Early Intervention Strategies for Lung Cancer

The First Affiliated Hospital of Guangzhou Medical University16,000 enrolled

Overview

Low-dose CT (LDCT）can detect and treat lung cancer earlier and more quickly, while expanded screening coverage helps reduce the incidence and mortality of respiratory diseases such as lung cancer. This study aims to conduct a single-arm cluster randomized trial of digitally enabled LDCT in Guangzhou to assess its intervention effectiveness and cost-effectiveness.

This study uses a single-arm design to assign community health service centers in two districts of Guangzhou (Liwan and Baiyun) to the intervention group. A historical self-comparison design is employed. The intervention measures utilize a digital empowerment model for lung cancer screening, which includes the following components: ① Digital health platform: Each street and community health center manages resident information through the Lung Health mini-program; ② AI-based full-lung model reading system: Using artificial intelligence technology to assist in interpreting CT images; ③ Low-dose CT screening: Low-dose CT screening is conducted at primary healthcare institutions, and patients with detected lung nodules are referred to hospitals for further examination. The sampling method used is Probability Proportional to Size (PPS), with an expected sample size of 16000. Participants will complete the "Lung Cancer Health Questionnaire" to collect individual-level confounding factors. Screening data will be collected through the "Fei'anxin" mini-program, and diagnostic data will be provided by designated hospitals and the First Affiliated Hospital of Guangzhou Medical University. The primary outcome of the study is the proportion of early-stage lung cancer in the screening population, defined as the number of early-stage lung cancer cases divided by the total number of people screened. An economic evaluation of the lung cancer CT screening will also be conducted.

Study Type

INTERVENTIONAL

Allocation

Purpose

SCREENING

Masking

NONE

Enrollment

Interventions

Low-dose CT screeningDEVICE

Low-dose CT screening is conducted at primary healthcare institutions, and patients with detected lung nodules are referred to hospitals for further examination

AI full-lung model interpretation systemDEVICE

Using artificial intelligence technology to assist in the interpretation of CT images

Digital Health PlatformDEVICE

Community health centers and streets in Guangzhou use a program called "Fei Anxin" to manage residents' information in a unified way

Eligibility

Sex: ALLMin age: 40 YearsMax age: 74 YearsHealthy volunteers:

Medical Language ↔ Plain English

1.Community Health Service Centers (Cluster Level) 1. Inclusion Criteria The community health service center must be located within one of the 11 districts of Guangzhou. The center must manage a population of over 10,000 elderly individuals. The center should be equipped with at least one CT machine and have qualified medical personnel, such as radiologists, radiologic technicians, and nursing staff. 2. Exclusion Criteria Community health centers currently participating in other public health projects or studies that may affect screening results. Community health service centers where researchers cannot collect data or conduct follow-up. 2\. Screening Subjects (Individual Level) 1. Inclusion Criteria Aged 40-75 years. Residing in the community participating in the study for a long time. No known history of lung cancer and has not undergone lung cancer screening in the past three months. Able to understand and willing to sign the informed consent form, and able to participate in long-term follow-up. 2. Exclusion Criteria Individuals diagnosed with lung cancer. Individuals with severe other health issues that make them unsuitable for CT imaging. Individuals unable to understand the study protocol or who cannot provide informed consent due to cognitive impairments. Individuals participating in other clinical trials that may affect the results of this study. Individuals unable to undergo follow-up.