-
La Radiologia Medica Jan 2024The purpose of this study was to explore a machine learning-based residual networks (ResNets) model to detect atrial septal defect (ASD) on chest radiographs.
OBJECT
The purpose of this study was to explore a machine learning-based residual networks (ResNets) model to detect atrial septal defect (ASD) on chest radiographs.
METHODS
This retrospective study included chest radiographs consecutively collected at our hospital from June 2017 to May 2022. Qualified chest radiographs were obtained from patients who had finished echocardiography. These chest radiographs were labeled as positive or negative for ASD based on the echocardiographic reports and were divided into training, validation, and test dataset. Six ResNets models were employed to examine and compare by using the training dataset and was tuned using the validation dataset. The area under the curve, recall, precision and F1-score were taken as the evaluation metrics for classification result in the test dataset. Visualizing regions of interest for the ResNets models using heat maps.
RESULTS
This study included a total of 2105 chest radiographs of children with ASD (mean age 4.14 ± 2.73 years, 54% male), patients were randomly assigned to training, validation, and test dataset with an 8:1:1 ratio. Healthy children's images were supplemented to three datasets in a 1:1 ratio with ASD patients. Following the training, ResNet-10t and ResNet-18D have a better estimation performance, with precision, recall, accuracy, F1-score, and the area under the curve being (0.92, 0.93), (0.91, 0.91), (0.90, 0.90), (0.91, 0.91) and (0.97, 0.96), respectively. Compared to ResNet-18D, ResNet-10t was more focused on the distribution of the heat map of the interest region for most chest radiographs from ASD patients.
CONCLUSION
The ResNets model is feasible for identifying ASD through children's chest radiographs. ResNet-10t stands out as the preferable estimation model, providing exceptional performance and clear interpretability.
Topics: Child; Child, Preschool; Female; Humans; Infant; Male; Echocardiography; Heart Septal Defects, Atrial; Machine Learning; Radiography; Retrospective Studies
PubMed: 38082195
DOI: 10.1007/s11547-023-01744-0 -
European Journal of Cardio-thoracic... Feb 2024Mitral valve surgery (MVS), with repair preferred to replacement, is a common procedure for the treatment of severe primary mitral regurgitation related to leaflet...
Mitral valve surgery (MVS), with repair preferred to replacement, is a common procedure for the treatment of severe primary mitral regurgitation related to leaflet prolapse. Structural complications after MVS include left ventricular outflow obstruction, paravalvular leak and atrial septal defect. Intraoperative transoesophageal echocardiography and predischarge transthoracic echocardiography (TTE) specifically screen for these complications. Ventricular septal defect (VSD), a known complication after aortic valve surgery, is rarely reported after MVS. Recently, unsuccessful valvuloplasty prior to replacement was suggested as a risk factor. We present such a case and explore mechanisms with advanced cardiac imaging. In this case, the patient was found to have an elongated membranous septum that likely predisposed her to septal injury. Finally, we provide guidance on specific transoesophageal/transthoracic echocardiography views to avoid a missed diagnosis.
Topics: Humans; Female; Mitral Valve; Ventricular Outflow Obstruction; Heart Septal Defects, Ventricular; Echocardiography; Echocardiography, Transesophageal
PubMed: 38290788
DOI: 10.1093/ejcts/ezae029 -
Trends in Cardiovascular Medicine Aug 2023
Topics: Humans; Foramen Ovale, Patent; Ischemic Stroke; Heart Septal Defects, Atrial; Stroke; Risk Factors; Aneurysm
PubMed: 35568264
DOI: 10.1016/j.tcm.2022.05.003 -
Diagnostics (Basel, Switzerland) Jan 2024Atrial septal defects (ASDs) present a significant healthcare challenge, demanding accurate and timely diagnosis and precise management to ensure optimal patient... (Review)
Review
Atrial septal defects (ASDs) present a significant healthcare challenge, demanding accurate and timely diagnosis and precise management to ensure optimal patient outcomes. Artificial intelligence (AI) applications in healthcare are rapidly evolving, offering promise for enhanced medical decision-making and patient care. In the context of cardiology, the integration of AI promises to provide more efficient and accurate diagnosis and personalized treatment strategies for ASD patients. In interventional cardiology, sometimes the lack of precise measurement of the cardiac rims evaluated by transthoracic echocardiography combined with the floppy aspect of the rims can mislead and result in complications. AI software can be created to generate responses for difficult tasks, like which device is the most suitable for different shapes and dimensions to prevent embolization or erosion. This paper reviews the current state of AI in healthcare and its applications in cardiology, emphasizing the specific opportunities and challenges in applying AI to ASD diagnosis and management. By exploring the capabilities and limitations of AI in ASD diagnosis and management. This paper highlights the evolution of medical practice towards a more AI-augmented future, demonstrating the capacity of AI to unlock new possibilities for healthcare professionals and patients alike.
