 1008 days, 36 of 87 patients with MVP with >6-month follow-up developed ventricular arrhythmias associated (univariable) with fibrosis, greater prolapse, mitral annular disjunction, and double-peak strain. In multivariable analysis, double-peak strain showed incremental risk of arrhythmia over fibrosis. CONCLUSIONS: Basal inferior-posterior myocardial fibrosis in MVP is associated with abnormal MVP-related myocardial mechanics, which are potentially associated with ventricular arrhythmia. These associations suggest pathophysiological links between MVP-related mechanical abnormalities and myocardial fibrosis, which also may relate to ventricular arrhythmia and offer potential imaging markers of increased arrhythmic risk.

Research Opportunities in the Treatment of Mitral Valve Prolapse: JACC Expert Panel.

In light of the adverse prognosis related to severe mitral regurgitation, heart failure, or sudden cardiac death in a subset of patients with mitral valve prolapse (MVP), identifying those at higher risk is key. For the first time in decades, researchers have the means to rapidly advance discovery in the field of MVP thanks to state-of-the-art imaging techniques, novel omics methodologies, and the potential for large-scale collaborations using web-based platforms. The National Heart, Lung, and Blood Institute recently initiated a webinar-based workshop to identify contemporary research opportunities in the treatment of MVP. This report summarizes 3 specific areas in the treatment of MVP that were the focus of the workshop: 1) improving management of degenerative mitral regurgitation and associated left ventricular systolic dysfunction; 2) preventing sudden cardiac death in MVP; and 3) understanding the mechanisms and progression of MVP through genetic studies and small and large animal models, with the potential of developing medical therapies.

Valvular disease burden in the modern era of percutaneous and surgical interventions: the UK Biobank.

BACKGROUND: The burden of valvular heart disease (VHD) has increased significantly among ageing populations, yet remains poorly understood in the present-day context of percutaneous and surgical interventions. OBJECTIVE: To define the incidence, clinical correlates and associated mortality of VHD in the UK Biobank cohort. METHODS: We interrogated data collected in the UK Biobank between 1 January 2000 and 30 June 2020. VHD incidence was determined using International Classification of Disease-10 codes for aortic stenosis (AS), aortic regurgitation (AR), mitral stenosis, mitral regurgitation (MR) and mitral valve prolapse. We calculated HRs for incident VHD and all-cause mortality. Clinical correlates of VHD included demographics, coronary artery disease, heart failure and atrial fibrillation. Surgical and percutaneous interventions for mitral and aortic VHD were considered time-dependent variables. RESULTS: Among 486 187 participants, the incidence of any VHD was 16 per 10 000 person-years, with highest rates for MR (8.2), AS (7.2) and AR (5.0). Age, heart failure, coronary artery disease and atrial fibrillation were significantly associated with all types of VHD. In our adjusted model, aortic and mitral VHD had an increased risk of all-cause death compared with no VHD (HR 1.62, 95% CI 1.44 to 1.82, p<0.001 and HR 1.25, 95% CI 1.09 to 1.44, p=0.002 for aortic and mitral VHD, respectively). CONCLUSION: VHD continues to constitute a significant public health burden, with MR and AS being the most common. Age and cardiac comorbidities remain strong risk factors for VHD. In the modern era of percutaneous and surgical interventions, mortality associated with VHD remains high.

Genome-wide association study reveals novel genetic loci: a new polygenic risk score for mitral valve prolapse.

