The Impact of AI Assistance on Radiologist Performance and Healthcare Costs in LDCT-Based Lung Cancer Screening

NCT06988579 | Recruiting

• 1 other identifier: ES-2024-193-01-002
• Study Type: interventional
• Target: 7,294
• Locations: 1 country
• Sites: 1

Brief Summary

AI diagnostic systems show great promise for improving lung cancer screening in community healthcare settings. While not originally designed for primary care, these tools demonstrate capabilities in nodule detection and workflow optimization. However, their effectiveness in resource-limited community centers requires thorough evaluation. This RCT compares AI-assisted versus manual CT interpretation across community health centers. Expert radiologists will establish reference standards, while an independent committee blindly evaluates cases from both groups. The study assesses diagnostic accuracy, operational efficiency, and cost-effectiveness, with blinded analysts resolving discrepancies through consensus to ensure reliable results.

Conditions

Lung Cancer; Artificial Intelligence (AI); Randomized Controlled Trial

Outcome Measures

Primary Outcomes (2)

• Diagnostic Accuracy

  Sensitivity and Specificity: Comparison of AI-assisted versus manual interpretation in detecting malignant pulmonary nodules, validated against histopathological confirmation or 12-month clinical follow-up. Early Detection Rate: Proportion of stage I/II lung cancers correctly identified by each method.

  One year after entry

• Interpretation Consistency

  Inter-reader Agreement: Measured by Cohen's kappa (κ) between AI-assisted radiologists and the independent review committee (IRC). Intra-reader Variability: Consistency of nodule classification in repeat readings (subset analysis).

  One year after entry

Secondary Outcomes (1)

• Cost-Effectiveness

  One year after entry

Study Arms (2)

AI-Assisted Group

EXPERIMENTAL

The AI-assisted group utilized AI-powered diagnostic software for interpreting low-dose computed tomography (LDCT) scans

Other: AI

The manual interpretation group

NO INTERVENTION

The manual interpretation group relied on standard radiologist evaluation for analyzing low-dose computed tomography (LDCT) scans.

Interventions

AI OTHER

An integrated AI-human collaborative workflow for lung cancer screening interpretation

AI-Assisted Group

Eligibility Criteria

• Age: 40 Years - 74 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Aged 45-74 years
• Permanent resident of participating study communities
• No prior history of lung cancer and no lung cancer screening within the past 3 months
• Able to comprehend and voluntarily sign informed consent, with willingness to participate in long-term follow-up

You may not qualify if:

• Individuals with a confirmed diagnosis of lung cancer
• Those with severe comorbidities contraindicating CT imaging
• Inability to understand study protocols or provide informed consent due to cognitive impairment
• Concurrent participation in other clinical trials that may interfere with study outcomes
• Unable to comply with follow-up requirements

Sponsors & Collaborators

• The First Affiliated Hospital of Guangzhou Medical University: lead

Study Sites (1)

the First Affiliated Hospital of Guangzhou Medical University,

Guangzhou, Guangdong, 510120, China

RECRUITING

MeSH Terms

Conditions

Lung Neoplasms

Condition Hierarchy (Ancestors)

Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Lung Diseases; Respiratory Tract Diseases

Central Study Contacts

Jianxing He

CONTACT

+8618320729913; drjianxing.he@gmail.com

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: May 16, 2025
• First Posted: May 25, 2025
• Study Start: July 1, 2024
• Primary Completion: October 31, 2025
• Study Completion: January 7, 2026
• Last Updated: June 26, 2025

Record last verified: 2025-05

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)