Skip to content

A Multicenter Prospective Silent Observation Study of an Artificial Intelligence Screening Model for Incidental Pulmonary Embolism on Non-contrast Chest CT

A Multicenter Prospective Silent Observation Study of an Artificial Intelligence Screening Model for Incidental Pulmonary Embolism on Non-contrast Chest CT

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600126615
Enrollment
Unknown
Registered
2026-06-12
Start date
2026-06-15
Completion date
Unknown
Last updated
2026-06-22

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

Conditions

pulmonary embolism

Interventions

Gold Standard:1.Confirmatory imaging examination results within 72 hours (including CTPA, V/Q scan, pulmonary MRA, or contrast-enhanced CT of sufficient technical quality to evaluate the pulmonary art
Index test:Artificial Intelligence Opportunistic Screening Model for Incidental Pulmonary Embolism Based on Non-Contrast Chest CT

Sponsors

The First Affiliated Hospital of Zhejiang University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1.Age >=18 years. 2. Underwent a routine non-contrast chest CT examination at a participating center during the study period. 3. Judged as positive by the version-locked artificial intelligence model.

Exclusion criteria

Exclusion criteria: 1. A definite diagnosis of pulmonary embolism was made prior to the enrolled examination, and the current examination does not represent a new opportunistic screening scenario. 2. The examination was performed primarily with suspected pulmonary embolism as the main purpose, or the patient had already been clearly entered into a confirmatory diagnostic pathway for pulmonary embolism. 3. The baseline examination images have severe motion artifacts, metal artifacts, data corruption, or clearly insufficient scan coverage, rendering reliable artificial intelligence inference impossible. 4. Severe lack of imaging or clinical data prevents completion of the basic verification process.

Design outcomes

Primary

MeasureTime frame
Overall positive predictive value of AI?positive cases;

Secondary

MeasureTime frame
Imaging-confirmed positive predictive value;Expert-adjudicated positive predictive value;Positive predictive value (PPV) in different clinical scenarios and high-risk subgroups;Model performance across different centers and scanning conditions;

Countries

China

Contacts

Public ContactHongkun Zhang

The First Affiliated Hospital of Zhejiang University School of Medicine

1198050@zju.edu.cn+86 135 8823 0962

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jun 29, 2026