AIMS: Mitral valve prolapse (MVP) is a common valvular heart disease with a prevalence of >2% in the general adult population. Despite this high incidence, there is a limited understanding of the molecular mechanism of this disease, and no medical therapy is available for this disease. We aimed to elucidate the genetic basis of MVP in order to better understand this complex disorder. METHODS AND RESULTS: We performed a meta-analysis of six genome-wide association studies that included 4884 cases and 434 649 controls. We identified 14 loci associated with MVP in our primary analysis and 2 additional loci associated with a subset of the samples that additionally underwent mitral valve surgery. Integration of epigenetic, transcriptional, and proteomic data identified candidate MVP genes including LMCD1, SPTBN1, LTBP2, TGFB2, NMB, and ALPK3. We created a polygenic risk score (PRS) for MVP and showed an improved MVP risk prediction beyond age, sex, and clinical risk factors. CONCLUSION: We identified 14 genetic loci that are associated with MVP. Multiple analyses identified candidate genes including two transforming growth factor-ß signalling molecules and spectrin ß. We present the first PRS for MVP that could eventually aid risk stratification of patients for MVP screening in a clinical setting. These findings advance our understanding of this common valvular heart disease and may reveal novel therapeutic targets for intervention.

Sex Differences and Similarities in Valvular Heart Disease.

As populations age worldwide, the burden of valvular heart disease has grown exponentially, and so has the proportion of affected women. Although rheumatic valve disease is declining in high-income countries, degenerative age-related causes are rising. Calcific aortic stenosis and degenerative mitral regurgitation affect a significant proportion of elderly women, particularly those with comorbidities. Women with valvular heart disease have been underrepresented in many of the landmark studies which form the basis for guideline recommendations. As a consequence, surgical referrals in women have often been delayed, with worse postoperative outcomes compared with men. As described in this review, a more recent effort to include women in research studies and clinical trials has increased our knowledge about sex-based differences in epidemiology, pathophysiology, diagnostic criteria, treatment options, outcomes, and prognosis.

Antemortem and Post-Mortem Characteristics of Lethal Mitral Valve Prolapse Among All Countywide Sudden Deaths.

OBJECTIVES: The goal of this study was to investigate the characteristics of mitral valve prolapse (MVP) in a post-mortem study of consecutive sudden cardiac deaths (SCDs) in subjects up to 90 years of age. BACKGROUND: Up to 2.3% of subjects with MVPs experience SCD, but by convention SCD is rarely confirmed by autopsy. In a post-mortem study of persons <40 years of age, 7% of SCDs were caused by MVP; bileaflet involvement, mitral annular disjunction (MAD), and replacement fibrosis were common. METHODS: In the San Francisco POST SCD (Postmortem Systematic Investigation of Sudden Cardiac Death) study, autopsies have been performed on >1,000 consecutive World Health Organization-defined (presumed) cases of SCD in subjects aged 18 to 90 years since 2011; a total of 603 were adjudicated. Autopsy-defined sudden arrhythmic death (SAD) required absence of nonarrhythmic cause; MVP diagnosis required leaflet billowing. One hundred antemortem echocardiograms were revised to identify additional MVPs missed on autopsy. RESULTS: Among the 603 presumed SCDs, 339 (56%) were autopsy-defined SADs, with MVP identified in 7 (1%). Six additional MVPs were identified by review of echocardiograms, for a prevalence of at least 2% among 603 presumed SCDs and 4% among 339 SADs (vs. 264 non-SADs; p = 0.02). All 6 additional MVPs had monoleaflet rather than bileaflet involvement and mild mitral regurgitation, ruling out hemodynamic cause. Less than one-half had MAD with replacement fibrosis, but all had multisite interstitial fibrosis. CONCLUSIONS: In a countywide post-mortem study of all adult cases of SCD, MVP prevalence was at least 4% of SADs, but one-half were missed on autopsy. Monoleaflet MVP was often underdiagnosed post-mortem. Compared with young cases of SCD, lethal MVP in older cases of SCD did not consistently have bileaflet anatomy, replacement fibrosis, or MAD.

Heart Disease and Stroke Statistics-2021 Update: A Report From the American Heart Association.

