[Transcatheter closure of patent ductus arteriosus using the Amplatzer duct occluder: initial results and mid-term follow-up]

Prediction of significant congenital heart disease in infants and children using continuous wavelet transform and deep convolutional neural network with 12-lead electrocardiogram

BACKGROUND

Congenital heart disease (CHD) affects approximately 1% of newborns and is a leading cause of mortality in early childhood. Despite the importance of early detection, current screening methods, such as pulse oximetry and auscultation, have notable limitations, particularly in identifying non-cyanotic CHD. (AI)-assisted electrocardiography (ECG) analysis offers a cost-effective alternative to conventional CHD detection. However, most existing models have been trained on older children, limiting their generalizability to infants and young children. This study developed an AI model trained on real-world ECG data for the detection of hemodynamically significant CHD in children under five years of age.

METHODS

ECG data was retrospectively collected from 1,035 patients under five years old at Chang Gung Memorial Hospital, Taoyuan, Taiwan (2013-2020). Based on ECG findings, patients were categorized into the following groups: normal heart structure (NOR), non-significant right heart disease (RHA), significant right heart disease (RHB), non-significant left heart disease (LHA), and significant left heart disease (LHB). ECG signals underwent preprocessing using continuous wavelet transformation and segmentation into 2-s intervals for data augmentation. Transfer learning was applied using three pre-trained deep learning models: ResNet- 18, InceptionResNet-V2, and NasNetMobile. Model performance was evaluated in terms of accuracy, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC).

RESULTS

Among the tested models, the model based on ResNet-18 demonstrated the best overall performance in predicting clinically significant CHD, achieving accuracy of 73.9%, an F1 score of 75.8%, and an AUC of 81.0% in differentiating significant from non-significant CHD. InceptionResNet-V2 performed well in detecting left heart disease but was computationally intensive. The proposed AI model significantly outperformed conventional ECG interpretation by pediatric cardiologists (accuracy 67.1%, sensitivity 71.6%).

CONCLUSIONS

This study highlights the potential of AI-assisted ECG analysis for CHD screening in young children. The ResNet-18-based model outperformed conventional ECG evaluation, suggesting its feasibility as a supplementary tool for early CHD detection. Future studies should focus on multi-center validation, inclusion of more CHD subtypes, and integration with other screening modalities to improve diagnostic accuracy and clinical applicability.

Percutaneous Closure of Patent Ductus Arteriosus in Infants 1.5 kg or Less: A Meta-Analysis

OBJECTIVE

To investigate technical success and safety of percutaneous patent ductus arteriosus closure in infants ≤1.5 kg.

STUDY DESIGN

A systematic review and meta-analysis was performed. Data sources included Scopus, Web of Science, Embase, CINAHL, Cochrane, and PubMed from inception to April 2020. Publications were included if they had a clear definition of the intervention as percutaneous patent ductus arteriosus closure in infants ≤1.5 kg. Data extraction was independently performed by multiple observers. Primary outcome was technical success and secondary outcomes were adverse events (AEs). Subgroup analysis was performed in infants ≤6.0 kg. Data were pooled by using a random-effects model.

RESULTS

We included 28 studies, including 373 infants ≤1.5 kg and 69 studies enrolling 1794 infants ≤6.0 kg. In patients ≤1.5 kg, technical success was 96% (95% CI, 93%-98%; P = .16; I² = 23%). The overall incidence of AE was 27% (95% CI, 17%-38%; P < .001; I² = 70%) and major AEs was 8% (95% CI, 5%-10%; P = .63; I² = 0%). There were 5 deaths related to the procedure (2%; 95% CI, 1%-4%; P = .99; I² = 0%); 4 of these deaths occurred in infants <0.8 kg. The probability of technical failure was inversely related to age at the time of the procedure (OR, 0.9; 95% CI, 0.830-0.974; P = .009). Weight at intervention has decreased over time and procedural success has increased.

CONCLUSIONS

Percutaneous patent ductus arteriosus closure is feasible in infants ≤1.5 kg with few major AEs. The procedural success rate is high, despite performing the intervention in smaller patients.

