Retrospective Validation of AccuPulmo CT Portal for Detecting Pulmonary Fibrosis on Chest CT

Sponsor
Taichung Veterans General Hospital
Study ID
NCT07761377
Status
Recruiting
Apply to this trial

Conditions

Eligibility Criteria

Sex
ALL
Age
20 Years - N/A
Healthy Volunteers
Not accepted

Interventions

  • AccuPulmo CT Portal — DEVICE
    AccuPulmo CT Portal is an artificial intelligence-assisted medical imaging software intended to analyze chest computed tomography images and identify imaging findings associated with pulmonary fibrosis. The software estimates the proportion of pulmonary fibrosis within the lung. In this study, a pulmonary fibrosis area greater than 10 percent is classified as positive, and a pulmonary fibrosis area of 10 percent or less is classified as negative. The software will be applied retrospectively to de-identified pre-existing chest computed tomography images in an offline research environment. Its output will not be returned to treating physicians and will not affect participant diagnosis, treatment, or clinical management.

Study Details

This retrospective observational study evaluates the diagnostic performance of AccuPulmo CT Portal, an artificial intelligence-assisted medical imaging software, for detecting pulmonary fibrosis on pre-existing chest computed tomography images. A total of 900 chest computed tomography examinations obtained at Taichung Veterans General Hospital between January 1, 2020, and December 31, 2024, will be retrospectively selected. The planned sample includes 300 examinations with pulmonary fibrosis and 600 examinations without pulmonary fibrosis. All study images will be de-identified and coded before evaluation. Three qualified specialists in pulmonology or radiology will independently review each image without access to the original radiology report or the artificial intelligence output. The reference standard will be established by majority agreement of at least two of the three specialists. AccuPulmo CT Portal will retrospectively analyze the coded images. An artificial intelligence-derived pulmonary fibrosis area greater than 10 percent will be classified as positive, and an area of 10 percent or less will be classified as negative. The primary performance measures are sensitivity and specificity. Secondary measures include accuracy, positive predictive value, negative predictive value, and performance across clinically relevant subgroups. The software results will not be returned to treating physicians and will not affect participant diagnosis, treatment, or clinical management.

Key Dates

First listed
Aug 12, 2026
Start date
Oct 15, 2025
Status verified
Aug 2026
Primary completion
Dec 31, 2026
Completion
Dec 31, 2026

Study Design

Enrollment
900 participants (estimated)

Arms

  • Arm: Pulmonary Fibrosis-Positive Cases
    Participants with pre-existing chest computed tomography examinations selected as potentially positive for pulmonary fibrosis based on available institutional radiology records. Final pulmonary fibrosis status for the performance analysis will be determined by majority agreement of at least two of three blinded specialists in pulmonology or radiology.
  • Arm: Pulmonary Fibrosis-Negative Controls
    Participants with pre-existing chest computed tomography examinations selected as potentially negative for pulmonary fibrosis based on available institutional radiology records. Final pulmonary fibrosis status for the performance analysis will be determined by majority agreement of at least two of three blinded specialists in pulmonology or radiology.

Primary Outcome Measure

Sensitivity of AccuPulmo CT Portal for Detecting Pulmonary Fibrosis [ Time Frame: Baseline ]

Central Contacts

Related Studies