Table 1.
Descriptive statistics of the challenge data set.
| Corpus information, annotation type, and annotation category | 2019 n2c2 family history challenge corpus | |||||
| Training set | Test set | |||||
| Number of notes | 99 | 117 | ||||
| Entity-level annotation |
|
|
||||
|
|
Concept |
|
|
|||
|
|
|
Family members | 803 | N/A | ||
| Observations | 978 | N/A | ||||
| Living status | 415 | N/A | ||||
| Document-level annotation |
|
|
||||
|
|
Concept |
|
|
|||
|
|
|
Family members | 667 | 638 | ||
| Observations | 930 | 983 | ||||
| Relation |
|
|
||||
|
|
Family members—observations | 740 | 755 | |||
| Family members—living status | 376 | 349 | ||||