PubMed: 38248009
DOI: 10.3390/diagnostics14020132 -
Journal of Cardiovascular Magnetic... Dec 2023Due to the heterogeneity of anatomic anomalies in Ebstein's anomaly (EA), particularly in the subset of patients with atrial septal defect (ASD), hemodynamic changes,...
Effect of concomitant atrial septal defect on left ventricular function in adult patients with unrepaired Ebstein's anomaly: a cardiovascular magnetic resonance imaging study.
BACKGROUND
Due to the heterogeneity of anatomic anomalies in Ebstein's anomaly (EA), particularly in the subset of patients with atrial septal defect (ASD), hemodynamic changes, which ultimately cause left ventricular (LV) deterioration remain unclear. The current study aimed to investigate the effect of concomitant ASD on LV function using cardiovascular magnetic resonance (CMR) imaging in patients with EA.
METHODS
This study included 31 EA patients with ASD, 76 EA patients without ASD, 35 patients with simple ASD and 40 healthy controls. Left/right ventricular (RV, the RV was defined as a summation of the functional RV and atrialized RV in EA patients) volumes and functional parameters, LV strain parameters, and echocardiogram indices were compared among the four groups. Associations between variables were evaluated via Spearman or Pearson correlation analyses. The association between risk factors and LV ejection fraction (EF) was determined via multivariate linear regression analysis.
RESULTS
Both EA patients and ASD patients had a higher RV/LV end-diastolic volume (RVEDV/LVEDV) as well as lower LV and RV ejection fractions (LVEF/RVEF) compared to healthy controls (all p < 0.05). Moreover, the EA patients with ASD had a significantly higher RVEDV/LVEDV and a lower LVEF and RVEF than those without ASD (all p < 0.05). Multivariate linear regression analysis revealed that the presence of ASD was independently associated with LVEF (β = - 0.337, p < 0.001). The RVEDV/LVEDV index was associated with LVEF (r = - 0.361, p < 0.001). Furthermore, the LV longitudinal peak diastolic strain rate (PDSR) was lower in EA patients with ASD than those without ASD, patients with simple ASD, and healthy controls (p < 0.05).
CONCLUSION
Concomitant ASD is an important risk factor of LV dysfunction in patients with EA, and diastolic dysfunction is likely the predominate mechanism related to LV dysfunction.
Topics: Adult; Humans; Ventricular Function, Left; Ebstein Anomaly; Predictive Value of Tests; Magnetic Resonance Imaging; Ventricular Dysfunction, Left; Stroke Volume; Heart Septal Defects, Atrial
PubMed: 38057914
DOI: 10.1186/s12968-023-00976-3 -
Journal of Cardiology Cases Nov 2023We report a case of a 54-year-old man with atrial septal defect who presented with oxygen desaturation on pulse oximetry. Cardiac magnetic resonance imaging and...
UNLABELLED
We report a case of a 54-year-old man with atrial septal defect who presented with oxygen desaturation on pulse oximetry. Cardiac magnetic resonance imaging and transesophageal echocardiography showed right-to-left shunting through an atrial septal defect, which was confirmed by superior vena cavography and suggested Eisenmenger syndrome. However, cardiac catheterization revealed a normal pulmonary arterial pressure. Simultaneous measurement of interatrial pressure identified two transient interatrial pressure gradient points, where the right atrial pressure was higher than the left atrial pressure. The patient was finally diagnosed with atrial septal defect without pulmonary hypertension. Right-to-left shunting was primarily caused by a transient interatrial pressure gradient due to a time delay in both initial atrial contraction and completion of passive ventricular filling between the right and left sides of the heart. Surgical closure of the atrial septal defect was performed, and hypoxemia improved. This is the first report of right-to-left shunting without pulmonary hypertension caused by a transient interatrial pressure gradient due to a time delay between the right and left cardiac cycles. Precise assessment of the simultaneous interatrial pressure in addition to diagnostic imaging played a pivotal role in clarifying the etiology of this rare condition.
