Skip to content

Research Protocol for Identifying Left and Right Ventricular Dysfunction from Chest X-ray Images Using Deep Learning

Research Protocol for Identifying Left and Right Ventricular Dysfunction from Chest X-ray Images Using Deep Learning

Status
Active, not recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500095838
Enrollment
Unknown
Registered
2025-01-14
Start date
2025-02-01
Completion date
Unknown
Last updated
2025-01-27

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

left and right ventricular dysfunction

Interventions

Gold Standard:In echocardiography, male subjects with an interventricular septal thickness at end-diastole (IVSd) value > 1.5 cm or a left ventricular posterior wall thickness at end-diastole (LVPWd)
Index test:The probability of diagnosing left ventricular diastolic dysfunction and right ventricular dysfunction by the deep learning model.

Sponsors

Shapingba People's Hospital, Chongqing.
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 90 Years

Inclusion criteria

Inclusion criteria: 1. Chest X-rays in their full resolution are extracted in DICOM format 2. CXRs and echocardiograms performed within 12 months of each other 3. The age of the patients for whom the X-ray is performed is over 18 but under 90 years old 4. The X-ray image captures the RV. 5. only include posteroanterior frontal X-rays 6. Echocardiograms will be filtered to only those with all continuous measurements of interest

Exclusion criteria

Exclusion criteria: 1. Exclude echocardiograms without continuous measurements 2. Exclude patients with thoracic deformities 3. Exclude lateral oranteroposterior films 4. Excluded patients with pacemakers(PM), implantable cardioverter defibrillators (ICDs), or heart transplants (HTs), and lung transplants (LTs).

Design outcomes

Primary

MeasureTime frame
Accuracy;Precision;Recall;Sensitivity;F1 - Score;ROC ;AUC;

Countries

China

Contacts

Public ContactChenshu Huang

Department of Radiology, Shapingba People's Hospital, Chongqing.

bl8997@outlook.com+86 132 7272 9420

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026