Title | ||
---|---|---|
Inter-labeler and intra-labeler variability of condition severity classification models using active and passive learning methods. |
Abstract | ||
---|---|---|
•AL methods produce smoother Intra-labeler learning curves during the training phase.•AL methods result in almost half of the mean Inter-labeler AUC standard deviation.•The consensus label resulted in an AUC that was at least as high as that of the gold standard label.•The consensus label resulted in an AUC that was higher than the mean AUC of any random labeler.•AL methods reduce Inter-labeler performance variance, and the dependence on a particular labeler. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.artmed.2017.03.003 | Artificial Intelligence in Medicine |
Keywords | Field | DocType |
CAESAR,CAESAR-ALE,EHR,AL,SVM,VS,SNOMED-CT,ICD-9,SVM-Margin,Exploitation,Combination_XA | Data mining,Condition severity,Active learning,Computer science,Support vector machine,Artificial intelligence,Learning curve,Statistics,Passive learning,Standard deviation,Machine learning,Version space | Journal |
Volume | Issue | ISSN |
81 | C | 0933-3657 |
Citations | PageRank | References |
6 | 0.45 | 33 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nir Nissim | 1 | 199 | 19.42 |
Yuval Shahar | 2 | 1974 | 214.22 |
Yuval Elovici | 3 | 2583 | 204.53 |
George Hripcsak | 4 | 1493 | 160.86 |
Robert Moskovitch | 5 | 729 | 39.62 |