Congenital Heart Disease (CHD), Ventricular Septal Defects (VSD)
Conditions
Brief summary
The goal of this observational study is to develop and test a AI-based prediction model for children with perimembranous ventricular septal defect, also called PMVSD. PMVSD is a type of hole between the lower chambers of the heart. Some children with PMVSD may later develop heart structure problems, such as aortic valve prolapse or leakage, subaortic fibrous ridge, left ventricle-to-right atrium shunt, or right ventricular outflow tract obstruction. This study will use past medical records and echocardiography reports from children who received care at six hospitals in China between 2004 and 2022. The main questions it aims to answer are: Can information written in echocardiography reports help predict which children with PMVSD are more likely to develop heart structure problems? Can natural language processing and machine learning improve early risk prediction when used together with routine clinical information? Researchers will review existing, de-identified medical data. They will use natural language processing to turn written descriptions in echocardiography reports into data that a computer model can analyze. These descriptions may include details about the edge of the heart defect, the direction of blood flow, and the relationship between the defect and nearby heart valves. Participants will not receive any study treatment or extra tests. The study will only use information already collected during routine medical care. The prediction models will be trained and tested using data from different hospitals to see how well they work across medical centers.
Interventions
None listed
Sponsors
Xinhua Hospital, Shanghai Jiao Tong University School of Medicine
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
0 Years to 14 Years
Healthy volunteers
No
Inclusion criteria
* Children aged 14 years or younger at the time of presentation/diagnosis; * Confirmed diagnosis of perimembranous ventricular septal defect (PMVSD), or PMVSD accompanied by minor cardiac anomalies that do not alter the hemodynamic status of the VSD, including small patent foramen ovale, atrial septal defect, patent ductus arteriosus, or persistent left superior vena cava; * Availability of at least two consecutive follow-up records, with consistency between the electronic echocardiography reports and the Hospital Information System data.
Exclusion criteria
* Age older than 14 years at diagnosis; * Presence of complex congenital heart disease; * Patients lost to follow-up due to inability to establish contact, resulting in an indeterminate clinical outcome.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Occurrence of Perimembranous Ventricular Septal Defect Related Structural Complications | From initial diagnosis through 3 years after diagnosis | Occurrence of at least one structural complication related to perimembranous ventricular septal defect, as identified by echocardiography, including: (1) aortic valve prolapse and/or aortic regurgitation, defined as valvular leaflet displacement into the defect and/or regurgitation detected by color Doppler; (2) subaortic fibrous ridge, defined as abnormal fibrous strand or ridge-like echogenicity in the left ventricular outflow tract; (3) left ventricle-to-right atrium shunt; or (4) right ventricular outflow tract obstruction, defined as abnormal muscular bundle hypertrophy with increased Doppler flow velocity and a peak pressure gradient greater than 20 mmHg. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Area Under the Precision-Recall Curve (AUCPR) for Complication Prediction | From initial diagnosis through 3 years after diagnosis | The area under the precision-recall curve (AUCPR) of the model for predicting PMVSD-related complication endpoint. |
| Sensitivity of the Model at a Pre-Specified Risk Threshold | From initial diagnosis through 3 years after diagnosis | Sensitivity for predicting PMVSD-related complication endpoint at a pre-specified probability (risk) threshold. |
| Positive Predictive Value (PPV) of the Model at a Pre-Specified Risk Threshold | From initial diagnosis through 3 years after diagnosis | Positive predictive value (PPV) for predicting PMVSD-related complication endpoint at the same pre-specified probability (risk) threshold. |
| Negative Predictive Value (NPV) of the Model at a Pre-Specified Risk Threshold | From initial diagnosis through 3 years after diagnosis | Negative predictive value (NPV) for predicting PMVSD-related complication endpoint at the same pre-specified probability (risk) threshold. |
Countries
China
Outcome results
None listed