Echocardiographic Interpretation Research Articles

Нормативные интервалы и цифровое приложение для оценки параметров эхокардиографии детей Архангельской области

Objective interpretation of echocardiography results in the paediatric population is an urgent issue due to the difficulties in identifying the correct cardiovascular allometric relationship. A wide use of existing echocardiographic nomograms in paediatric cardiology is problematic due to the lack of clear data on the subjects’ regional affiliation, the volume of samples analysed, and the insufficient number of Russian studies in this sphere. The purpose of the study was to develop reference intervals for echocardiography parameters of children living in the Arkhangelsk Region and to automate the process of interpretation of the results by creating a digital application. Materials and methods. We analysed 3811 echocardiography protocols of children living in the Arkhangelsk Region aged from 1 to 15 years with no signs of organic pathology of the cardiovascular system or heart rhythm disorders. Results. Using echocardiography data, we developed reference intervals for morphometric parameters of the heart for children aged 1 to 15 years living in the Arkhangelsk Region. The research applied the Z-score approach based on the empirical determination of the degree of abnormalities by the standard deviation from normal values obtained during the examination of a large population of healthy individuals. Reference intervals of echocardiography parameters were determined using body surface area as the dependent variable. The values were automatically calculated in our digital application that allows one to increase the accuracy and efficiency of interpretation of cardiac ultrasound parameters. The results of studying the differences between the reference values in Russian and foreign studies and the obtained regional norms indicate that the hearts of children living in the Arkhangelsk Region are statistically significantly smaller in size. The practical use of the digital application created by us in functional diagnostics will allow doctors to objectivize the measurements of morphometric parameters of the heart and reduce overdiagnosis.

Abstract 4144553: Fully Automated Machine Learning Based Echocardiographic Assessment of Global Longitudinal Strain in Breast Cancer Patients Receiving Cardiotoxic Chemotherapy

Background: Global longitudinal strain (GLS) is considered the most sensitive echocardiographic marker for detecting cardiotoxicity and subclinical changes in cardiac function in patients receiving cardiotoxic therapies. Despite literature that has shown less inter-observer variability for GLS compared to left ventricular ejection fraction, there remains significant variability in GLS measurement across observers and vendors. US2.AI is a novel, machine learning-based artificial intelligence (AI) algorithm for automated echocardiographic interpretation. We aim to demonstrate the feasibility of AI-based GLS assessment and hypothesize that AI-based GLS measurement is more reproducible compared to human-based measurement Methods: A total of 27 transthoracic echocardiograms were selected at random from a population of female cardio-oncology breast cancer patients and were run through the US2.AI algorithm twice to calculate GLS. The same echocardiograms were then analyzed by two board-certified cardiologists in a blinded fashion to calculate GLS using QLAB software (Philips). The two methods of GLS measurement (AI versus humans) were compared using linear regression, as assessed by the Pearson correlation coefficient. Reproducibility for each method was assessed using the intra-class correlation coefficient (ICC). Results: A total of 27 studies were analyzed with a mean age of 55.6 ± 11.3 and all patients were female. The feasibility of US2.AI for the assessment of GLS was demonstrated with a strong correlation between AI-based and human reads (r = 0.80, p < 0.00001). The reproducibility of AI-based GLS assessment was superior to that of human readers as assessed by an ICC of 1.0 versus 0.52, respectively. Conclusion: AI-based assessment of GLS was shown to be both feasible and more reproducible compared to expert human readers in a population of breast cancer patients receiving cardiotoxic chemotherapy. Given the important clinical implications of GLS in cardio-oncology patients, more widespread implementation of AI-based strain assessment has the potential to significantly improve the reproducibility of GLS measurement in this unique patient population.

Assessment of echocardiographic interpretation of dual-lumen cannula during venovenous extracorporeal membrane oxygenation use for pediatric respiratory failure.

