Evaluation of CAD-based Triage for CXR Interpretation During TB Screening

NCT ID: NCT06401434

Last Updated: 2025-08-12

Basic Information

• Recruitment Status: COMPLETED
• Clinical Phase: NA
• Total Enrollment: 23835 participants
• Study Classification: INTERVENTIONAL
• Study Start Date: 2024-05-29
• Study Completion Date: 2025-04-20

Brief Summary

Clinical workflows which position computer-aided detection (CAD) software for chest X-ray interpretation during TB screening as a decision support tool for radiologists, with the aim of improving interpretation accuracy and/or efficiency, may prove to be a more acceptable use case than outright radiologist replacement.

Freundeskreis Für Internationale Tuberkulosehilfe e.V. (FIT) will organize 80 community-based chest X-ray screening events for TB across three provinces of Viet Nam as part of a pragmatic clinical trial designed to assess the real-world impact a CAD software deployment. INSIGHT CXR CAD software (Lunit, South Korea) will be used to support CXR interprtation at half of the screening events (randomly selected) by automating the identification of normal CXR images before an on-site radiologist makes a final CXR interpretation (CAD-based triage use case). The other screening events will use only an on-site radiologist for CXR interpretation (usual care).

Aims

1. Compare the difference in the proportion of chest X-ray images which are declared as abnormal by the on-site radiologist between the study arms

2. Compare the difference in the proportion of people diagnosed with TB using the Xpert MTB/RIF Ultra assay among those screened by chest X-ray between the study arms

Detailed Description

In 2021, the World Health Organization released guidelines which recommended computer-aided detection (CAD) software as a replacement for radiologists during chest X-ray (CXR) screening for TB.[1] However, clinical workflows which position CAD software as a decision support tool for radiologists, with the aim of improving CXR interpretation accuracy and/or efficiency, may prove to be a more acceptable use case with radiologists. CAD software are now being integrated into breast [2], prostate [3], and lung [4] cancer screening programs in high-income countries in these ways. Yet, there is currently a dearth of literature evaluating CAD software during CXR screening for TB under such use cases.

Freundeskreis Für Internationale Tuberkulosehilfe e.V. (FIT), in collaboration with local public-sector partners, will organize 80 community-based CXR screening events for TB [5,6] across three provinces in Southern Viet Nam (Ba Ria - Vung Tau, Ho Chi Minh City and Long An) as part of a pragmatic clinical trial designed to assess the real-world impact a CAD software deployment. INSIGHT CXR CAD software (Lunit, South Korea) will be used to support CXR interprtation at half of the screening events (randomly selected) by automating the identification of normal CXR images before an on-site radiologist makes a final CXR interpretation (CAD-based triage use case). The other screening events will use only an on-site radiologist for CXR interpretation (usual care).

A retrospective assessment of comparing radiologist only CXR interpretation to CAD-based triage with INSIGHT CXR software showed that CAD-based triage resutled in a -68.9% reduction in human workloads, a -30.1% decrease in CXR abnormality rates and follow-on diagnostic testing, and just a -0.2% reduction in TB detection. This pragmatic clinical trial is neseted within a community-based CXR screening initiative whose scale has been determined by the availability of donor funding. However, a sufficient number of participants will be recruited and screened in each arm to detect a 30% difference (12.4% vs 17.8%) in the proportion of CXR images labelled as abnormal (primary aim).

Study Arms

1. On-site radiologist / usual care (40 screening events; 12,000 participants): All participants in this arm will be screened by CXR. All CXR images will be interpreted by only an on-site radiologist. Participants with an abnormal CXR result from the radiologist will be indicated for diagnostic testing.

2. CAD-based triage / experimental care (40 screening events; 12,000 participants): All participants in this arm will be screened by CXR. All CXR images will first be processed with the INSIGHT CXR CAD software (Lunit, South Korea) to identify the totally normal/clear CXR images; only those with the possibility of containing an abnormality (abnormality score ≥ 20) will be sent to the on-site radiologist. Participants with an abnormal CXR result from the radiologist will be indicated for diagnostic testing.

Aims

1. Compare the difference in the proportion of CXR images which are declared as abnormal by the on-site radiologist between the study arms

2. Compare the difference in the proportion of people diagnosed with TB using the Xpert MTB/RIF Ultra assay among those screened by CXR between the study arms

Conditions

Tuberculosis

Study Design

• Allocation Method: RANDOMIZED
• Intervention Model: PARALLEL
• Primary Study Purpose: SCREENING
• Blinding Strategy: NONE

Study Groups

On-site radiologist

On-site radiologist reads/interprets all CXR images

Group Type: ACTIVE_COMPARATOR

On-site radiologist

Intervention Type: DIAGNOSTIC_TEST

All participants in this arm will be screened by CXR. All CXR images will be interpreted by only an on-site radiologist. Participants with an abnormal CXR result from the radiologist will be indicated for follow-on diagnostic testing with the Xpert MTB/RIF Ultra assay.

