Published on Authors of this article:. Background: Tuberculosis TB was the leading infectious cause of mortality globally prior to COVID and chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease.
The conventional experts reading has substantial within- and between-observer variability, indicating poor reliability of human readers. Substantial efforts have been made in utilizing various artificial intelligence—based algorithms to address the limitations of human reading of chest radiographs for diagnosing TB. We independently screened, reviewed, and assessed all available records and included 47 studies that met the inclusion criteria in this SLR.
We also performed the risk of bias assessment using Quality Assessment of Diagnostic Accuracy Studies version 2 QUADAS-2 and meta-analysis of 10 included studies that provided confusion matrix results.
Based on data from 10 studies that provided confusion matrix results, we estimated the pooled sensitivity and specificity of ML and DL methods to be 0. From the risk of bias assessment, 17 studies were regarded as having unclear risks for the reference standard aspect and 6 studies were regarded as having unclear risks for the flow and timing aspect. Only 2 included studies had built applications based on the proposed solutions. Future studies need to pay a close attention on 2 aspects of risk of bias, namely, the reference standard and the flow and timing aspects.
Many people with TB do not have symptoms and, therefore, chest radiography has an important role in the detection, and subsequent diagnosis, of patients with this disease [ 4 , 5 ]. Traditionally, chest radiographs have required expert clinicians usually radiologists or chest physicians to interpret radiographic images, but this method is expensive and, furthermore, there is substantial within- and between-observer variability, indicating poor reliability of human readers [ 6 ].
