Skip to content

Research on Artificial Intelligence Models for Pulmonary Embolism Diagnosis and Critical Assessment Based on Deep Learning

Research on Artificial Intelligence Models for Pulmonary Embolism Diagnosis and Critical Assessment Based on Deep Learning

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500110871
Enrollment
Unknown
Registered
2025-10-22
Start date
2025-10-22
Completion date
Unknown
Last updated
2025-10-27

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

Conditions

Acute Pulmonary Thromboembolism (APTE)

Interventions

Gold Standard:Pulmonary embolism is diagnosed when filling defect shadows without contrast agent filling are found in the main pulmonary artery and its branches on CT pulmonary artery examination (CTP
Index test:On CT pulmonary artery examination (CTPA), filling defects without contrast agent filling were found in the main trunk and branches of the pulmonary artery?Whether there is right ventricula

Sponsors

Shanghai Tenth People's Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Age >=18 years old; 2.CTPA confirmed acute pulmonary embolism; 3. Be capable of grouping cases in accordance with the 2019ESC/ERS guidelines for the Diagnosis and Treatment of acute pulmonary embolism;

Exclusion criteria

Exclusion criteria: 1.Pregnant patients; 2.End-stage renal disease (eGFR<15ml/min); 3.History of contrast agent allergy;

Design outcomes

Primary

MeasureTime frame
The AUC value of the developed artificial intelligence model for predicting the accuracy of critical condition assessment in patients with pulmonary embolism (target >0.90);

Secondary

MeasureTime frame
The sensitivity and specificity of the automatic diagnosis performance for pulmonary embolism are over 85%;The net benefit from the clinical decision curve analysis exceeded the PESI score;For operational efficiency, such as singleton prediction time less than 30 seconds;

Countries

China

Contacts

Public ContactDan Mu

Shanghai Tenth People's Hospital

mudan118@126.com+86 13305143131

Outcome results

None listed

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