Retrospective Validation of AccuPulmo CT Portal for Detecting Pulmonary Fibrosis on Chest CT
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age20+
SponsorTaichung Veterans General Hospital
About this trial
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.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
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
Disqualifiers
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
Trial 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.
Trial design
Design model
Case-control
Time perspective
Retrospective
Treatments tested in this trial
AccuPulmo CT Portal
DeviceAccuPulmo 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.
Treatment groups
900 Participants
are divided into 2 treatment groupsGroup A: Pulmonary Fibrosis-Positive Cases1 intervention
Group B: Pulmonary Fibrosis-Negative Controls1 intervention
Trial outcomes
Primary outcomes
1
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.
Time frame
Baseline2
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.
Time frame
BaselineSecondary outcomes
1
Diagnostic Accuracy of AccuPulmo CT Portal
Diagnostic accuracy is defined as the proportion of all evaluated examinations that are correctly classified by AccuPulmo CT Portal as pulmonary fibrosis positive or pulmonary fibrosis negative compared with the specialist-derived reference standard. Accuracy will be reported with a 95 percent confidence interval and evaluated relative to the prespecified threshold of 0.80.
Time frame
Baseline2
Positive Predictive Value of AccuPulmo CT Portal
Positive predictive value is defined as the proportion of examinations classified as positive by AccuPulmo CT Portal that are pulmonary fibrosis positive according to the specialist-derived reference standard. Positive predictive value will be reported with a 95 percent confidence interval and evaluated relative to the prespecified threshold of 0.80.
Time frame
Baseline3
Negative Predictive Value of AccuPulmo CT Portal
Negative predictive value is defined as the proportion of examinations classified as negative by AccuPulmo CT Portal that are pulmonary fibrosis negative according to the specialist-derived reference standard. Negative predictive value will be reported with a 95 percent confidence interval and evaluated relative to the prespecified threshold of 0.80.
Time frame
Baseline4
Sensitivity and Specificity Across Prespecified Clinical Subgroups
The sensitivity and specificity of AccuPulmo CT Portal will be descriptively evaluated across prespecified clinically relevant subgroups, subject to the availability of corresponding retrospective data. Subgroups may include age, sex, computed tomography acquisition characteristics, and other clinical categories defined in the statistical analysis plan. Estimates will be reported with 95 percent confidence intervals.
Time frame
BaselineSponsors and contacts
Click on the lead sponsor to view all of their trials.
Taichung Veterans General Hospital
Lead sponsor
V5med Inc.
Collaborator
Source ClinicalTrials.gov