Accuracy of artificial intelligence in CXR screening for pulmonary tuberculosis

Status

Active, not recruiting

Phases

Unknown

Study type

Observational

Source

TCTR

Registry ID

TCTR20220627003

Enrollment

Registered

2022-06-27

Start date

2020-12-15

Completion date

Unknown

Last updated

2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Subjects with high risk of pulmonary tuberculosis Artificial intelligence, pulmonary tuberculosis

Interventions

1. Abnormal CXR with positive bacteriological examination (AFB smear, Xpert MTB/RIF or MTB culture) or 2. Abnormal CXR with negative bacteriological examination but pulmonologist treated with Anti-TB

Diagnostic,Diagnostic

Pulmonary tuberculosis,No pulmonary tuberculosis

Eligibility

Sex/Gender

All

Age

18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Age more than 18 years old 2. High risk for pulmonary tuberculosis subjects who were investigated with CXR PA upright or AP supine 3. Visited during 15 December 2020- 31 January 2022

Exclusion criteria

Exclusion criteria: Suspected active pulmonary tuberculosis subjects who no sputum bacteriological examination

Design outcomes

Primary

Measure	Time frame
Risk of pulmonary TB from CXR within 3 month after CXR Bacteriological examination of sputum	—

Secondary

Measure	Time frame
Compare diagnostic performance between AI and radiologist None sensitivity, specificity, PPV, NPV	—

Countries

Thailand

Contacts

Public ContactPharida Pengwan

280 Paholyotin Road, Mueang District, Lampang Zip code 52000, Thailand

pha095@hotmai.com054237400

Outcome results

None listed

Source: TCTR (via WHO ICTRP) · Data processed: Aug 9, 2026