Research on Key Interventional Technologies for Controlling the Epidemic in High-prevalence Areas of Tuberculosis in Guangxi, China

Active Case Finding Using Mobile Vans Equipped With Artificial Intelligence Aided Radiology Tests and Sputum Collection for Rapid Diagnostic Tests to Reduce Tuberculosis Prevalence Among High-risk Populations in Rural China: a Pragmatic Cluster Randomized Controlled Trial

The goal of this study is to find out if using mobile vans with advanced technology can help reduce tuberculosis (TB) in rural Guangxi, China. The study will also examine how practical and cost-effective this approach is. The main questions it aims to answer are: 1) Does this new screening method lower the number of TB cases among high-risk groups? and 2) Is this method practical and acceptable for communities and healthcare workers? Participants in the study will: 1) undergo TB screening with mobile vans that use artificial intelligence (AI) to read chest X-rays, 2) answer a short questionnaire about their symptoms and health history, and 3) provide sputum samples for GeneXpert testing if needed.

Some communities will receive the new screening method, while others will continue with usual care. Researchers will compare TB rates in the two groups over three years to see if the new approach works better for TB control. If successful, this method could be used to improve TB control in other areas.

Study Overview

• Status: Recruiting
• Conditions: Tuberculosis (TB)
• Intervention / Treatment: Diagnostic test: Active case finding

Detailed Description

This study evaluates the effectiveness and feasibility of a novel active case finding (ACF) strategy for tuberculosis (TB) in rural Guangxi, China. The intervention involves the use of mobile vans equipped with artificial intelligence (AI)-aided radiology, and rapid diagnostic testing (GeneXpert) to identify TB cases among high-risk populations. TB is a significant public health issue in the proposed research areas, particularly among older adults, individuals with a history of TB, close contacts of TB patients, and those with underlying conditions such as diabetes or HIV. By addressing the gaps in routine care, this study aims to reduce TB prevalence and provide insights for implementing similar approaches in other high-burden settings.

The study is designed as a pragmatic, parallel, cluster-randomized controlled trial conducted in two counties with high TB prevalence. A total of 23 townships are randomized into intervention and control groups in a 1:1 ratio. In the intervention group, a one-time ACF campaign will be conducted during Year 1. This campaign integrates AI-supported digital radiography (DR) for chest X-rays, symptom screening, and sputum collection for laboratory-based TB testing. The control group will continue receiving routine care, primarily relying on passive case finding. TB treatment in both groups will follow standard national guidelines.

Participants are individuals aged 15 years and older who are at high risk for TB. This includes older adults, individuals previously treated for TB or with close contact with TB patients diagnosed in the last three years, and those clinically diagnosed with conditions such as diabetes or HIV or exposed to occupational hazards like mining. In the intervention group, mobile vans equipped with DR machines and refrigerated storage will visit villages to perform on-site screenings. Eligible individuals will undergo chest X-rays and provide sputum samples if TB-related symptoms or abnormalities on X-rays are detected. Sputum samples will be transported to county hospitals for diagnostic testing using smear microscopy, culture, and GeneXpert technologies. Diagnosed TB cases will be promptly notified and referred for treatment per national guidelines.

The primary outcome of this study is the prevalence of bacteriologically confirmed TB among high-risk populations in Year 3. Data collection includes demographic, clinical, laboratory, and cost information from patient, health system, and societal perspectives. The analysis will employ mixed-effect logistic regression models to evaluate the impact of the intervention on primary and secondary outcomes. Cost-effectiveness analysis will calculate the incremental cost required for a percentage reduction in TB prevalence. In addition, a process evaluation will assess the intervention's feasibility, acceptability, and fidelity using qualitative and quantitative methods, including interviews with healthcare workers, community members, and participants, as well as analysis of participation rates.

This trial addresses the challenges of TB detection in resource-limited rural settings by integrating innovative technologies such as AI and mobile health solutions. It has the potential to contribute significantly to achieving the World Health Organization's (WHO) End TB Strategy, which aims to eliminate TB by 2035. The study has received ethical approval from the Guangxi Institutional Review Board, and informed consent will be obtained from all participants. Findings from this study will be disseminated through academic publications, policy briefs, and conference presentations to inform global TB control strategies.

