i2b2
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
i2b2
52.36A_T
44
i2b2 2014
0.582Micro F1 Score
26
I2B2 2010 (test)
0.72Micro F1
24
i2b2 2014 (test)
98.6Precision
20
i2b2 2010 (test)
90.25Exact F1
18
I2B2 Three-site experiment (test)
0.745Strict Micro F1
13
I2B2 Three-site experiment (test)
85.2Strict Micro F1
13
I2B2 Two-site experiment (test)
74.6Strict Micro F1
13
I2B2 Two-site experiment (test)
86.4Strict Micro F1
13
i2b2 2012 (test)
80.91Exact F1
13
i2b2 bert-base-cased (FG-8-PG-2)
56.96At Score
11
i2b2 FG-8-PG-1 bert-base-cased
50.75At Score
11
i2b2 FG-2-PG-2 bert-base-cased
54.84At
11
i2b2 bert-base-cased (FG-1-PG-1)
43.88At Score
11
i2b2
3.36GPT-4 Score
10
I2B2 (test)
64.3Micro-F1
9
i2b2 English 2010
91.8Micro F1
8
i2b2 2009
93.2F1 Score
8
i2b2 Turkish 2010
0.87Micro F1
6
i2b2-10
87.4Micro F1 (span-level)
6
i2b2 2012
80F1 Score
5
i2b2 2006
97.4F1 Score
5
i2b2 (test)
82.31AUROC
4
i2b2 2014 (20% test)
96Precision
4
i2b2-Clinical (test)
69.1Macro F1
3