LEARNING OBJECTIVE
Atrial septal defect with right-to-left shunting without Eisenmenger syndrome is a rare condition. We identified transient interatrial pressure gradients associated with a time delay in both initial atrial contraction and completion of the passive ventricular filling phase, which we considered as the primary mechanism underpinning right-to-left shunting. Simultaneous measurement of interatrial pressure played a pivotal role in elucidating the hemodynamics and abnormal shunt flow mechanism.
PubMed: 38024117
DOI: 10.1016/j.jccase.2023.07.006 -
Journal of Cardiothoracic Surgery Nov 2023This study used an atrial septal shunt to compare the treatment progress and prognosis for patients with heart failure (HF) who have different ejection fractions.
BACKGROUND
This study used an atrial septal shunt to compare the treatment progress and prognosis for patients with heart failure (HF) who have different ejection fractions.
METHODS
Twenty HF patients with pulmonary hypertension, who required atrial septal shunt therapy, were included in this study. The patients underwent surgery between December 2012 and December 2020. They were divided into two groups based on their ejection fraction: a group with reduced ejection fraction (HFrEF) and a group with preserved ejection fraction(HFpEF) + mid-range ejection fraction (HfmrEF). Echocardiography was utilized to evaluate parameters such as left ventricular dimension (LVD), left ventricular ejection fraction (LVEF), and left ventricular end-diastolic volume (LVEDV). Hemodynamic parameters were measured using cardiac catheterization. The patient's cardiac function was assessed using the six-minute walking test (6MWT), KCCQ score, NYHA classification, and the degree of functional mitral regurgitation (FMR). Followed-up visits were conducted at 1, 3, and 6 months, and any adverse effects were recorded.
RESULTS
The LVEF values were consistently higher in the HFpEF+HFmrEF group than HFrEF group at all periods (P < 0.05). Differences in LVD were observed between the two groups before the surgery. Statistically, significant differences were found at the preoperative stage, 1 month, and 3 months (P < 0.05, respectively). However, the LVEDV showed a significant difference between the two groups only at 3 months (P = 0.049). Notably, there were notable variations in LAPm, LAPs, and the pressure gradient between the LA-RA gradient at baeline, after implantation, and during the 6 months follow-up (all P < 0.05).
CONCLUSION
Following treatment, the HFpEF+HFmrEF group exhibited more significant improvements in echocardiographic and cardiac catheterization indices than the HFrEF group. However, there was no statistically significant difference between the two groups regarding the 6MWT and KCCQ scores. It is important to note that the findings of this study still require further investigation in a large sample size of patients.
Topics: Humans; Ventricular Function, Left; Stroke Volume; Heart Failure; Mitral Valve Insufficiency; Atrial Fibrillation; Prognosis; Heart Septal Defects, Atrial
PubMed: 37968674
DOI: 10.1186/s13019-023-02398-9 -
Journal of Imaging Informatics in... Jun 2024Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial...
Thoracic echocardiography (TTE) can provide sufficient cardiac structure information, evaluate hemodynamics and cardiac function, and is an effective method for atrial septal defect (ASD) examination. This paper aims to study a deep learning method based on cardiac ultrasound video to assist in ASD diagnosis. We chose four standard views in pediatric cardiac ultrasound to identify atrial septal defects; the four standard views were as follows: subcostal sagittal view of the atrium septum (subSAS), apical four-chamber view (A4C), the low parasternal four-chamber view (LPS4C), and parasternal short-axis view of large artery (PSAX). We enlist data from 300 children patients as part of a double-blind experiment for five-fold cross-validation to verify the performance of our model. In addition, data from 30 children patients (15 positives and 15 negatives) are collected for clinician testing and compared to our model test results (these 30 samples do not participate in model training). In our model, we present a block random selection, maximal agreement decision, and frame sampling strategy for training and testing respectively, resNet18 and r3D networks are used to extract the frame features and aggregate them to build a rich video-level representation. We validate our model using our private dataset by five cross-validation. For ASD detection, we achieve AUC, accuracy, sensitivity, specificity, and F1 score. The proposed model is a multiple instances learning-based deep learning model for video atrial septal defect detection which effectively improves ASD detection accuracy when compared to the performances of previous networks and clinical doctors.