Echocardiography is considered essential during cannulation placement and manipulations. Literature evaluating transthoracic echocardiography (TTE) usage during pediatric VV-ECMO is scant. The purpose of this study is to describe the use of echocardiography during VV-ECMO at a large, quaternary children's hospital. A retrospective, single-year cohort study was performed of pediatric patients on VV-ECMO via dual-lumen cannula at our institution from January 2019 through December 2019. For each echocardiogram, final cannula component (re-infusion port (ReP), distal tip, proximal port and distal port) positions were evaluated by one echocardiographer. For TTEs with ReP in the right atrium, two echocardiographers independently evaluated ReP direction using 2-point (Yes/No) and 4-point scales, which were semi-quantitative protocols using color Doppler images to estimate ReP jet direction to the tricuspid valve. Cohen's kappa or weighted kappa was used to measure interrater agreement. During study period, 11 patients (64% male) received VV-ECMO with 49 TTEs and one transesophageal echocardiogram performed. The median patient age was 4.3 years [IQR: 1.1-11.5] and median VV-ECMO run time of 192h [90-349]. The median time between TTEs on VV-ECMO was 34h [8.3-65]. Most common position for the ReP was the right atrium (n=33, 67%), and ReP location was not identified in five TTEs (10%). For ReP flow direction, echocardiographers agreed on 82% of TTEs using 2-point evaluation. There was only moderate agreement between echocardiographers on the 2-point and 4-point assessments (k=.54, kw=.46 respectively). TTE is the predominant cardiac ultrasound modality used during VV-ECMO for pediatric respiratory failure. Subjective evaluation of VV-ECMO ReP jet direction in the right atrium is challenging, regardless of assessment method.

Simulation-based echocardiography learning contribution on training of medical residents.

Echocardiography is a pivotal exam in critically ill patients, a specific training is crucial. Medical residents often lack echocardiography practice. This study aims to evaluate the impact of simulation-based training on medical residents' echocardiography mastery. This interventional study was conducted among medical residents at the Simulation Center of the Faculty of Medicine in Monastir (CeSim) in January 2022. The intervention consisted of a theoretical training and a simulator-based practical training concerning echocardiography. Residents underwent evaluation before and after training through a "Pre-Test" and a "Post-Test," respectively, using a French-language questionnaire. Participation was entirely voluntary. A total of 28 medical residents participated in our study, with the majority being female (57.1%). The median age was 29 years (interquartile range: 28-31.75). Following training, the proportion of participants who reported having the necessary skills for echocardiography interpretation significantly increased (p<0.05). Respondents demonstrated significant improvements in their scores on theoretical tests and practical skills assessments. Concerning echocardiographic views, the percentage of participants who correctly identified the title of the parasternal small axis section increased from 53.6% before training to 100% after training (p <10-3). Significant enhancements were observed in all parameters evaluating the practice of echocardiographic sections by respondents on a mannequin after training, encompassing time to obtain the view, view quality, image quality, visualization of structures, interpretability, and image stability (p<10-3). There was a significant improvement in average response rates for echocardiographic clinical syndroms among medical residents before and after training. All participants emphasized the indispensability of ultrasound education in the training of physicians specializing in managing cardiopulmonary emergencies. This study reports the beneficial role of simulation-based training in enhancing the mastery of medical residents in echocardiography. Incorporating such training methods into their learning curricula is advisable.

CASE STUDY OF NORMAL ECHOCARDIOGRAPHYIN AN ADULT SIBERIAN HUSKY DOG

Echocardiography is commonly used in veterinary medicine to assess cardiac structure and function in dogs. This case study was aimed to evaluate normal echocardiography of an adult Siberian Husky. Standard techniques, including B-Mode, M-Mode, and Color Flow Doppler, were carried out by using the Acclarix AX3 Vet USG and a micro convex probe 5-9 MHz. Examinations were conducted in the right parasternal and left apical positions. The results indicate that the six-year-old, 32 kg Siberian Husky in this study exhibited a normal heart. When comparing M-Mode echocardiography with the normal range for dogs of similar size, role, and weight, left ventricular internal dimension in diastole (LVIDd) was below the normal range, while left ventricular posterior wall in diastole (LVWPd) and left ventricular posterior wall in systole (LVPWs) were higher. These findings highlight the necessity for breed-specific reference intervals. This case study emphasizes the correlation between the normal echocardiography interpretation and canine cardiac function, as depicted by the value of ejection fraction (EF) 66.04% and fractional shortening (FS) 35.52%. The echocardiography results of the Siberian Husky in the study are comparable to reference interval values of similar breeds that are working dogs, making them valuable as reference values for future studies.

