create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: nl
|
| 3 |
+
license: mit
|
| 4 |
+
tag_0: Text Classification
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# A-PROOF ICF-domains Classification
|
| 8 |
+
|
| 9 |
+
## Description
|
| 10 |
+
|
| 11 |
+
A fine-tuned multi-label classification model that detects 9 [WHO-ICF](https://www.who.int/standards/classifications/international-classification-of-functioning-disability-and-health) domains in clinical text in Dutch. The model is based on a pre-trained Dutch medical language model [link to be added](), a RoBERTa model, trained from scratch on clinical notes of the Amsterdam UMC.
|
| 12 |
+
|
| 13 |
+
## ICF domains
|
| 14 |
+
The model can detect 9 domains, which were chosen due to their relevance to recovery from COVID-19:
|
| 15 |
+
|
| 16 |
+
ICF code | Domain | name in repo
|
| 17 |
+
---|---|---
|
| 18 |
+
b1300 | Energy level | ENR
|
| 19 |
+
b140 | Attention functions | ATT
|
| 20 |
+
b152 | Emotional functions | STM
|
| 21 |
+
b440 | Respiration functions | ADM
|
| 22 |
+
b455 | Exercise tolerance functions | INS
|
| 23 |
+
b530 | Weight maintenance functions | MBW
|
| 24 |
+
d450 | Walking | FAC
|
| 25 |
+
d550 | Eating | ETN
|
| 26 |
+
d840-d859 | Work and employment | BER
|
| 27 |
+
|
| 28 |
+
## Intended uses and limitations
|
| 29 |
+
TBD
|
| 30 |
+
|
| 31 |
+
## Training data
|
| 32 |
+
TBD
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
TBD
|
| 36 |
+
|
| 37 |
+
## Evaluation results
|
| 38 |
+
TBD
|
| 39 |
+
|
| 40 |
+
## Authors and references
|
| 41 |
+
TBD
|