|
Download README.md from PredLMed/ICD2BERT: direct link, hf CLI and curl.
- Browser
- Download file 1.75 kB
-
https://huggingface.co/PredLMed/ICD2BERT/resolve/main/README.md
- Command line
-
hf download hf://PredLMed/ICD2BERT/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/PredLMed/ICD2BERT/resolve/main/README.md
1.75 kB
| license: gpl-3.0 | |
| pipeline_tag: feature-extraction | |
| base_model: | |
| - google-bert/bert-base-uncased | |
| extra_gated_prompt: "Access requires a verified CITI training certificate using the same process outlined by PhysioNet (see https://physionet.org/about/citi-course/). | |
| Please complete the 'Data or Specimens Only Research' course and please provide proof via the verification URL, which takes the form https://www.citiprogram.org/verify/?XXXXXX. | |
| You agree to not use the model to conduct experiments that cause harm to human subjects." | |
| extra_gated_fields: | |
| Full Name: text | |
| Email: text | |
| Affiliation: text | |
| CITI Certification Verification URL: text | |
| # ICD2BERT | |
| Pretrained model on electronic health records on the MIMIC-IV dataset using a masked language modeling (MLM) objective. | |
| # Quickstart | |
| ```python | |
| from transformers import BertForMaskedLM, BertTokenizer | |
| model = BertForMaskedLM.from_pretrained( | |
| "PredLMed/ICD2BERT", | |
| subfolder="model", | |
| ) | |
| tokenizer = BertTokenizer.from_pretrained( | |
| "PredLMed/ICD2BERT", | |
| subfolder="tokenizer", | |
| ) | |
| def encode(icd_sequence: str, model: BertForMaskedLM, tokenizer: BertTokenizer): | |
| inputs = tokenizer( | |
| icd_sequence, | |
| return_tensors="pt", | |
| truncation=True, | |
| padding=True, | |
| max_length=512, | |
| ) | |
| outputs = model(**inputs, output_hidden_states=True) | |
| embedding = outputs.hidden_states[-1][:, 0, :] | |
| return embedding | |
| icd_sequence = ( | |
| [ | |
| "d_10_T1404 d_10_I82532 d_10_Z7901 d_10_Z86711 d_10_S0628 d_10_I872 d_10_F329 d_10_E669 d_10_Z6834 d_10_Z590 ", | |
| "p_09_5122 d_09_57400 d_09_V6441 d_09_78829 d_09_53081 ", | |
| ], | |
| ) | |
| embedding = encode(icd_sequence, model=model, tokenizer=tokenizer) | |
| print(embedding[0]) | |
| print(embedding[1]) | |
| ``` |