TABLE 9.
Author | Identification | NLP model | Embeddings and Corpus | F1-score [%] |
Cohen et al. (101) | Candidates for surgery for drug-resistant epilepsy | Naïve Bayes | ∼6,300 patients’ EHR | 82 |
Sung et al. (103) | Intravenous thrombolytic therapy candidates | MetaMap-based | 234 clinical notes | 98.6 |
NLP, natural language processing; EHR, electronic health record.