The model is an NER LLM algorithm that can classify each word in a text into different clinical categories.

The base pretrained model is GatorTronS which was trained on billions of words in various clinical texts (https://huggingface.co/UFNLP/gatortronS). Then using the NCBI Disease dataset (https://www.sciencedirect.com/science/article/pii/S1532046413001974?via%3Dihub), I fine-tuned the model for NER task in which the model can classify each word in a text into one of the categories ['no disease', 'disease', 'disease-continue'].

The github code associated with the model can be found here: https://github.com/longluu/LLM-NER-clinical-text.

This dataset contains the disease name and concept annotations of the NCBI disease corpus, a collection of 793 PubMed abstracts fully annotated at the mention and concept level to serve as a research resource for the biomedical natural language processing community. Details are here https://www.sciencedirect.com/science/article/pii/S1532046413001974?via%3Dihub.

The preprocessed data for LLM training can be found here https://huggingface.co/datasets/ncbi_disease.

The hyperparameters are --batch_size 24 --num_train_epochs 5 --learning_rate 5e-5 --weight_decay 0.01

The model was trained and validated on train and validation sets. Then it was tested on a separate test set. Note that some concepts in the test set were not available in the train and validatin sets.

Here we use several metrics for classification tasks including macro-average F1, precision, recall and Matthew correlation.

{'f1': 0.876008064516129, 'precision': 0.9052083333333333, 'recall': 0.8486328125}

Feel free to reach out to me at thelong20.4@gmail.com if you have any question or suggestion.