Artificial intelligence-assisted automated heart failure detection and classification from electronic health records.

Electronic health records (EHR) linked to Digital Imaging and Communications in Medicine (DICOM), biological specimens, and deep learning (DL) algorithms could potentially improve patient care through automated case detection and surveillance. We hypothesized that by applying keyword searches to routinely stored EHR, in conjunction with AI-powered automated reading of DICOM echocardiography images and analysing biomarkers from routinely stored plasma samples, we were able to identify heart failure (HF) patients. We used EHR data between 1993 and 2021 from Tayside and Fife (~20% of the Scottish population). We implemented a keyword search strategy complemented by filtering based on International Classification of Diseases (ICD) codes and prescription data to EHR data set. We then applied DL for the automated interpretation of echocardiographic DICOM images. These methods were then integrated with the analysis of routinely stored plasma samples to identify and categorize patients into HF with reduced ejection fraction (HFrEF), HF with preserved ejection fraction (HFpEF), and controls without HF. The final diagnosis was verified through a manual review of medical records, measured natriuretic peptides in stored blood samples, and by comparing clinical outcomes among groups. In our study, we selected the patient cohort through an algorithmic workflow. This process started with 60850 EHR data and resulted in a final cohort of 578 patients, divided into 186 controls, 236 with HFpEF, and 156 with HFrEF, after excluding individuals with mismatched data or significant valvular heart disease. The analysis of baseline characteristics revealed that compared with controls, patients with HFrEF and HFpEF were generally older, had higher BMI, and showed a greater prevalence of co-morbidities such as diabetes, COPD, and CKD. Echocardiographic analysis, enhanced by DL, provided high coverage, and detailed insights into cardiac function, showing significant differences in parameters such as left ventricular diameter, ejection fraction, and myocardial strain among the groups. Clinical outcomes highlighted a higher risk of hospitalization and mortality for HF patients compared with controls, with particularly elevated risk ratios for both HFrEF and HFpEF groups. The concordance between the algorithmic selection of patients and manual validation demonstrated high accuracy, supporting the effectiveness of our approach in identifying and classifying HF subtypes, which could significantly impact future HF diagnosis and management strategies. Our study highlights the feasibility of combining keyword searches in EHR, DL automated echocardiographic interpretation, and biobank resources to identify HF subtypes.

Reducing echocardiographic examination time through routine use of fully automated software: a comparative study of measurement and report creation time

BackgroundManual interpretation of echocardiographic data is time-consuming and operator-dependent. With the advent of artificial intelligence (AI), there is a growing interest in its potential to streamline echocardiographic interpretation and reduce variability. This study aimed to compare the time taken for measurements by AI to that by human experts after converting the acquired dynamic images into DICOM data.MethodsTwenty-three consecutive patients were examined by a single operator, with varying image quality and different medical conditions. Echocardiographic parameters were independently evaluated by human expert using the manual method and the fully automated US2.ai software. The automated processes facilitated by the US2.ai software encompass real-time processing of 2D and Doppler data, measurement of clinically important variables (such as LV function and geometry), automated parameter assessment, and report generation with findings and comments aligned with guidelines. We assessed the duration required for echocardiographic measurements and report creation.ResultsThe AI significantly reduced the measurement time compared to the manual method (159 ± 66 vs. 325 ± 94 s, p < 0.01). In the report creation step, AI was also significantly faster compared to the manual method (71 ± 39 vs. 429 ± 128 s, p < 0.01). The incorporation of AI into echocardiographic analysis led to a 70% reduction in measurement and report creation time compared to manual methods. In cases with fair or poor image quality, AI required more corrections and extended measurement time than in cases of good image quality. Report creation time was longer in cases with increased report complexity due to human confirmation of AI-generated findings.ConclusionsThis fully automated software has the potential to serve as an efficient tool for echocardiographic analysis, offering results that enhance clinical workflow by providing rapid, zero-click reports, thereby adding significant value.