BACKGROUND: The American Heart Association, in conjunction with the National Institutes of Health, annually reports the most up-to-date statistics related to heart disease, stroke, and cardiovascular risk factors, including core health behaviors (smoking, physical activity, diet, and weight) and health factors (cholesterol, blood pressure, and glucose control) that contribute to cardiovascular health. The Statistical Update presents the latest data on a range of major clinical heart and circulatory disease conditions (including stroke, congenital heart disease, rhythm disorders, subclinical atherosclerosis, coronary heart disease, heart failure, valvular disease, venous disease, and peripheral artery disease) and the associated outcomes (including quality of care, procedures, and economic costs). METHODS: The American Heart Association, through its Statistics Committee, continuously monitors and evaluates sources of data on heart disease and stroke in the United States to provide the most current information available in the annual Statistical Update. The 2021 Statistical Update is the product of a full year's worth of effort by dedicated volunteer clinicians and scientists, committed government professionals, and American Heart Association staff members. This year's edition includes data on the monitoring and benefits of cardiovascular health in the population, an enhanced focus on social determinants of health, adverse pregnancy outcomes, vascular contributions to brain health, the global burden of cardiovascular disease, and further evidence-based approaches to changing behaviors related to cardiovascular disease. RESULTS: Each of the 27 chapters in the Statistical Update focuses on a different topic related to heart disease and stroke statistics. CONCLUSIONS: The Statistical Update represents a critical resource for the lay public, policy makers, media professionals, clinicians, health care administrators, researchers, health advocates, and others seeking the best available data on these factors and conditions.

Characteristics and Significance of Tricuspid Valve Prolapse in a Large Multidecade Echocardiographic Study.

BACKGROUND: Characteristics of tricuspid valve prolapse (TVP) on transthoracic echocardiography are not well defined. As tricuspid valve interventions are increasingly considered, information on the definition and clinical significance of TVP is needed. METHODS: At the authors' institution, between January 26, 2000, and September 20, 2018, 410 patients (0.3%) were determined to have suspected TVP. These transthoracic echocardiograms and those of 97 age- and sex-matched normal control subjects were reviewed. Interrater agreement on TVP by visual inspection was assessed in a blinded subset. Leaflet atrial displacement (AD) > 2 SDs above the mean in normal control subjects was used to identify an empiric definition of TVP Features of patients meeting this definition were evaluated. RESULTS: Three hundred twelve transthoracic echocardiograms with available and interpretable images (76.1%) were included. Interrater agreement on TVP diagnosis by visual inspection was moderate. Normal values of AD were up to 4 mm in the right ventricular inflow view and 2 mm in all other views. AD > 2 mm in the parasternal short-axis view had the best accuracy against suspected TVP to identify TVP. Those with TVP by this definition more frequently had 3 to 4+ tricuspid regurgitation (22.2% vs 3.1%; P < .001), mitral valve prolapse (MVP; 75.0% vs 3.1%; P < .001), and more clinically significant MVP (greater prevalence of 3 to 4+ mitral regurgitation). No difference in mortality was observed in those with isolated TVP versus TVP and MVP (log-rank P = .93). CONCLUSIONS: In the largest study of TVP to date, interrater agreement on TVP diagnosis by visual inspection was moderate. A cutoff of >2-mm AD in the parasternal short-axis view was optimal to define TVP. Those with TVP by this definition had more significant tricuspid regurgitation, larger right ventricles, and more clinically significant MVP. Overall, these results suggest an increased role for surveillance for TVP and the need for clear diagnostic criteria in updated guidelines.

Long-term outcomes of ablation for ventricular arrhythmias in mitral valve prolapse.