• Study Type: Interventional
• Enrollment (Estimated): 72000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Dabin Liang, PhD; Phone Number: +86 771 251 8743; Email: gxmu958@163.com
• Study Contact Backup: Name: Xiaoyan Liang; Phone Number: +86 183 7717 1573; Email: lxy530028@163.com

Study Locations

• China
  • Guangxi
    • Nanning, Guangxi, China, 530000
      • Recruiting
      • Guangxi Zhuang Autonomous Region Center for Disease Control and Prevention
      • Contact: Xiaoyan Liang; Phone Number: +86 183 7717 1573; Email: lxy530028@163.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• all residents who are elderly (i.e., aged 65 and above)
• all residents who are aged 15 to 64 with one of the following conditions: being patients previously treated for TB or close contacts of a patient with a TB patient diagnosed within the last three years; having been clinically diagnosed with diabetes, HIV positive, or worked as a miner
• Have signed consent form

Exclusion Criteria:

• Residents who refuse participation.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention; A single active case finding campaign for Tuberculosis will occur in Year 1 alongside the usual care.	Diagnostic test: Active case finding; Villagers will be informed through public announcements and social workers. Before the campaign, social workers and village doctors will recruit participants and obtain consent through door-to-door visits. A mobile van equipped with an AI-assisted digital radiography (DR) machine and a refrigerator will visit villages on agreed dates. Participants will complete a TB symptom questionnaire and undergo DR screening. Those with TB symptoms or abnormal DR results will provide on-site sputum samples and collect additional morning and night samples. Trained staff will ensure proper collection and offer nebulizer support if needed. Samples will be transported daily to hospitals for testing using smear, culture, and GeneXpert. Participants with negative bacteriological results but abnormal findings will be referred for further clinical assessment.
No Intervention: Control; Usual care will be provided and no active case finding activities will be implemented.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prevalence rate of bacteriologically positive TB	Prevalence rate of bacteriologically positive TB in Year 3 among the high-risk populations , including those of 65 and older, those who are under 65 but have a history of tuberculosis treatment or have been in close contact with a person diagnosed of TB within the past three years, have been clinically diagnosed with diabetes, HIV, or have a background of working as a miner.	In year 3 after recruitment

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prevalence rate of active TB	Prevalence rate of active TB, including both bacteriologically positive and negative cases, among the high-risk populations in Year 3	In Year 3 after recruitment
Notification rates of bacteriologically positive TB	Notification rates of bacteriologically positive TB cases among all populations in Year 3	In Year 3 after recruitment
Notification rates of active TB cases	Notification rates of active TB cases, including both bacteriologically positive and negative cases among all populations in Year 3	In Year 3 after recruitment

Collaborators and Investigators

• Sponsor: University of Toronto
• Collaborators: Guangxi Zhuang Autonomous Region Center for Disease Control and Prevention
• Investigators: Principal Investigator: Xiaolin Wei, PhD, University of Toronto; Principal Investigator: Dabin Liang, PhD, Guangxi Zhuang Autonomous Region Center for Disease Control and Prevention

Study record dates

Study Major Dates

• Study Start (Actual): November 20, 2021
• Primary Completion (Estimated): January 31, 2025
• Study Completion (Estimated): April 30, 2025

Study Registration Dates

• First Submitted: November 20, 2024
• First Submitted That Met QC Criteria: November 20, 2024
• First Posted (Actual): November 25, 2024

Study Record Updates

• Last Update Posted (Estimated): December 6, 2024
• Last Update Submitted That Met QC Criteria: December 3, 2024
• Last Verified: December 1, 2024

More Information

Terms related to this study

• Keywords: China; artificial intelligence; Tuberculosis; cluster randomized controlled trial; active case finding; mobile van
• Additional Relevant MeSH Terms: Infections; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Actinomycetales Infections; Mycobacterium Infections; Tuberculosis
• Other Study ID Numbers: GXTB202108

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data won't be publicly available due to local policy. Clustered data can be shared upon reasonable request to lxy530028@163.com for research purpose only after January 1, 2027.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No