AI prediction of complications after transcatheter closure of perimembranous VSD in children
Multimodal Clinical Data Integration and Artificial Intelligence Modeling for Predicting Complications Following Pediatric Transcatheter Closure of Perimembranous Ventricular Septal Defect
This project will try an AI model that combines clinical data, text notes, and images to predict which children undergoing transcatheter closure of perimembranous VSD are at higher risk of treatment-related complications.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 5249 (estimated) |
| Ages | N/A to 18 Years |
| Sex | All |
| Sponsor | Xinhua Hospital, Shanghai Jiao Tong University School of Medicine Academic / other |
| Locations | 1 site (Shanghai, Shanghai Municipality) |
| Trial ID | NCT07375602 on ClinicalTrials.gov |
What this trial studies
This retrospective observational project will develop and validate a multimodal artificial intelligence model to predict treatment-related complications after transcatheter device closure for perimembranous ventricular septal defect in children. Researchers will extract demographics, laboratory results, electronic health record text, echocardiography reports, chest radiographs, and electrocardiograms from routine clinical records and use deep learning to pull features from text and images. The model will be trained and validated on cases from a single center with outcomes ascertained within a prespecified follow-up window. The aim is to generate individualized risk estimates that can inform monitoring and clinical decision-making.
Who should consider this trial
Good fit: Children aged 18 or younger with echocardiographically confirmed perimembranous VSD who underwent transcatheter device closure at the study center and have sufficient clinical records and follow-up data.
Not a fit: Children with non-perimembranous or complex VSDs, those with prior surgical or transcatheter VSD repair, or patients lacking adequate clinical records are not expected to benefit from this model.
Why it matters
Potential benefit: If successful, the model could help clinicians identify higher-risk children before or after device closure so monitoring and care can be tailored to reduce complications.
How similar studies have performed: AI approaches have shown promise for cardiac imaging and outcome prediction in related settings, but multimodal deep-learning models specifically for predicting complications after pediatric pmVSD device closure are largely novel and limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age ≤ 18 years at the time of transcatheter procedure. * Diagnosis of perimembranous ventricular septal defect confirmed by echocardiography, and underwent transcatheter device closure at the study center. * Medical records sufficient to ascertain the primary outcome within the pre-specified follow-up window, and availability of minimum baseline clinical information required for model development/validation. Exclusion Criteria: * Ventricular septal defects not classified as perimembranous on echocardiography, including muscular, outlet, or inlet VSDs, as well as multiple or complex VSDs involving more than one septal region. * Presence of complex congenital heart disease or associated structural abnormalities requiring concomitant surgical repair (e.g., tetralogy of Fallot). * Prior surgical VSD repair or prior transcatheter VSD closure.
Where this trial is running
Shanghai, Shanghai Municipality
- Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine — Shanghai, Shanghai Municipality, China (Recruiting)
Study contacts
- Study coordinator: Kun Sun
- Email: drsunkun@xinhuamed.com.cn
- Phone: 021-13601846338
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.