Aortic regurgitation in athletes: the challenges of echocardiographic interpretation

BackgroundBicuspid aortic valve (BAV) is the most common congenital cardiac defect and prone to premature degeneration causing aortic regurgitation (AR). The assessment of AR in athletic individuals poses several challenges as the pathological left ventricle (LV) remodelling caused by AR may overlap with the physiological remodelling of intense exercise. The purpose of this study is to highlight these challenges, review the existing literature and discuss how to tackle these conundrums. As a real-world example, we compare the resting transthoracic echocardiographic (TTE) findings in a cohort of individuals with BAV and AR, sub-grouped into “highly active” or “lightly active”.MethodsAdult male subjects with an index TTE performed at a tertiary referral centre between 2019 and 2022 were included if the TTE confirmed a BAV and at least moderate AR. Further strict inclusion criteria were applied and parameters of valve disease severity was made in accordance with existing guidelines. Subjects completed a physical activity questionnaire over the telephone, and were classified into either group 1: “highly active” or group 2: “lightly active” based on their answers. Demographics and TTE parameters were compared between the two groups.Results30 male subjects (mean age 44 ± 13 years) with BAV-AR were included – 17 were highly active, and 13 lightly active. There was no significant difference in age (group 1, 45 ± 12.7 years vs. group 2, 42 ± 17 years; p = 0.49), height (p = 0.45), weight (p = 0.268) or severity of AR, when quantitative assessment was possible. Group 1 had a significantly higher stroke volume (131 ± 17mls vs. 102 ± 13 mls; p = 0.027), larger LV volumes, diastolic dimensions and significantly larger bi-atrial and right ventricular size. This LV dilatation in the context of AR and athleticism poses a diagnostic and management conundrum. Despite this, none of these 17 highly active individuals demonstrated any of the traditional criteria used to consider surgery.ConclusionThere is significant overlap between the physiological adaptations to exercise and those caused by AR. Multi-modality imaging and stress testing can aid clinicians in diagnostic and management decisions in exercising individuals when there is discordance between AR severity and symptoms.

Identification of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound using artificial intelligence

Abstract Introduction Prenatal ultrasound screening for congenital heart disease (CHD) suffers from poor detection yield (10%-56%)[1, 2], with a strong impact on neonatal morbidity and mortality. The need for expertise in fetal cardiology and the high volume of screening cases limit the current detection rates. Computer-assisted prenatal screening could support clinicians in improving diagnostic yield, including for abnormal ventricular asymmetry, which is often hard to discriminate from physiological asymmetry. Here we aim at evaluating a deep neural network (DNN) for detection of abnormal ventricular asymmetry, which can be linked to multiple types of CHD, including coarctation of the aorta, pulmonary or aortic valve stenosis, ventricular hypoplasia or univentricular heart. Purpose To determine if a novel DNN can identify cases of abnormal ventricular asymmetry in 2nd trimester fetal ultrasound videos. Methods We used as an endpoint the presence of any abnormality causing a significantly abnormal asymmetry of the ventricles as seen in the fetal ultrasound. Consecutive patients who had an echocardiography performed at one center were included retrospectively starting from 2022, January 1st. Inclusion criteria were single pregnancy between 18 and 25 weeks of gestation. To have a high number of positive patients, patients were included separately if they were expected to be positive (n=35) or negative (n=75) to the endpoint, based on their medical record. Each case was reviewed by one of two physicians expert in fetal echocardiography interpretation to confirm the presence or absence of the endpoint. For each patient, a single video showing an interpretable four chamber view was selected. Patients with no such video were excluded. The DNN takes as input fetal ultrasound videos, and predicts the absence or presence of the endpoint for each video. If its confidence is low, the DNN predicts an "inconclusive" output instead. The DNN has a ResNet-50 architecture[3] adapted to videos and was trained on data from patients not included in the evaluation. The detection performance of the DNN and the proportion of conclusive outputs were assessed. Results Overall, 37 positive and 66 negative ultrasound videos were included. The DNN achieved an AUC of 75.5%, a sensitivity of 71.4% (54.9-83.7, 95%CI) and a specificity of 64.4% (51.7-75.4, 95%CI) in identifying cases of abnormal ventricular asymmetry, after excluding inconclusive diagnosis. The DNN predicted a conclusive diagnosis in 91.3% of cases. Conclusion A DNN could accurately identify cases of abnormal ventricular asymmetry in fetal heart ultrasound videos. Importantly, this evaluation was performed in a population of patients who had an echocardiogram, and which therefore contains more abnormal cases compared to patients undergoing standard screening. This work lays the ground for diagnostic support to enable a more efficient, accurate, and scalable analysis of fetal heart ultrasounds.

