Fig. 4From: Machine learning algorithms for systematic review: reducing workload in a preclinical review of animal studies and reducing human screening errorPerformance of approach 1 after error analysis. The updated approach is retrained on the corrected training set after error analysis correction. Performance on both the original and the updated approach is measured on the corrected validation set (with error analysis correction). For the interactive version of this plot with the ability to read off performance at all cut-off values, see code and data at https://github.com/abannachbrown/The-use-of-text-mining-and-machine-learning-algorithms-in-systematic-reviews/blob/master/error-analysis-plot.htmlBack to article page