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

NCT07761377 | Recruiting

• 2 other identifiers: SE25732CIGA11402
• Study Type: observational
• Target: 900
• Locations: 1 country
• Sites: 1

Brief Summary

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.

Conditions

Pulmonary Fibrosis; Interstitial Lung Disease

Keywords

Artificial Intelligence; Medical Device Software; Chest Computed Tomography; Pulmonary Fibrosis; Interstitial Lung Disease; Computer-Aided Detection; Computer-Aided Triage; Diagnostic Performance; Image Analysis; Deep Learning

Outcome Measures

Primary Outcomes (2)

• Sensitivity of AccuPulmo CT Portal for Detecting Pulmonary Fibrosis

  Sensitivity is defined as the proportion of pulmonary fibrosis-positive examinations according to the specialist-derived reference standard that are correctly classified as positive by AccuPulmo CT Portal. The reference standard is determined by majority agreement of at least two of three blinded specialists. A pulmonary fibrosis area greater than 10 percent generated by AccuPulmo CT Portal is classified as positive. Sensitivity will be reported with a 95 percent confidence interval and evaluated against the prespecified performance threshold of 0.80 using a one-sided binomial test.

  Baseline

• Specificity of AccuPulmo CT Portal for Detecting Pulmonary Fibrosis

  Specificity is defined as the proportion of pulmonary fibrosis-negative examinations according to the specialist-derived reference standard that are correctly classified as negative by AccuPulmo CT Portal. The reference standard is determined by majority agreement of at least two of three blinded specialists. A pulmonary fibrosis area of 10 percent or less generated by AccuPulmo CT Portal is classified as negative. Specificity will be reported with a 95 percent confidence interval and evaluated against the prespecified performance threshold of 0.80 using a one-sided binomial test.

  Baseline

Secondary Outcomes (4)

• Diagnostic Accuracy of AccuPulmo CT Portal

  Baseline

• Positive Predictive Value of AccuPulmo CT Portal

  Baseline

• Negative Predictive Value of AccuPulmo CT Portal

  Baseline

• Sensitivity and Specificity Across Prespecified Clinical Subgroups

  Baseline

Study Arms (2)

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.

Device: AccuPulmo CT Portal

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.

Device: AccuPulmo CT Portal

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.

Pulmonary Fibrosis-Negative Controls; Pulmonary Fibrosis-Positive Cases

Eligibility Criteria

• Age: 20 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of adults who underwent clinically indicated chest computed tomography examinations for pulmonary disease at Taichung Veterans General Hospital between January 1, 2020, and December 31, 2024. Participants will be retrospectively identified from existing institutional radiology and clinical information systems. Only pre-existing chest computed tomography images, radiology records, and study-related clinical information will be used.

You may qualify if:

• Participants aged 20 years or older at the time of the chest computed tomography examination
• Participants who underwent chest computed tomography for pulmonary disease at Taichung Veterans General Hospital between January 1, 2020, and December 31, 2024
• Availability of a completed clinical radiology report
• Availability of chest computed tomography images suitable for de-identification and analysis by AccuPulmo CT Portal
• Availability of sufficient image information to permit blinded specialist assessment of pulmonary fibrosis

You may not qualify if:

• Missing or incomplete chest computed tomography images
• Image quality insufficient for pulmonary fibrosis assessment
• Cardiac implants or other devices that substantially interfere with lung texture assessment
• Extensive pneumonia that substantially interferes with lung texture assessment
• Pleural effusion that substantially interferes with lung texture assessment
• Other image abnormalities or artifacts that preclude reliable evaluation of pulmonary fibrosis

Sponsors & Collaborators

• Taichung Veterans General Hospital: lead
• V5med Inc.: collaborator

Study Sites (1)

Taichung Veterans General Hospital City: Taichung

Taichung, 407219, Taiwan

RECRUITING

MeSH Terms

Conditions

Pulmonary Fibrosis; Lung Diseases, Interstitial

Condition Hierarchy (Ancestors)

Lung Diseases; Respiratory Tract Diseases; Fibrosis; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

Pin-Kuei Fu, MD

CONTACT

886 4 2359 2525; yetquen@gmail.com

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Director, Division of Clinical Trials

Study Record Dates

• First Submitted: August 6, 2026
• First Posted: August 12, 2026
• Study Start: October 15, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: August 12, 2026

Record last verified: 2026-08

Data Sharing

• IPD Sharing: Will not share

Locations

TW (1)