Accuracy of visual estimation of ejection fraction in patients with heart failure using augmented reality glasses

ObjectiveLeft ventricular ejection fraction (LVEF) is measured to assess haemodynamic status and cardiac function. It may be difficult to accurately measure in patients with heart failure (HF) as they are...

Deep Learning–Enabled Assessment of Left Heart Structure and Function Predicts Cardiovascular Outcomes

BackgroundDeep learning interpretation of echocardiographic images may facilitate automated assessment of cardiac structure and function. ObjectivesWe developed a deep learning model to interpret echocardiograms and examined the association of deep learning–derived echocardiographic measures with incident outcomes. MethodsWe trained and validated a 3-dimensional convolutional neural network model for echocardiographic view classification and quantification of left atrial dimension, left ventricular wall thickness, chamber diameter, and ejection fraction. The training sample comprised 64,028 echocardiograms (n = 27,135) from a retrospective multi-institutional ambulatory cardiology electronic health record sample. Validation was performed in a separate longitudinal primary care sample and an external health care system data set. Cox models evaluated the association of model-derived left heart measures with incident outcomes. ResultsDeep learning discriminated echocardiographic views (area under the receiver operating curve >0.97 for parasternal long axis, apical 4-chamber, and apical 2-chamber views vs human expert annotation) and quantified standard left heart measures (R2 range = 0.53 to 0.91 vs study report values). Model performance was similar in 2 external validation samples. Model-derived left heart measures predicted incident heart failure, atrial fibrillation, myocardial infarction, and death. A 1-SD lower model-left ventricular ejection fraction was associated with 43% greater risk of heart failure (HR: 1.43; 95% CI: 1.23-1.66) and 17% greater risk of death (HR: 1.17; 95% CI: 1.06-1.30). Similar results were observed for other model-derived left heart measures. ConclusionsDeep learning echocardiographic interpretation accurately quantified standard measures of left heart structure and function, which in turn were associated with future clinical outcomes. Deep learning may enable automated echocardiogram interpretation and disease prediction at scale.

2023 CCS/CSE Standards for Physician Training and Maintenance of Competence in Adult Echocardiography: Executive Summary.

Echocardiography is an imaging modality essential to the provision of contemporary cardiovascular care. Since the publication of the 2010 CCS/CSE Guidelines, 1 Burwash IG, Basmadjian A, Bewick D, Choy JB, Cujec B, Jassal DS, MacKenzie S, Nair P, Rudski L, Yu E, Tam JW. 2010 Canadian Cardiovascular Society/Canadian Society of Echocardiography Guidelines for Training and Maintenance of Competency in Adult Echocardiography. Can J Cardiol 2010;27:862-864. Google Scholar clinical echocardiography has expanded with respect to both technologies and applications. At the same time there has been a shift in emphasis away from quantity of training (duration and case volumes) to actual demonstration of competency to determine successful completion of training. 2 Royal College of Physicians and Surgeons of Canada “Competency by Design: Reshaping Medical Education” 2014 https://www.royalcollege.ca/rcsite/documents/educational-strategy-accreditation/royal-college-competency-by- design-ebook-e.pdf Accessed 8 March 2023. Google Scholar Concurrently, there is growing evidence of considerable variability in echocardiography competence among general cardiology trainees. 3 Nair P. Siu S.C. Sloggett C.E. Biclar L. Sidhu R.S. Yu E.H.C. The assessment of technical and interpretative proficiency in echocardiography. J Am Soc Echocardiogr. 2006; 19: 924-931 Abstract Full Text Full Text PDF PubMed Scopus (37) Google Scholar , 4 Bierowski M.J. Qureshi U. Ramedani S. Grewal S. Shah R. Park B. Peterson B.R. Variable exposure to echocardiography core competencies when applying minimum recommended procedural numbers of cardiology fellows in training. Cardiovasc Ultrasound. 2022; 20: 24-32 Crossref Scopus (0) Google Scholar , 5 Yu C.C.W. Pendrith C. Chun S. Echocardiographic interpretation skills of graduating cardiology trainees. Can J Cardiol. 2022; 38: 1304-1306 Abstract Full Text Full Text PDF PubMed Scopus (1) Google Scholar

