Skip to main content

Table 6 AMI dataset average ROC AUROC scores with an importance cutoff of 40

From: Leveraging medical context to recommend semantically similar terms for chart reviews

Model AUROC
Medical-context vector space features word2vec features
Logistic regression 0.80** 0.73
Random forest 0.75*** 0.56
Support vector machine 0.75* 0.71
  1. ***p < 0.001, **p < 0.01, *p < 0.05