PROSPERO REGISTRATION

CRD42020145230.

Echocardiographic Versus Angiographic Assessment of Patent Arterial Duct in Percutaneous Closure: Towards X-ray Free Duct Occlusion?

Device selection and procedural guidance for percutaneous ductal closure strongly rely upon angiographic and echocardiographic imaging. Current literature recognises 2D echocardiography as an essential tool for diagnosis and assessment but does not define a consistent methodology to optimise ductal measurement. There is little research comparing echocardiography with gold standard angiography for ductal measurement. Proving 2D echocardiographic ductal measurement to be equivalent to angiography could pave the way for its use as the primary modality in image guidance for percutaneous closure of the ductus. This was a retrospective study of 100 consecutive paediatric patients who underwent percutaneous ductal closure. Echocardiographic images were studied to determine ductal (a) morphology (b) dimensions (length, aortic ampulla, pulmonary end, minimum diameter) (c) size of device that would be appropriate for closure. These data were compared to corresponding measurements generated by angiographic images. Inter and intra-observer ratings were calculated to assess levels of agreement. There were significant differences between the imaging methods in classifying the morphological sub-type and ductal measurements (p < 0.005), except for length which was not found to be significantly different between modalities. Prediction of device selection from angiographic images showed excellent agreement (weighted k = 0.81). Predictions based on echocardiographic images showed a poor level of agreement (weighted k = 0.14). We found poor correlation between echocardiography and angiography for measurement, morphological assessment and device selection. Based on our findings, percutaneous arterial duct occlusion without angiographic guidance in this age group cannot be advocated.

Experience with percutaneous closure of ductus arteriosus using the Amplatzer duct occluder in 243 consecutive patients and long-term results-A single centre study

Background:

Percutaneous closure of patent ductus arteriosus (PDA) with Amplatzer duct occluder (ADO) has become increasingly popular in many cardiovascular centres. This study analysed the long-term results of percutaneous closure of PDA with ADO in a single centre.

Materials and Methods:

Between May 2004 and January 2013, 243 patients with median age of 2.5 years (range = 30 months to 38 years) and median weight of 10 Kg (range 4.5–80.5 Kg) underwent percutaneous closure of PDA using the ADO. The devices were implanted under fluoroscopic guidance. Patients were followed-up for any complications.

Results:

The mean diameter of narrow part of PDA was 6.4 ± 2.2 mm. The mean diameter of devices was 7.8 ± 2.3 mm. The devices were successfully implanted in 239 (98.3%) cases. At immediate, 1 day, 1, 6, 12 months and late follow-up, the complete occlusion rate was 33% (79 case), 97.1% (236 case), 97.5% (237 case), 98.3% (238 case), 98.3% (238 case) and 98.3% (238 case), respectively. Residual shunt remained in one case at late follow-up. The device embolisation occurred in five patients. The devices were successful retrieved in three patient and second larger devices were inserted. Two other devices were surgically retrieved and PDAs were ligated. Moderate left pulmonary artery stenosis (LPA) in one child and mild LPA stenosis in one infant were detected. Mild aortic obstruction occurred in one infant.

Conclusions:

Long-term follow-up of patients indicate that percutaneous closure of PDA using ADO is a safe and effective procedure. However, some complications, including device embolisation, left pulmonary stenosis and aortic obstruction may be observed in some cases.

Retrograde wire-assisted percutaneous transcatheter closure of persistent ductus arteriosus with Amplatzer duct occluder in the elderly: A new application

Percutaneous transcatheter closure of persistent ductus arteriosus (PDA) has been well established in the pediatric field. For moderate- to large-sized PDA, the newly developed Amplatzer duct occluder had offered a good solution, but it depends on stiff wire and delivery sheath. We reported two elderly patients of PDA with vascular anatomy too difficult to be antegradely approached and were closed by a retrograde technique by an assisting wire from the descending aorta. The wire served as a guide and tracked the delivery system to cross the ductus from the venous side smoothly. This retrograde wire-assisted technique could be utilized to overcome the PDA of difficult vascular anatomy, which could not be easily fulfilled by conventional antegrade venous approach.