Automatic echocardiographic anomalies interpretation using a stacked residual-dense network model

Echocardiographic interpretation during the prenatal or postnatal period is important for diagnosing cardiac septal abnormalities. However, manual interpretation can be time consuming and subject to human error. Automatic segmentation of echocardiogram can support cardiologists in making an initial interpretation. However, such a process does not always provide straightforward information to make a complete interpretation. The segmentation process only identifies the region of cardiac septal abnormality, whereas complete interpretation should determine based on the position of defect. In this study, we proposed a stacked residual-dense network model to segment the entire region of cardiac and classifying their defect positions to generate automatic echocardiographic interpretation. We proposed the generalization model with incorporated two modalities: prenatal and postnatal echocardiography. To further evaluate the effectiveness of our model, its performance was verified by five cardiologists. We develop a pipeline process using 1345 echocardiograms for training data and 181 echocardiograms for unseen data from prospective patients acquired during standard clinical practice at Muhammad Hoesin General Hospital in Indonesia. As a result, the proposed model produced of 58.17% intersection over union (IoU), 75.75% dice similarity coefficient (DSC), and 76.36% mean average precision (mAP) for the validation data. Using unseen data, we achieved 42.39% IoU, 55.72% DSC, and 51.04% mAP. Further, the classification of defect positions using unseen data had approximately 92.27% accuracy, 94.33% specificity, and 92.05% sensitivity. Finally, our proposed model is validated with human expert with varying Kappa value. On average, these results hold promise of increasing suitability in clinical practice as a supporting diagnostic tool for establishing the diagnosis.

Trainee selection of tasks in postgraduate medical education: Is there a role for 'cherry-picking' to optimise learning?

Learning is optimised when postgraduate trainees engage in clinical tasks in their zone of proximal development (ZPD). However, workplace learning environments impose additional non-learning goals and additional tasks that may lead to trainees engaging in tasks that do not fall within their ZPD. We do not fully understand how trainees select clinical tasks in the workplace learning environment. If we knew the goals and factors they consider when selecting a task, we could better equip trainees with strategies to select tasks that maximise learning. We explored how postgraduate trainees select clinical tasks using echocardiography interpretation as a model. Canadian General Cardiology residents and Echocardiography fellows were invited to participate in semi-structured interviews. Aligning with a theory-informed study, two independent researchers used a deductive, directed content analysis approach to identify codes and themes. Eleven trainees from seven Canadian universities participated (PGY4 =4, PGY5 =3, PGY6 =1 and echocardiography fellows =3). Goals included learning content, fulfilling assessment criteria and contributing to clinical demands. Trainees switched between goals throughout the day, as it was too effortful for them to engage in tasks within their ZPD at all times. When trainees had sufficient mental effort available, they selected higher complexity tasks that could advance learning content. When available mental effort was low, trainees selected less complex tasks that fulfilled numerically based assessment goals or contributed to clinical demands. Trainees predominantly used perceived complexity of the echocardiogram as a factor to select tasks to achieve their desired goals. Postgraduate trainees select tasks within their ZPD that enable them to maximise learning when they perceive to have sufficient mental effort available and workplace affordances are adequate. These findings can inform individual and systemic strategies to maximise learning when selecting tasks.

