Non-invasive Assessment of Pulmonary Circulation using Deep Learning on dynamic chest radiography

Non-invasive Assessment of Pulmonary Circulation using Deep Learning on dynamic chest radiography - Non-invasive Assessment of Pulmonary Circulation using Deep Learning on dynamic chest radiography

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

JPRN

Registry ID

JPRN-UMIN000060169

Enrollment

2000

Registered

2025-12-22

Start date

2025-12-24

Completion date

Unknown

Last updated

2026-06-29

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

Conditions

Pulmonary vascular diseases

Interventions

None listed

Eligibility

Sex/Gender

All

Inclusion criteria

Inclusion criteria: Patients aged 20 years or older who underwent right heart catheterization.

Exclusion criteria

Exclusion criteria: Pregnant women or women who may be pregnant. Patients in whom acquisition of dynamic images is difficult due to inability to maintain a relatively regular cardiac rhythm, such as atrial fibrillation.

Design outcomes

Primary

Measure	Time frame
To assess the agreement between mean pulmonary arterial pressure (mPAP) predicted by a deep learning model using pulmonary circulation images and measured mPAP obtained by right heart catheterization.	—

Countries

Japan

Contacts

Public ContactYoshito Ogihara

Mie University Graduate School of Medicine Department of Heath Care Transition

yoshito@med.mie-u.ac.jp+81-59-231-5015

Outcome results