Artificial Intelligence-driven Tuberculosis Landscape Analysis & Stratification Research

NCT07611695 | Not Yet Recruiting

• 1 other identifier: KY2025-1517
• Study Type: observational
• Target: 31,600
• Locations: 1 country
• Sites: 2

Brief Summary

The goal of this observational study is to establish and validate a comprehensive AI-driven clinical decision support system (AI-CDSS) in whole-chain management for pulmonary tuberculosis (TB) patients. The main question it aims to answer is: How is the predictive performance of this system in terms of multiple key links during TB diagnosis and treatment? Can real-world benefits be derived from this system? This AI framework supports clinicians in making smarter decisions, ultimately improving cure rates and ensuring that every patient receives the most effective, personalized care possible.

Conditions

Pulmonary Tuberculosis; Tuberculosis (TB); Tuberculosis Active

Keywords

tuberculosis; artificial intelligence; predictive model; clinical decision support system

Outcome Measures

Primary Outcomes (1)

• Predictive Performance of the "Easy-to-Treat" versus "Hard-to-Treat" stratification model for pulmonary tuberculosis (PTB)

  The Area Under the Receiver Operating Characteristic curve (AUROC) of the model for discriminating between PTB patients classified as "Easy-to-Treat" versus "Hard-to-Treat". "Easy-to-Treat" patients are defined as patients with PTB who can achieve favorable outcome when treated with a short-course regimen (≤4 months for drug-sensitive TB, ≤6 months for rifampin-resistant TB). "Hard-to-Treat" patients are defined as patients with PTB who will experience unfavorable outcome on short-course treatment (≤4 months for drug-sensitive TB, ≤6 months for rifampin-resistant TB).

  from treatment initiation to 6 months post treatment

Secondary Outcomes (20)

• Brier Score of the "Easy-to-treat" versus "Hard-to-treat" Model

  6 months post-treatment

• Calibration Slope of the "Easy-to-treat" versus "Hard-to-treat" Model

  6 months post-treatment

• Area Under the Receiver Operating Characteristic (AUROC) Curve of the Pre-Drug Susceptibility Testing (Pre-DST) Drug Resistance Predictive Model

  6 months post-treatment

• Area Under the Precision-Recall Curve (AUPRC) of the Pre-Drug Susceptibility Testing (Pre-DST) Drug Resistance Predictive Model

  6 months post-treatment

• F1-score of the Secondary Decision Models for Pre-Drug Susceptibility Testing (Pre-DST) Drug Resistance Prediction

  6 months post-treatment

Study Arms (2)

Model Development Cohort

Retrospective data used for model fitting and tuning. The training and validating sets are interchangeable due to 10-fold cross validation.

External Validation Cohort

Prospective collected data for external model validation and predictive performance measurement

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Pulmonary tuberculosis (TB) patients diagnosed and treated (or will treat) in several TB clinical centers from China

You may qualify if:

• Patient with clinically diagnosed or bacteriologically confirmed pulmonary tuberculosis (TB) who received TB treatment;
• Initiation of TB treatment on or after January 1, 2021;
• Complete key diagnosis and treatment data available in the electronic medical record system.
• Patient with clinically diagnosed or bacteriologically confirmed pulmonary tuberculosis (TB) who is planning to start TB treatment;
• Voluntary participation with signed informed consent form (for adults ≥18 years); parental / guardian consent and co-signed informed consent form are required for minors aged ≤ 18 years.

You may not qualify if:

• Co-morbidity confounding: the presence of other active, life-threatening disease (e.g. late-stage malignancy, non-HIV severe immunodeficiency) for which the expected survival or priority of treatment may substantially interfere with the attribution of TB treatment outcomes;
• Extremely poor treatment adherence: documented evidence indicating that the patient either never initiated treatment or was permanently lost to follow-up within the early treatment period (\<2 weeks), precluding the collection of any valid outcome data.

Sponsors & Collaborators

• Huashan Hospital: lead
• The Hong Kong Polytechnic University: collaborator

Study Sites (2)

Hunan Chest Hospital

Changsha, Hunan, China

Location

Huashan Hospital Affiliated to Fudan University

Shanghai, 210000, China

Location

MeSH Terms

Conditions

Tuberculosis, Pulmonary; Tuberculosis

Condition Hierarchy (Ancestors)

Mycobacterium Infections; Actinomycetales Infections; Gram-Positive Bacterial Infections; Bacterial Infections; Bacterial Infections and Mycoses; Infections; Respiratory Tract Infections; Lung Diseases; Respiratory Tract Diseases

Central Study Contacts

Yang Li, MD

CONTACT

021-52888123; yang.li@nmcid.org.cn

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: OTHER
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: April 23, 2026
• First Posted: May 28, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): December 31, 2027
• Study Completion (Estimated): June 30, 2028
• Last Updated: May 28, 2026

Record last verified: 2026-04

Locations

CN (2)