RESEARCH ON MACHINE LEARNING METHODS FOR RECOGNITION AND CLASSIFICATION OF CARDIOVASCULAR PATHOLOGIES

This research describes machine learning methods and algorithms for early diagnosis of cardiovascular diseases. In a comparative analysis of the noninvasive diagnostic methods used, echocardiography and electrocardiography are the most common. This article explores new methods of automatic augmentation and correction of echocardiogram and electrocardiogram results using machine learning methods and algorithms. The article develops a system that minimizes both medical and hardware errors in the interpretation of echocardiography and electrocardiography using neural networks and machine learning methods. The scientific novelty of the study is that machine learning methods can reduce image analysis time, accelerate clinical decision making, and provide feedback to less experienced clinicians. The experiment, by training models of pathology recognition and classification, gave a clear idea of how to create the same model for other, more serious diseases, such as cancer and its various types. The purpose of this article is to analyze new methods for automatically adding and correcting echocardiogram and electrocardiogram results. The practical relevance of this study is to use computational resources to improve subsequent interpretation using machine learning algorithms.

Screening for the prevalence of rheumatic heart disease among school children in Egypt.

In low-income nations, Rheumatic valvular heart disease remains a major cause of morbidity and premature deaths. Accurate prevalence data in Egypt are still lacking yet highly desirable to facilitate health care planning. An cluster sample of school children in eastern Egyptian Governorates was examined clinically and echocardiographically (using abbreviated protocol) for detection of rheumatic valvular heart disease based on 2012 World Heart Federation criteria (the Doppler and the morphological criteria) for diagnosis. According to echocardiography interpretation, participants were categorized as having definite rheumatic heart disease (RHD), borderline RHD or no RHD. A total of 1680 students aged between 6 and 18 years were screened, 119 echocardiographic studies were non-interpretable; so, a total of 1560 studies were evaluated. From the total screened students, 1560 studies were adequate and interpretable according to the criteria specified in the methods section. This revealed a prevalence of 2.3% of the sample with RHD without adding the equivocal cases. The most prevalent lesion as detected by echocardiography was mitral regurgitation (29% of definite RHD cases). Rheumatic valvular heart disease remains prevalent in Egypt and the findings of this study should influence early detection, primary and secondary prevention, and adequate future national health plans.

Evaluating Independent Echocardiography Interpretation Skills: A Novel Assessment Tool.

Echocardiography is an essential imaging modality for clinical care. Currently, by virtue of graduating from cardiology residency and performing/interpreting an arbitrary number of echocardiograms, cardiology trainees are deemed competent to independently practice echocardiography. There is no formal assessment to ensure their competence. Recognizing this unmet need, we developed a novel echocardiography assessment tool and piloted it in a sample of 38 participants (including 7 expert echocardiographers). The tool was found to be valid and reliable in assessing independent echocardiography interpretation skills; thus can be used during training to ensure cardiology residents achieve competence in echocardiography before completing their training.

Echocardiographic values in healthy Pugs: Effect of body weight, age, and sex.

Transthoracic echocardiography represents the main noninvasive technique for evaluating cardiac morphology and function in dogs. In dogs with particular somatotypes, such as brachymorphic dogs, breed-specific echocardiographic values are needed for a proper echocardiographic interpretation. Nowadays, the Pug represents one of the most popular brachymorphic canine breeds worldwide. However, data on echocardiographic measurements in this breed are currently limited. We aimed to determine echocardiographic values in a population of apparently healthy Pugs, and to assess the possible effects of body weight (BW), age, and sex on selected echocardiographic variables, with particular emphasis on those related to the left-sided cardiac chambers. Apparently healthy Pugs underwent a full physical examination, a 1-minute six-lead electrocardiogram, and a complete transthoracic echocardiography. Twenty-four echocardiographic variables were measured by combining M-mode, two-dimensional and Doppler modalities, and relative values were determined by applying the statistical procedures recommended by the Clinical and Laboratory Standards Institute. Moreover, the effect of selected demographic variables on echocardiographic measurements was tested using a linear mixed model. The investigation included 86 Pugs. Echocardiographic values were provided for each variable and compared with previous veterinary literature. A statistically significant effect of BW, age, and sex was documented for several of the tested variables. Doppler examination demonstrated a trivial pulmonary regurgitation in 24/86 (27.9%) Pugs. Moreover, a persistent left cranial vena cava was suspected in 4/86 (4.7%) dogs. Echocardiographic features of the Pug were addressed and echocardiographic values were made available for clinical use. Because our findings were obtained using a standardized echocardiographic analysis in a population of 86 healthy Pugs, they may act as a reliable guide for an accurate echocardiographic interpretation in this breed.

