icf-levels-ins / README.md
CLTL's picture
Create README.md
language: nl
license: mit
pipeline_tag: text-classification
inference: false

Regression Model for Exercise Tolerance Functioning Levels (ICF b455)


A fine-tuned regression model that assigns a functioning level to Dutch sentences describing exercise tolerance functions. 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. To detect sentences about exercise tolerance functions in clinical text in Dutch, use the icf-domains classification model.

Functioning levels

Level Meaning
5 MET>6. Can tolerate jogging, hard exercises, running, climbing stairs fast, sports.
4 4≤MET≤6. Can tolerate walking / cycling at a brisk pace, considerable effort (e.g. cycling from 16 km/h), heavy housework.
3 3≤MET<4. Can tolerate walking / cycling at a normal pace, gardening, exercises without equipment.
2 2≤MET<3. Can tolerate walking at a slow to moderate pace, grocery shopping, light housework.
1 1≤MET<2. Can tolerate sitting activities.
0 0≤MET<1. Can physically tolerate only recumbent activities.

The predictions generated by the model might sometimes be outside of the scale (e.g. 5.2); this is normal in a regression model.

Intended uses and limitations

  • The model was fine-tuned (trained, validated and tested) on medical records from the Amsterdam UMC (the two academic medical centers of Amsterdam). It might perform differently on text from a different hospital or text from non-hospital sources (e.g. GP records).
  • The model was fine-tuned with the Simple Transformers library. This library is based on Transformers but the model cannot be used directly with Transformers pipeline and classes; doing so would generate incorrect outputs. For this reason, the API on this page is disabled.

How to use

To generate predictions with the model, use the Simple Transformers library:

from simpletransformers.classification import ClassificationModel

model = ClassificationModel(

example = 'kan nog goed traplopen, maar flink ingeleverd aan conditie na Corona'
_, raw_outputs = model.predict([example])
predictions = np.squeeze(raw_outputs)

The prediction on the example is:


The raw outputs look like this:


Training data

  • The training data consists of clinical notes from medical records (in Dutch) of the Amsterdam UMC. Due to privacy constraints, the data cannot be released.
  • The annotation guidelines used for the project can be found here.

Training procedure

The default training parameters of Simple Transformers were used, including:

  • Optimizer: AdamW
  • Learning rate: 4e-5
  • Num train epochs: 1
  • Train batch size: 8

Evaluation results

The evaluation is done on a sentence-level (the classification unit) and on a note-level (the aggregated unit which is meaningful for the healthcare professionals).

Sentence-level Note-level
mean absolute error 0.69 0.61
mean squared error 0.80 0.64
root mean squared error 0.89 0.80

Authors and references


Jenia Kim, Piek Vossen