Search alternatives:
update algorithm » data algorithms (Expand Search), ipca algorithm (Expand Search), monte algorithm (Expand Search)
complement pass » complement past (Expand Search), complement 5a (Expand Search)
relevant update » relevant data (Expand Search), relevant rate (Expand Search)
pass algorithm » lasso algorithm (Expand Search), pso algorithm (Expand Search), rast algorithm (Expand Search)
level finding » novel findings (Expand Search), review finding (Expand Search), level coding (Expand Search)
update algorithm » data algorithms (Expand Search), ipca algorithm (Expand Search), monte algorithm (Expand Search)
complement pass » complement past (Expand Search), complement 5a (Expand Search)
relevant update » relevant data (Expand Search), relevant rate (Expand Search)
pass algorithm » lasso algorithm (Expand Search), pso algorithm (Expand Search), rast algorithm (Expand Search)
level finding » novel findings (Expand Search), review finding (Expand Search), level coding (Expand Search)
-
1
-
2
-
3
-
4
-
5
-
6
-
7
-
8
-
9
-
10
-
11
-
12
-
13
-
14
Data Sheet 1_Clinical validation of an artificial intelligence algorithm for classifying tuberculosis and pulmonary findings in chest radiographs.pdf
Published 2025“…</p>Results<p>In the internal validation, the Lung Abnormality and Tuberculosis models achieved an AUC of 0.94, while the Radiological Findings model yielded a mean AUC of 0.84. During the external validation, utilizing the ground truth generated by board-certified thoracic radiologists, the algorithm achieved better sensitivity in 6 out of 11 classes than physicians with varying experience levels. …”
-
15
-
16
-
17
-
18
-
19
-
20