Accepted for/Published in: JMIR Formative Research
Date Submitted: Dec 21, 2023
Open Peer Review Period: Dec 19, 2023 - Jan 12, 2024
Date Accepted: Jun 25, 2024
(closed for review but you can still tweet)
Comparing the Output of an Artificial Intelligence Algorithm in Detecting Radiological Signs of Pulmonary Tuberculosis in Digital Chest X-rays and Their Smartphone-captured Photos of X-ray Films: A Retrospective Study
ABSTRACT
Background:
Artificial intelligence (AI) based computer-assisted diagnostic devices are recommended for screening and triaging of pulmonary tuberculosis (TB) using digital chest X-ray (CXR) images (soft copies). Most AI algorithms are trained using input data from digital CXR DICOM (Digital Imaging and Communications in Medicine) files. There can be scenarios when only digital CXR films (hard copies) are available for interpretation. A smartphone-captured photo of the digital CXR film may be used for AI to process in such a scenario. There is a gap in the literature investigating if there is a difference in the accuracy of AI algorithms when digital CXR DICOM files are used as input for AI to process as opposed to photos of the digital CXR films being used as input.
Objective:
The primary objective was to compare the sensitivity and specificity of AI in detecting radiological signs of TB when using DICOM files (digital) as input versus when using smartphone-captured photos of digital CXR films (analog).
Methods:
Digital CXR images in DICOM format, corresponding smartphone-captured photos of the digital CXR films, and results from a commercially available AI device (qXR) were obtained retrospectively from data of patients screened for TB. AI results were obtained using both the digital and analog CXR images. A radiological ground truth was established using a panel of three radiologists. The sensitivity and specificity of AI in detecting radiological signs of TB were estimated, and the sensitivity and specificity of AI in digital and analog CXR images were compared.
Results:
A total of 1278 CXR pairs were analyzed. The sensitivity of AI was found to be 92.22% (95% CI: 89.94-94.12) and 90.75% (95% CI: 88.32-92.82), respectively, for digital and analog CXR images (P = .09). The specificity of AI was 82.08% (95% CI: 78.76-85.07) and 79.23% (95% CI: 75.75-82.42), respectively, for digital and analog CXR images (P = .06).
Conclusions:
We did not observe any statistically significant differences in the sensitivity and specificity of AI in digital CXRs and photos of digital CXR films. Clinical Trial: Not applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.