PURPOSE: Prior studies reporting efficacy of radiofrequency catheter ablation for complex ventricular ectopy in mitral valve prolapse (MVP) are limited by selective inclusion of bileaflet MVP, papillary muscle only ablation, or short-term follow-up. We sought to evaluate the long-term incidence of hemodynamically significant ventricular tachycardia (VT) or fibrillation (VF) in patients with MVP after initial ablation. METHODS: We studied consecutive patients with MVP undergoing ablation for complex ventricular ectopy between 2013 and 2017 at our institution. Of 580 patients with MVP, we included 15 (2.6%, 10 women; mean age 50 ± 14 years, 53% bileaflet) with complex ventricular ectopy treated with initial ablation. RESULTS: Over a median follow-up of 3406 (1875-6551) days or 9 years, 5 of 15 (33%) patients developed hemodynamically significant VT/VF after their initial ablation and underwent placement of an implantable cardioverter defibrillator (ICD). Three of 5 also underwent repeat ablations. Sustained VT was inducible prior to index ablation in all 5 who developed VT/VF, compared to none of the 10 patients who did not develop VT/VF after index ablation (p = 0.002). Complex ventricular ectopy at index ablation was multifocal in all 5 patients who underwent repeat intervention versus 4 of 10 patients (40%) who did not (p = 0.04). All 3 patients with subsequent VT/VF who underwent repeat ablation had a new clinically dominant focus of ventricular arrhythmia and 3 of the patients with ICD had appropriate VT/VF therapies. CONCLUSIONS: In the long term, a subset of MVP patients treated with ablation for ventricular arrhythmias, all with multifocal ectopy on initial EP study, develop hemodynamically significant VT/VF. Our findings suggest the progressive nature of ventricular arrhythmias in patients with MVP and multifocal ectopy.

Artificial Intelligence in Cardiovascular Imaging.

The number of cardiovascular imaging studies is growing exponentially, and so is the need to improve clinical workflow efficiency and avoid missed diagnoses. With the availability and use of large datasets, artificial intelligence (AI) has the potential to improve patient care at every stage of the imaging chain. Current literature indicates that in the short-term, AI has the capacity to reduce human error and save time in the clinical workflow through automated segmentation of cardiac structures. In the future, AI may expand the informational value of diagnostic images based on images alone or a combination of images and clinical variables, thus facilitating disease detection, prognosis, and decision making. This review describes the role of AI, specifically machine learning, in multimodality imaging, including echocardiography, nuclear imaging, computed tomography, and cardiac magnetic resonance, and highlights current uses of AI as well as potential challenges to its widespread implementation.

Heart Disease and Stroke Statistics-2020 Update: A Report From the American Heart Association.

BACKGROUND: The American Heart Association, in conjunction with the National Institutes of Health, annually reports on the most up-to-date statistics related to heart disease, stroke, and cardiovascular risk factors, including core health behaviors (smoking, physical activity, diet, and weight) and health factors (cholesterol, blood pressure, and glucose control) that contribute to cardiovascular health. The Statistical Update presents the latest data on a range of major clinical heart and circulatory disease conditions (including stroke, congenital heart disease, rhythm disorders, subclinical atherosclerosis, coronary heart disease, heart failure, valvular disease, venous disease, and peripheral artery disease) and the associated outcomes (including quality of care, procedures, and economic costs). METHODS: The American Heart Association, through its Statistics Committee, continuously monitors and evaluates sources of data on heart disease and stroke in the United States to provide the most current information available in the annual Statistical Update. The 2020 Statistical Update is the product of a full year's worth of effort by dedicated volunteer clinicians and scientists, committed government professionals, and American Heart Association staff members. This year's edition includes data on the monitoring and benefits of cardiovascular health in the population, metrics to assess and monitor healthy diets, an enhanced focus on social determinants of health, a focus on the global burden of cardiovascular disease, and further evidence-based approaches to changing behaviors, implementation strategies, and implications of the American Heart Association's 2020 Impact Goals. RESULTS: Each of the 26 chapters in the Statistical Update focuses on a different topic related to heart disease and stroke statistics. CONCLUSIONS: The Statistical Update represents a critical resource for the lay public, policy makers, media professionals, clinicians, healthcare administrators, researchers, health advocates, and others seeking the best available data on these factors and conditions.

Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discovery.

