Chest X-ray for Clinical Evaluation
Conditions
Keywords
X-Ray, AI, Chest diseases, Accuracy
Brief summary
X-ray examination is one of the most commonly used imaging modalities, especially chest X-ray, which is routinely performed for hospitalized patients. However, due to the low density resolution of X-ray images, radiologists' ability to diagnose diseases-particularly small lesions-is often affected. Studies have shown that the diagnostic accuracy of radiologists using chest X-rays is only around 70%, which does not meet clinical demands. Based on this, we developed an artificial intelligence model to assist radiologists in interpreting X-ray images and generating reports, with the aim of improving diagnostic accuracy and reducing interpretation time.
Interventions
DIAGNOSTIC_TESTAI-assisted radiologist diagnostic group
Based on the previously developed X-ray image diagnosis and report generation model, radiologists are assisted in interpreting X-ray images and generating reports.
DIAGNOSTIC_TESTRadiologist diagnostic group
After the patient undergoes an X-ray examination, a radiologist generates the report and makes the diagnosis.
Sponsors
Union Hospital, Tongji Medical College, Huazhong University of Science and Technology
Study design
Observational model
CASE_CONTROL
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
Inclusion criteria
* Clinically suspected thoracic diseases (such as pneumonia, tuberculosis, or lung cancer) requiring X-ray diagnosis； * Patients providing written informed consent for research data use； * Complete clinical records (including chief complaints, medical history, and laboratory test results)
Exclusion criteria
* Substandard X-ray image quality (including severe motion artifacts, over-/underexposure, or missing anatomical structures) * Pregnant or lactating women
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Area Under the Curve | From enrollment to the end of X-ray image acquisition at 1 week | The primary outcome was the AUC to evaluate diagnostic performance, comparing radiologists with and without AI assistance. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| X-ray report generation time | From enrollment to the end of X-ray image acquisition at 1 week | X-ray report generation time refers to the amount of time required to produce a diagnostic report after an X-ray examination has been performed. It typically measures the interval from when the X-ray images are acquired to when the radiologist (with or without AI assistance) completes and finalizes the report. |
Countries
China
Contacts
CONTACTHuangxuan Zhao, PhD
Outcome results
None listed