CAD-based triage (with INSIGHT CXR software)

CAD software processes all CXR images and the on-site radiologist only reads/interprets the subset not deemed totally to be clear/normal by the CAD software

Group Type: EXPERIMENTAL

CAD-based triage (with INSIGHT CXR software)

Intervention Type: DIAGNOSTIC_TEST

All participants in this arm will be screened by CXR. All CXR images will first be processed with the INSIGHT CXR CAD software (Lunit, South Korea) to identify the totally normal/clear CXR images; only those with the possibility of containing an abnormality (abnormality score ≥ 20) will be sent to the on-site radiologist for reading/interpretation. Participants with an abnormal CXR result from the radiologist will be indicated for follow-on diagnostic testing with the Xpert MTB/RIF Ultra assay.

Interventions

On-site radiologist

All participants in this arm will be screened by CXR. All CXR images will be interpreted by only an on-site radiologist. Participants with an abnormal CXR result from the radiologist will be indicated for follow-on diagnostic testing with the Xpert MTB/RIF Ultra assay.

Intervention Type: DIAGNOSTIC_TEST

CAD-based triage (with INSIGHT CXR software)

All participants in this arm will be screened by CXR. All CXR images will first be processed with the INSIGHT CXR CAD software (Lunit, South Korea) to identify the totally normal/clear CXR images; only those with the possibility of containing an abnormality (abnormality score ≥ 20) will be sent to the on-site radiologist for reading/interpretation. Participants with an abnormal CXR result from the radiologist will be indicated for follow-on diagnostic testing with the Xpert MTB/RIF Ultra assay.

Intervention Type: DIAGNOSTIC_TEST

Eligibility Criteria

Inclusion Criteria

• Willing to be screened for TB
• Aged ≥ 18 years

Exclusion Criteria

• Recently received a TB diagnosed (not yet on treatment)
• Currently being treated for TB
• Pregnant women

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: Yes

Sponsors

Freundeskreis Für Internationale Tuberkulosehilfe e.V

OTHER

Sponsor Role: lead

Responsible Party

Responsibility Role: SPONSOR

Principal Investigators

Andrew J Codlin

Role: PRINCIPAL_INVESTIGATOR

Freundeskreis Für Internationale Tuberkulosehilfe e.V

Locations

Pham Ngoc Thach Hospital

Ho Chi Minh City, , Vietnam

Long An Lung Hospital

Long An, , Vietnam

Pham Huu Chi Lung Hospital, BR-VT

Vũng Tàu, , Vietnam

Countries

Vietnam

References

WHO consolidated guidelines on tuberculosis: Module 2: screening - systematic screening for tuberculosis disease [Internet]. Geneva: World Health Organization; 2021. No abstract available. Available from http://www.ncbi.nlm.nih.gov/books/NBK569338/

Reference Type: BACKGROUND

PMID: 33822560 (View on PubMed)

Potnis KC, Ross JS, Aneja S, Gross CP, Richman IB. Artificial Intelligence in Breast Cancer Screening: Evaluation of FDA Device Regulation and Future Recommendations. JAMA Intern Med. 2022 Dec 1;182(12):1306-1312. doi: 10.1001/jamainternmed.2022.4969.

Reference Type: BACKGROUND

PMID: 36342705 (View on PubMed)

Twilt JJ, van Leeuwen KG, Huisman HJ, Futterer JJ, de Rooij M. Artificial Intelligence Based Algorithms for Prostate Cancer Classification and Detection on Magnetic Resonance Imaging: A Narrative Review. Diagnostics (Basel). 2021 May 26;11(6):959. doi: 10.3390/diagnostics11060959.

Reference Type: BACKGROUND

PMID: 34073627 (View on PubMed)

Milam ME, Koo CW. The current status and future of FDA-approved artificial intelligence tools in chest radiology in the United States. Clin Radiol. 2023 Feb;78(2):115-122. doi: 10.1016/j.crad.2022.08.135. Epub 2022 Sep 28.

Reference Type: BACKGROUND

PMID: 36180271 (View on PubMed)

Vo LNQ, Forse RJ, Codlin AJ, Vu TN, Le GT, Do GC, Van Truong V, Dang HM, Nguyen LH, Nguyen HB, Nguyen NV, Levy J, Squire B, Lonnroth K, Caws M. A comparative impact evaluation of two human resource models for community-based active tuberculosis case finding in Ho Chi Minh City, Viet Nam. BMC Public Health. 2020 Jun 15;20(1):934. doi: 10.1186/s12889-020-09042-4.

Reference Type: BACKGROUND

PMID: 32539700 (View on PubMed)

Nguyen LH, Codlin AJ, Vo LNQ, Dao T, Tran D, Forse RJ, Vu TN, Le GT, Luu T, Do GC, Truong VV, Minh HDT, Nguyen HH, Creswell J, Caws M, Nguyen HB, Nguyen NV. An Evaluation of Programmatic Community-Based Chest X-ray Screening for Tuberculosis in Ho Chi Minh City, Vietnam. Trop Med Infect Dis. 2020 Dec 10;5(4):185. doi: 10.3390/tropicalmed5040185.

Reference Type: BACKGROUND

PMID: 33321696 (View on PubMed)

Other Identifiers

EVALUATE

Identifier Type: -

Identifier Source: org_study_id