BACKGROUND: The ECG remains the most widely used diagnostic test for characterization of cardiac structure and electrical activity. We hypothesized that parallel advances in computing power, machine learning algorithms, and availability of large-scale data could substantially expand the clinical inferences derived from the ECG while at the same time preserving interpretability for medical decision-making. METHODS AND RESULTS: We identified 36 186 ECGs from the University of California, San Francisco database that would enable training of models for estimation of cardiac structure or function or detection of disease. We segmented the ECG into standard component waveforms and intervals using a novel combination of convolutional neural networks and hidden Markov models and evaluated this segmentation by comparing resulting electrical intervals against 141 864 measurements produced during the clinical workflow. We then built a patient-level ECG profile, a 725-element feature vector and used this profile to train and interpret machine learning models for examples of cardiac structure (left ventricular mass, left atrial volume, and mitral annulus e-prime) and disease (pulmonary arterial hypertension, hypertrophic cardiomyopathy, cardiac amyloid, and mitral valve prolapse). ECG measurements derived from the convolutional neural network-hidden Markov model segmentation agreed with clinical estimates, with median absolute deviations as a fraction of observed value of 0.6% for heart rate and 4% for QT interval. Models trained using patient-level ECG profiles enabled surprising quantitative estimates of left ventricular mass and mitral annulus e' velocity (median absolute deviation of 16% and 19%, respectively) with good discrimination for left ventricular hypertrophy and diastolic dysfunction as binary traits. Model performance using our approach for disease detection demonstrated areas under the receiver operating characteristic curve of 0.94 for pulmonary arterial hypertension, 0.91 for hypertrophic cardiomyopathy, 0.86 for cardiac amyloid, and 0.77 for mitral valve prolapse. CONCLUSIONS: Modern machine learning methods can extend the 12-lead ECG to quantitative applications well beyond its current uses while preserving the transparency that is so fundamental to clinical care.

Does cannabis legalisation change healthcare utilisation? A population-based study using the healthcare cost and utilisation project in Colorado, USA.

OBJECTIVE: To assess the effect of cannabis legalisation on health effects and healthcare utilisation in Colorado (CO), the first state to legalise recreational cannabis, when compared with two control states, New York (NY) and Oklahoma (OK). DESIGN: We used the 2010 to 2014 Healthcare Cost and Utilisation Project (HCUP) inpatient databases to compare changes in rates of healthcare utilisation and diagnoses in CO versus NY and OK. SETTING: Population-based, inpatient. PARTICIPANTS: HCUP state-wide data comprising over 28 million individuals and over 16 million hospitalisations across three states. MAIN OUTCOME MEASURES: We used International Classification of Diseases-Ninth Edition codes to assess changes in healthcare utilisation specific to various medical diagnoses potentially treated by or exacerbated by cannabis. Diagnoses were classified based on weight of evidence from the National Academy of Science (NAS). Negative binomial models were used to compare rates of admissions between states. RESULTS: In CO compared with NY and OK, respectively, cannabis abuse hospitalisations increased (risk ratio (RR) 1.27, 95% CI 1.26 to 1.28 and RR 1.16, 95% CI 1.15 to 1.17; both p<0.0005) post-legalisation. In CO, there was a reduction in total admissions but only when compared with OK (RR 0.97, 95% CI 0.96 to 0.98, p<0.0005). Length of stay and costs did not change significantly in CO compared with NY or OK. Post-legalisation changes most consistent with NAS included an increase in motor vehicle accidents, alcohol abuse, overdose injury and a reduction in chronic pain admissions (all p<0.05 compared with each control state). CONCLUSIONS: Recreational cannabis legalisation is associated with neutral effects on healthcare utilisation. In line with previous evidence, cannabis liberalisation is linked to an increase in motor vehicle accidents, alcohol abuse, overdose injuries and a decrease in chronic pain admissions. Such population-level effects may help guide future decisions regarding cannabis use, prescription and policy.