Topics: Humans; Heart Septal Defects, Atrial; Child; Echocardiography; Female; Deep Learning; Male; Child, Preschool; Double-Blind Method; Infant; Image Interpretation, Computer-Assisted; Video Recording; Adolescent
PubMed: 38347394
DOI: 10.1007/s10278-024-00987-1 -
Cardiology in the Young Feb 2024Up to 90% of adults with untreated atrial septal defect will be symptomatic by 4 decade, and 30-49% will develop heart failure. 8-10% of these patients have pulmonary...
BACKGROUND
Up to 90% of adults with untreated atrial septal defect will be symptomatic by 4 decade, and 30-49% will develop heart failure. 8-10% of these patients have pulmonary arterial hypertension with a female predominance regardless of age. We aimed to demonstrate that fenestrated closure can be safely performed in patients with decompensated heart failure and atrial septal defect-associated pulmonary arterial hypertension with improved outcome.
METHODS
Transcatheter fenestrated atrial septal defect closures (Occlutech GmbH, Jena, Germany) were performed on a compassionate-use basis in 5 consecutive adult patients with atrial septal defect-associated pulmonary arterial hypertension and severe heart failure with prohibitive surgical mortality risks. Change in systemic oxygen saturation, 6-minute walk test, NYHA class, echocardiographic and haemodynamic parameters were used as parameters of outcome.
RESULTS
All patients were female, mean age 48.8 ± 13.5 years, followed up for a median of 29 months (max 64 months). Significant improvements observed in the 6-minute walk test, and oxygen saturation comparing day 0 time point to all other follow-up time points data ( = 1.32, SE = 0.28, (22.7) = -4.77, = 0.0001); and in the haemodynamic data (including pulmonary vascular resistance and pulmonary pressure) ( = -0.60, SE = 0.22, (40.2) = 2.74, = .009). All patients showed improved right ventricular size and function along with NYHA class. There were no procedure-related complications.
CONCLUSION
Fenestrated atrial septal defect closure is feasible in adults with decompensated heart failure and atrial septal defect-associated pulmonary arterial hypertension. It results in sustained haemodynamic and functional improvement.
Topics: Adult; Humans; Female; Middle Aged; Male; Hypertension, Pulmonary; Pulmonary Arterial Hypertension; Cardiac Catheterization; Treatment Outcome; Heart Septal Defects, Atrial; Heart Failure
PubMed: 37466020
DOI: 10.1017/S104795112300152X -
Current Problems in Cardiology Mar 2024The left atrial septal pouch (LASP) is a small anatomical septal recess in the heart that has been linked with cardioembolic events. A systematic appraisal of the... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
The left atrial septal pouch (LASP) is a small anatomical septal recess in the heart that has been linked with cardioembolic events. A systematic appraisal of the existing literature is necessary to establish a better understanding of the risk as studies continue to indicate a correlation between LASPs and cryptogenic strokes.
OBJECTIVES
To determine the level of association between the presence of LASP and the risk of developing cryptogenic stroke.
METHODS
We searched PubMed, EMBASE and Scopus for studies comparing the prevalence of LASP in patients with cryptogenic stroke against non-cryptogenic stroke control groups from inception till December, 2023. The Newcastle Ottawa scale was used for quality assessment and Comprehensive Meta-Analysis Version 3.3 was used for data analysis with odds ratio (OR) as the effect measure.
RESULTS
Our review included a total of 10 retrospective, observational studies published between 2010 to 2022. A total of 683 cases of cryptogenic strokes were identified, out of which 33.1 % (n = 271) were associated with a LASP. Among the non-cryptogenic stroke controls (n = 2641), LASP was present in 20.6 % cases (n = 476). The aggregate OR for cryptogenic stroke was 1.618 times greater than non-cryptogenic stroke (p < 0.001) among LASP cases, CONCLUSION: The presence of a septal pouch in the left atrium is significantly linked to a higher risk of developing cryptogenic strokes. As a potential site of thrombus formation and subsequent dislodgement, further large-scale studies are necessary to establish the guidelines for management and prophylaxis to prevent embolic events.
Topics: Humans; Stroke; Heart Septal Defects, Atrial; Retrospective Studies; Risk Factors; Heart Atria; Ischemic Stroke
PubMed: 38232917
DOI: 10.1016/j.cpcardiol.2024.102400