# Clinical Concept Extraction on i2b2 2012 (test) Source: [Clinical Concept Extraction on i2b2 2012 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:42:25.920Z Evaluation of clinical concept extraction performance on the test split of the i2b2 2012 dataset, measured using metrics like Exact F1. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Clinical concept extraction | | Dataset (including any stated split) | i2b2 2012 (test) | | Metric | Exact F1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 13 of 13 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Exact F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact F1 | Result date | Report paper | | --- | --- | --- | --- | | BERTlarge | 80.91 | Not recorded | 68fa663c1e209131cea0f0eb | | ELMo | 80.5 | Not recorded | 68fa663c1e209131cea0f0eb | | BERTbase | 80.34 | Not recorded | 68fa663c1e209131cea0f0eb | | BERTlarge | 78.14 | Not recorded | 68fa663c1e209131cea0f0eb | | BioBERT | 77.77 | Not recorded | 68fa663c1e209131cea0f0eb | | BERTbase | 76.62 | Not recorded | 68fa663c1e209131cea0f0eb | | ELMo | 76.61 | Not recorded | 68fa663c1e209131cea0f0eb | | GloVe | 75.27 | Not recorded | 68fa663c1e209131cea0f0eb | | word2vec | 75.09 | Not recorded | 68fa663c1e209131cea0f0eb | | GloVe | 74.95 | Not recorded | 68fa663c1e209131cea0f0eb | | fastText | 74.83 | Not recorded | 68fa663c1e209131cea0f0eb | | fastText | 73.24 | Not recorded | 68fa663c1e209131cea0f0eb | | word2vec | 71.07 | Not recorded | 68fa663c1e209131cea0f0eb | ### BERTlarge Exact F1: 80.91. Result ID: 698ce4bb8b517eb4331d7a1f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### ELMo Exact F1: 80.5. Result ID: 698ce4bb8b517eb4331d7a1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### BERTbase Exact F1: 80.34. Result ID: 698ce4bb8b517eb4331d7a1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### BERTlarge Exact F1: 78.14. Result ID: 698ce4bb8b517eb4331d7a1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### BioBERT Exact F1: 77.77. Result ID: 698ce4bb8b517eb4331d7a20. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### BERTbase Exact F1: 76.62. Result ID: 698ce4bb8b517eb4331d7a1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### ELMo Exact F1: 76.61. Result ID: 698ce4bb8b517eb4331d7a1a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### GloVe Exact F1: 75.27. Result ID: 698ce4bb8b517eb4331d7a17. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### word2vec Exact F1: 75.09. Result ID: 698ce4bb8b517eb4331d7a15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### GloVe Exact F1: 74.95. Result ID: 698ce4bb8b517eb4331d7a16. [Reporting paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### fastText Exact F1: 74.83. Result ID: 698ce4bb8b517eb4331d7a19. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Corpus":"MIMIC"}. This record does not assert independent reproduction. ### fastText Exact F1: 73.24. Result ID: 698ce4bb8b517eb4331d7a18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. ### word2vec Exact F1: 71.07. Result ID: 698ce4bb8b517eb4331d7a14. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pre-training Corpus":"General"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.