The Chang Gung Pneumothorax Detection Software is a medical software that can automatically detect whether there is a pneumothorax in Chest X-Ray. The purpose of this study is to verify whether the Chang Gung Pneumothorax Detection Software can correctly identify patients with pneumothorax in Chest X-Ray. The results of the software analysis will be used for the performance of the software on the primary and secondary outcomes.
This clinical trial is a retrospective study. DICOM images of de-identified Chest X-Ray were collected from 6 hospitals of Chang Gung Memorial Hospital from January 1, 2006 to December 31, 2020. The test set of 5,347 items was established, and total of 344 cases will be sampled by simple random stratification, including 172 cases with pneumothorax and 172 cases without pneumothorax. The image must be in DICOM format. Follow-up by three specialist physicians to interpret the presence or absence of pneumothorax, the result will be the standard of this test (Reference). After confirming the correct standard of each Chest X-Ray, the Chest X-Ray will be put into Chang Gung Pneumothorax Detection Software, and analyzed by the primary and secondary outcomes.
Study Type
OBSERVATIONAL
Enrollment
344
The Chang Gung Pneumothorax Detection Software is an independent software as a medical device, which inputs digital Chest X-Ray to automatically detect whether there is a pneumothorax. The inferred results output by this software can assist clinicians or professional medical personnel to identify whether a patient has pneumothorax. This product is only used to analyze the digitized Chest X-Ray DICOM of patients over 20 years old and under 100 years old.
Chang Gung memorial hospital
Taoyuan, Taiwan
Sensitivity
The rate of test results that correctly indicate the presence.
Time frame: baseline
Specificity
The rate of test results that correctly indicate the absence.
Time frame: baseline
Area Under the receiver operating characteristic Curve
A graphical plot that illustrates the diagnostic ability of a binary classifier system as its discrimination threshold is varied.
Time frame: baseline
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.