fix file locations

README.md

@@ -1,3 +1,87 @@
----
-license: mit
----
+---
+language:
+  - en
+thumbnail: "https://www.onebraveidea.org/wp-content/uploads/2019/07/OBI-Logo-Website.png"
+tags:
+- deidentification
+- medical notes
+- ehr
+- phi
+datasets:
+- I2B2
+metrics:
+- F1
+- Recall
+- AUC
+widget:
+- text: "Physician Discharge Summary Admit date: 10/12/1982 Discharge date: 10/22/1982 Patient Information Jack Reacher, 54 y.o. male (DOB = 1/21/1928)."
+- text: "Home Address: 123 Park Drive, San Diego, CA, 03245. Home Phone: 202-555-0199 (home)."
+- text: "Hospital Care Team Service: Orthopedics Inpatient Attending: Roger C Kelly, MD Attending phys phone: (634)743-5135 Discharge Unit: HCS843 Primary Care Physician: Hassan V Kim, MD 512-832-5025."
+license: mit
+---
+
+
+# Model Description
+
+* A ClinicalBERT [[Alsentzer et al., 2019]](https://arxiv.org/pdf/1904.03323.pdf) model fine-tuned for de-identification of medical notes.
+* Sequence Labeling (token classification): The model was trained to predict protected health information (PHI/PII) entities (spans). A list of protected health information categories is given by [HIPAA](https://www.hhs.gov/hipaa/for-professionals/privacy/laws-regulations/index.html).
+* A token can either be classified as non-PHI or as one of the 11 PHI types. Token predictions are aggregated to spans by making use of BILOU tagging.
+* The PHI labels that were used for training and other details can be found here: [Annotation Guidelines](https://github.com/obi-ml-public/ehr_deidentification/blob/master/AnnotationGuidelines.md)
+* More details on how to use this model, the format of data and other useful information is present in the GitHub repo: [Robust DeID](https://github.com/obi-ml-public/ehr_deidentification).
+
+
+# How to use
+
+* A demo on how the model works (using model predictions to de-identify a medical note) is on this space: [Medical-Note-Deidentification](https://huggingface.co/spaces/obi/Medical-Note-Deidentification).
+* Steps on how this model can be used to run a forward pass can be found here: [Forward Pass](https://github.com/obi-ml-public/ehr_deidentification/tree/master/steps/forward_pass)
+* In brief, the steps are:
+    * Sentencize (the model aggregates the sentences back to the note level) and tokenize the dataset.
+    * Use the predict function of this model to gather the predictions (i.e., predictions for each token).
+    * Additionally, the model predictions can be used to remove PHI from the original note/text.
+    
+    
+# Dataset
+
+* The I2B2 2014 [[Stubbs and Uzuner, 2015]](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4978170/) dataset was used to train this model.
+
+|           | I2B2                  |            |  I2B2                |            |
+| --------- | --------------------- | ---------- | -------------------- | ---------- |
+|           | TRAIN SET - 790 NOTES |            | TEST SET - 514 NOTES |            |
+| PHI LABEL | COUNT                 | PERCENTAGE | COUNT                | PERCENTAGE |
+| DATE      | 7502                  | 43.69      | 4980                 | 44.14      |
+| STAFF     | 3149                  | 18.34      | 2004                 | 17.76      |
+| HOSP      | 1437                  | 8.37       | 875                  | 7.76       |
+| AGE       | 1233                  | 7.18       | 764                  | 6.77       |
+| LOC       | 1206                  | 7.02       | 856                  | 7.59       |
+| PATIENT   | 1316                  | 7.66       | 879                  | 7.79       |
+| PHONE     | 317                   | 1.85       | 217                  | 1.92       |
+| ID        | 881                   | 5.13       | 625                  | 5.54       |
+| PATORG    | 124                   | 0.72       | 82                   | 0.73       |
+| EMAIL     | 4                     | 0.02       | 1                    | 0.01       |
+| OTHERPHI  | 2                     | 0.01       | 0                    | 0          |
+| TOTAL     | 17171                 | 100        | 11283                | 100        |
+
+
+# Training procedure
+
+* Steps on how this model was trained can be found here: [Training](https://github.com/obi-ml-public/ehr_deidentification/tree/master/steps/train). The "model_name_or_path" was set to: "emilyalsentzer/Bio_ClinicalBERT".
+    * The dataset was sentencized with the en_core_sci_sm sentencizer from spacy.
+    * The dataset was then tokenized with a custom tokenizer built on top of the en_core_sci_sm tokenizer from spacy.
+    * For each sentence we added 32 tokens on the left (from previous sentences) and 32 tokens on the right (from the next sentences).
+    * The added tokens are not used for learning - i.e, the loss is not computed on these tokens - they are used as additional context.
+    * Each sequence contained a maximum of 128 tokens (including the 32 tokens added on). Longer sequences were split.
+    * The sentencized and tokenized dataset with the token level labels based on the BILOU notation was used to train the model.
+    * The model is fine-tuned from a pre-trained RoBERTa model.
+    
+* Training details:
+    * Input sequence length: 128
+    * Batch size: 32
+    * Optimizer: AdamW 
+    * Learning rate: 4e-5
+    * Dropout: 0.1
+    
+# Results
+
+# Questions?
+
+Post a Github issue on the repo: [Robust DeID](https://github.com/obi-ml-public/ehr_deidentification).

