---
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
widget:
- text: "SAMPLE 32,441 archived appendix samples fixed in formalin and embedded in paraffin and tested for the presence of abnormal prion protein (PrP)."

model-index:
- name: PubMedBert-PubMed200kRCT
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# PubMedBert-PubMed200kRCT

This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the [PubMed200kRCT](https://github.com/Franck-Dernoncourt/pubmed-rct/tree/master/PubMed_200k_RCT) dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2833
- Accuracy: 0.8942

## Model description

More information needed

## Intended uses & limitations

The model can be used for text classification tasks of Randomized Controlled Trials that does not have any structure. The text can be classified as one of the following:
* BACKGROUND
* CONCLUSIONS
* METHODS
* OBJECTIVE
* RESULTS

The model can be directly used like this:

```python
from transformers import TextClassificationPipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model = AutoModelForSequenceClassification.from_pretrained("pritamdeka/PubMedBert-PubMed200kRCT")
tokenizer = AutoTokenizer.from_pretrained("pritamdeka/PubMedBert-PubMed200kRCT")
pipe = TextClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True)
pipe("Treatment of 12 healthy female subjects with CDCA for 2 days resulted in increased BAT activity.")
```
Results will be shown as follows:

```python
[[{'label': 'BACKGROUND', 'score': 0.0028450002428144217},
  {'label': 'CONCLUSIONS', 'score': 0.2581048607826233},
  {'label': 'METHODS', 'score': 0.015086210332810879},
  {'label': 'OBJECTIVE', 'score': 0.0016815993003547192},
  {'label': 'RESULTS', 'score': 0.7222822904586792}]]
```

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2.0

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.3604        | 0.14  | 5000  | 0.3162          | 0.8821   |
| 0.3326        | 0.29  | 10000 | 0.3112          | 0.8843   |
| 0.3293        | 0.43  | 15000 | 0.3044          | 0.8870   |
| 0.3246        | 0.58  | 20000 | 0.3040          | 0.8871   |
| 0.32          | 0.72  | 25000 | 0.2969          | 0.8888   |
| 0.3143        | 0.87  | 30000 | 0.2929          | 0.8903   |
| 0.3095        | 1.01  | 35000 | 0.2917          | 0.8899   |
| 0.2844        | 1.16  | 40000 | 0.2957          | 0.8886   |
| 0.2778        | 1.3   | 45000 | 0.2943          | 0.8906   |
| 0.2779        | 1.45  | 50000 | 0.2890          | 0.8935   |
| 0.2752        | 1.59  | 55000 | 0.2881          | 0.8919   |
| 0.2736        | 1.74  | 60000 | 0.2835          | 0.8944   |
| 0.2725        | 1.88  | 65000 | 0.2833          | 0.8942   |


### Framework versions

- Transformers 4.18.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.6

## Citing & Authors

<!--- Describe where people can find more information -->

If you use the model kindly cite the following work

```
@inproceedings{deka2022evidence,
  title={Evidence Extraction to Validate Medical Claims in Fake News Detection},
  author={Deka, Pritam and Jurek-Loughrey, Anna and others},
  booktitle={International Conference on Health Information Science},
  pages={3--15},
  year={2022},
  organization={Springer}
}
```