Comparing AI vs. Human Reading for Lung Cancer Screening : A Randomized Controlled Trial

Launched by THE FIRST AFFILIATED HOSPITAL OF GUANGZHOU MEDICAL UNIVERSITY · May 23, 2025

Keywords

ClinConnect Summary

This clinical trial is looking at the effectiveness of artificial intelligence (AI) compared to human doctors in reading CT scans for lung cancer screening in community health centers. The goal is to see if AI can help detect lung nodules more accurately and efficiently, especially in places with limited resources. The study will involve expert radiologists who will set the standards for what a correct diagnosis looks like, while an independent committee will review cases from both the AI and human-read groups to ensure fair comparisons.

To participate in this trial, you need to be between 45 and 74 years old and a permanent resident of the communities involved in the study. You should not have a history of lung cancer and should not have been screened for lung cancer in the last three months. Participants can expect to undergo a CT scan and will need to agree to follow-up assessments over time. It's important to know that if you have a confirmed lung cancer diagnosis or severe health issues that prevent CT imaging, you won’t be able to join this study. Overall, this trial aims to provide valuable insights into how AI can assist in improving lung cancer screening processes.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • 1. Aged 45-74 years
• • 2. Permanent resident of participating study communities
• • 3. No prior history of lung cancer and no lung cancer screening within the past 3 months
• • 4. Able to comprehend and voluntarily sign informed consent, with willingness to participate in long-term follow-up
• Exclusion Criteria:
• • 1. Individuals with a confirmed diagnosis of lung cancer
• • 2. Those with severe comorbidities contraindicating CT imaging
• • 3. Inability to understand study protocols or provide informed consent due to cognitive impairment
• • 4. Concurrent participation in other clinical trials that may interfere with study outcomes
• • 5. Unable to comply with follow-up requirements