Tuberculosis Screening

Purpose

Screen detection of tuberculosis on chest radiograph, in asymptomatic adults

Tag(s)

 

Panel

Thoracic

Define-AI ID

08190005

Originator

Eric J. Stern

Panel Chair

Eric J. Stern

Panel Reviewers

Thoracic Panel

License

Creative Commons 4.0

Status

Published

Clinical Implementation


Value Proposition

The value proposition is well stated by the World Health Organization publication: Chest radiography in tuberculosis detection – summary of current WHO recommendations and guidance on programmatic approaches:

“Systematic screening for active pulmonary TB is defined as the “systematic identification of people with suspected active TB in a predetermined target group, using tests, examinations or other procedures that can be applied rapidly”. Unlike the evaluation of those who actively seek care for respiratory symptoms (see Tuberculosis, Triage), the systematic screening of individuals for TB is typically initiated by a provider and offered in a systematic way to an apparently healthy target group that has been determined to have a high risk of TB.

Systematic screening outside health facilities – such as in the community or in special institutions such as prisons or shelters for homeless people – is often labelled active case finding, which refers to a provider initiated approach that actively reaches outside the health services. Such screening can help find prevalent cases of TB in the community that might otherwise go undiagnosed and untreated. It often requires screening a large number of people who do not have TB. Costs can be high, and the risk of a false positive diagnosis is high when TB prevalence in the screened group is low or moderate (4). Therefore, choosing an accurate screening algorithm is critical, and there are specific considerations involved, including how well the screening and diagnostic tools perform in the population to be screened, the tradeoff between risks and benefits to the person being screened, the ability of the screening algorithms to detect TB without risking overdiagnosis, and the feasibility and costs.” [1]

The chest radiography (CXR) has high sensitivity for pulmonary TB and thus is a valuable tool to identify TB as a differential diagnosis for patients, especially when the radiograph is interpreted to identify any abnormality that is consistent with TB. However, many CXR abnormalities that are consistent with pulmonary TB are seen also in several other lung diseases, often with significant intra- and interobserver variation in interpretations, which can lead to both overdiagnosis and underdiagnosis.

Narrative(s)

In the specific context of a TB prevalence survey to determine the population prevalence of TB, screening is applied to identify individuals who should undergo bacteriological examinations. CXR is the most sensitive screening tool for identifying those survey participants with a high probability of having TB. For diagnosis, combining CXR and symptom checklists for screening (with, typically, a positive result in either category being sufficient to warrant further testing) with culture or an alternative bacteriological test with high sensitivity (such as the Xpert MTB/RIF assay), will generate the most accurate prevalence estimate for bacteriologically positive TB (the objective of a TB prevalence survey). CXR should, therefore, be used for all participants in a survey, regardless of their symptoms or risk markers.

Workflow Description

Image obtained from modality and sent to PACS (or mini-PACS) and the AI engine. Image analyzed by engine. System detects and characterizes exam for suspected tuberculosis. An alert message is sent to PACS from the engine with the information, and identification, and graphic highlighting abnormalities. Cases in which AI has detected active TB are flagged and prioritized for expedited reading in worklist.

Considerations for Dataset Development


Procedures(s): {XRAY, Chest}

View(s): {AP, PA only, PA/Lat} (supplementary Apical Lordotic or decubitus views}

Sex at Birth:
{Male, Female}

History: {asymptomatic}

Comorbidities:
{pleural fluid (including air/fluid levels), other lung disease (eg. bullous emphysema, malignancy, left-sided congestive heart failure, pulmonary edema, prior chest surgery, prior lung injury, sarcoidosis, nontuberculous mycobacterial infection, apical radiation fibrosis, chronic aspergillosis, HIV}

Lung Tissue Involvement: {right, left, bilateral} {Distribution: upper, middle, lower, diffuse, segmental or lobar} {cavitary, micronodular, bronchocentric nodules, nodular, calcifications, linear scarring}

Other abnormalities: {pleural effusion, pleural calcification, tracheal deviation, lymphadenopathy, lobar collapse, consolidation, extrathoracic disease}

Disease prevalence: {popoulation demographics and disease prevalence within population}

Technical Specifications


Inputs

DICOM Study

Procedure

XRAY, Chest

Views

PA, AP, PA/Lat, apical lordotic, lateral decubitus

Data Type

DICOM

Modality

XRAY

Body Region

Chest

Anatomic Focus

Lung

Pharmaceutical

N/A

Scenario

N/A

 

Primary Outputs

Tuberculosis Detection

RadElement ID

 

Definition

Detection of tuberculosis in symptomatic adult patient

Data Type

Categorical

Value Set

0-Unknown

1-Tuberculosis present

2-Tuberculosis absent

Units

N/A

 

Secondary Outputs

Probability of Tuberculosis

RadElement ID

 

Definition

Probability of tuberculosis

Data Type

Numerical

Value Set

[0,1]

0-Tuberculosis absent

1-Tuberculosis present

Units

N/A

Reference


1. Chest radiography in tuberculosis detection – summary of current WHO recommendations and guidance on programmatic approaches. I. World Health Organization. ISBN 978 92 4 151150 6

Reference


1. Chest radiography in tuberculosis detection – summary of current WHO recommendations and guidance on programmatic approaches. I. World Health Organization. ISBN 978 92 4 151150 6

Public Commenting


Use cases are meant to be a primary vehicle for distributing clinical information to the developer community. They pinpoint precise scenarios within radiology workflows where potential automation could add noticeable value and establish standards for interpreting and passing corresponding common data elements. Implementing effective standards requires the perspective from all stakeholders. So to that end, we encourage your feedback on use cases.

To submit comments, please email DSIUseCases@acr.org with the use case title(s) and relevant comments by January 1, 2019. If more convenient, you may also download this use case and comment directly on the PDF. Just attach the PDF copy on the email.