2014
A study was published on the use of CAD4TB in Tanzania. CAD4TB was evaluated on chest radiographs of patients with symptoms suggestive of pulmonary tuberculosis enrolled in two cohort studies in Tanzania. CAD4TB was significantly more accurate for discriminating smear-positive cases against non-TB patients than for smear-negative cases. It also showed that CAD4TB significantly outperformed the clinical officer but did not reach the accuracy of the expert reader. Note that the study used a substantially older version of CAD4TB than the currently available one.
2015
Another study was published using CAD4TB, examining CAD4TB as a tool to aid in screening for pulmonary tuberculosis in a Tanzanian prison. The study demonstrated that CAD4TB accurately evaluates chest X-rays from a predominantly asymptomatic prison population, with diagnostic performance inferior to that of expert readers but comparable to that of local readers. Note that the study used a significantly older version of CAD4TB than the currently available one.
2024
A study on the use of CAD4TB in mobile clinics in Tanzania demonstrated the solution’s efficiency in quickly analyzing cases compared to manual readings by radiologists. This efficiency is particularly beneficial in resource-limited settings, as it reduces reliance on the costly GeneXpert test. Additionally, the study recommended a specific threshold score for CAD4TB tailored to Tanzania’s needs.