DEEP LEARNING MODELS FOR AUTOMATING ASSESSMENT OF LEFT VENTRICULAR WALL THICKNESS AND DIMENSIONS

Left ventricular (LV) geometric patterns aid clinicians in the diagnosis and prognostication of various cardiomyopathies. Two-dimensional transthoracic echocardiogram is the clinical standard for the assessment of LV dimensions. Assessment of LV dimensions and wall thickness is known to be associated with significant interobserver and intraobserver variability. Automation of echocardiographic interpretation using machine learning may allow non-experts to assess LV dimensions while improving reliability.

Preoperative hemodynamics as predictors of right heart failure post-left ventricular assist device

BackgroundMechanical circulatory support has garnered significant popularity as both a bridge to transplant as well as a destination therapy for patients with end-stage heart failure. Right heart failure (RHF) is a devastating complication after LVAD placement and is very unpredictable. Assisted circulation of the left ventricle (LV) with an LVAD device could unmask an underlying RHF. However, otherwise healthy right ventricles (RVs) can develop RHF after LVAD placement as well due to poor adaptation to new filling pressures and altered hemodynamics. It has been proposed that preoperative volumetric measurements in the pulmonary and systemic vasculature may serve as indicators for a risk of RHF after LVAD implantation. The aim of this study is to examine a potential relationship of preoperative hemodynamic values such as pulmonary artery pulsatility index (PAPi) and the ratio of central venous pressure to pulmonary wedge pressure (CVP/PWP) as preoperative predictors for RHF post LVAD placement.MethodsWe retrospectively reviewed patients undergoing initially planned isolated LVAD implantation with or without concomitant procedures in our institution from January 1, 2017 to June 12, 2020. Data were gathered from hemodynamic records, echocardiographic interpretations, and clinical notes. Patients who had RHF after LVAD implantation but without hemodynamic data available within 14 days from the operation were excluded. Univariable analysis was performed.ResultsOf the 114 patients who received planned isolated LVAD surgery, 70 (61.4%) experienced RHF within the first 7 days postoperatively. PAPi did not correlate significantly with RHF vs non-RHF among LVAD recipients (3.1 ± 2.1 vs. 3.8 ± 3.4 P = 0.21). Pre-op CVP/PWP did not differ significantly between RHF and non-RHF patients (0.4 ± 0.2 vs. 0.5 ± 0.8 P = 0.28). There was a nonsignificant correlation between elevated pre-op PWP and those with RHF vs those without, OR = 1.05 (95% CI: 1.00, 1.10). Pre-op systolic pulmonary artery pressure (SysPAP) was elevated in patients with post-LVAD RHF compared to those without (51.3 ± 12.3 vs. 47.2 ± 13.0, P = 0.09).ConclusionPreoperative hemodynamic variables such as PAPi or CVP/PWP did not show a significant correlation predicting RHF post LVAD implantation. Acute RHF post LVAD implantation remains a complex medical entity. Several studies have devised multivariable risk scores; however, their performance has been limited. Despite the widespread use of preoperative hemodynamics measurements as risk scores, our study suggests these scores are not as accurate as their use would suggest, particularly among especially morbid patient populations. More prospective studies are needed to accurately demonstrate how preoperative hemodynamics could predict and help prevent this catastrophic complication.