Model Description

ClinicalMobileBERT-i2b2-2010 is a fine-tuned version of the ClinicalMobileBERT model on the i2b2-2010 dataset for clinical Named Entity Recognition (NER). The model specialises in recognising entities from three categories: problems, treatments, and tests. The initialisation was conducted using the pre-trained checkpoints of the ClinicalMobileBERT model available on Huggingface.

Architecture

The architecture of this model is identical to ClinicalMobileBERT. The model was fine-tuned on the i2b2-2010 dataset for the task of clinical NER. The fine-tuning process targeted three categories of entities: problems, treatments, and tests. The model has around 25M parameters.

Use Cases

This model is useful for NLP tasks in the clinical domain that require identification and classification of problems, treatments, and tests.

Citation

If you use this model, please consider citing the following paper:

@article{rohanian2023lightweight,
  title={Lightweight transformers for clinical natural language processing},
  author={Rohanian, Omid and Nouriborji, Mohammadmahdi and Jauncey, Hannah and Kouchaki, Samaneh and Nooralahzadeh, Farhad and Clifton, Lei and Merson, Laura and Clifton, David A and ISARIC Clinical Characterisation Group and others},
  journal={Natural Language Engineering},
  pages={1--28},
  year={2023},
  publisher={Cambridge University Press}
}

Support

If this model helps your work, you can keep the project running with a one-off or monthly contribution:
https://github.com/sponsors/nlpie-research