config.json

@@ -0,0 +1,118 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AGE",
+    "1": "B-DATE",
+    "2": "B-EMAIL",
+    "3": "B-HOSP",
+    "4": "B-ID",
+    "5": "B-LOC",
+    "6": "B-OTHERPHI",
+    "7": "B-PATIENT",
+    "8": "B-PATORG",
+    "9": "B-PHONE",
+    "10": "B-STAFF",
+    "11": "I-AGE",
+    "12": "I-DATE",
+    "13": "I-EMAIL",
+    "14": "I-HOSP",
+    "15": "I-ID",
+    "16": "I-LOC",
+    "17": "I-OTHERPHI",
+    "18": "I-PATIENT",
+    "19": "I-PATORG",
+    "20": "I-PHONE",
+    "21": "I-STAFF",
+    "22": "L-AGE",
+    "23": "L-DATE",
+    "24": "L-EMAIL",
+    "25": "L-HOSP",
+    "26": "L-ID",
+    "27": "L-LOC",
+    "28": "L-OTHERPHI",
+    "29": "L-PATIENT",
+    "30": "L-PATORG",
+    "31": "L-PHONE",
+    "32": "L-STAFF",
+    "33": "O",
+    "34": "U-AGE",
+    "35": "U-DATE",
+    "36": "U-EMAIL",
+    "37": "U-HOSP",
+    "38": "U-ID",
+    "39": "U-LOC",
+    "40": "U-OTHERPHI",
+    "41": "U-PATIENT",
+    "42": "U-PATORG",
+    "43": "U-PHONE",
+    "44": "U-STAFF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AGE": 0,
+    "B-DATE": 1,
+    "B-EMAIL": 2,
+    "B-HOSP": 3,
+    "B-ID": 4,
+    "B-LOC": 5,
+    "B-OTHERPHI": 6,
+    "B-PATIENT": 7,
+    "B-PATORG": 8,
+    "B-PHONE": 9,
+    "B-STAFF": 10,
+    "I-AGE": 11,
+    "I-DATE": 12,
+    "I-EMAIL": 13,
+    "I-HOSP": 14,
+    "I-ID": 15,
+    "I-LOC": 16,
+    "I-OTHERPHI": 17,
+    "I-PATIENT": 18,
+    "I-PATORG": 19,
+    "I-PHONE": 20,
+    "I-STAFF": 21,
+    "L-AGE": 22,
+    "L-DATE": 23,
+    "L-EMAIL": 24,
+    "L-HOSP": 25,
+    "L-ID": 26,
+    "L-LOC": 27,
+    "L-OTHERPHI": 28,
+    "L-PATIENT": 29,
+    "L-PATORG": 30,
+    "L-PHONE": 31,
+    "L-STAFF": 32,
+    "O": 33,
+    "U-AGE": 34,
+    "U-DATE": 35,
+    "U-EMAIL": 36,
+    "U-HOSP": 37,
+    "U-ID": 38,
+    "U-LOC": 39,
+    "U-OTHERPHI": 40,
+    "U-PATIENT": 41,
+    "U-PATORG": 42,
+    "U-PHONE": 43,
+    "U-STAFF": 44
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b7a2d5f26e5f7adbc6d438398302c38c4686e710bbd93473a1e5c61eafcafa
+size 431325444

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcdae29c075ca986684a5d544cf46ba01ceed5d2773d0213f842a48059cd5dc
+size 101

onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bbde06e370439cd0b9cf6759bd334131ab42aff249b97f0d869a7636df57a1
+size 108643070

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db94e29d75410d7b5330b67a8a2e9129bf7176ba66f235d6a89974fd0391012f
+size 99

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58a01284892fc12bfba83178a850b2064bec74ef2fbe03faac8de8a4ad5efa0
+size 102

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90bbde06e370439cd0b9cf6759bd334131ab42aff249b97f0d869a7636df57a1
+size 108643070

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d082c15d1e71120baa00e28023fe09e9e37484b4e8acf0770599cadd1af0c71
+size 108643102

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842d9f0d394c71528bb73f87748c580a9a3ea82973a18e0871fd579e3eb21c6b
+size 431100529

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "do_basic_tokenize": true, "never_split": null}