Finland (Finnish) | Sweden (Swedish) | |
---|---|---|
Health records | 514 (496 unique patients) | 379 (333 unique patients) |
Daily documents (i.e., daily notes about a patient) | 5,915 (17,103 shifts) | 4,700 |
Tokens | 1,227,909 | 1,959,271 |
Types (i.e., unique tokens) before/after FinCG/GTA | 63,328 / 38,649 | – / 41,883 |
Tokens per patient / Tokens per daily document | ||
Minimum | 540 / 0 | 92 / 5 |
Maximum | 14,118 / 915 | 36,830 / 9,389 |
Average | 2,389 / 208 | 5,169 / 417 |
Standard deviation | 1,635 / 87 | 5,271 / 239 |
The number of bigrams | 368,166 (275,205 after FinCG) | 469,455 (344,127 after GTA) |
The number of trigrams | 745,407 (356,307 after FinCG) | 1,064,944 (905,539 after GTA) |
Proportion of pronouns after FinCG/GTA | < 1% | 2% |
Proportion of nouns after FinCG/GTA | 7% | 27% |
Proportion of verbs after FinCG/GTA | 11% | 11% |