Biomedical Ner All

🚀 生物醫學命名實體識別模型

這是一個英文命名實體識別模型，可從給定文本語料（如病例報告）中識別生物醫學實體（共107種實體），為生物醫學領域的信息提取提供了有力支持。

🚀 快速開始

本模型可以通過從Hugging Face加載推理API，或者使用transformers庫提供的pipeline對象這兩種方式使用。

✨ 主要特性

• 實體識別能力：能夠識別107種生物醫學實體，適用於病例報告等文本語料。
• 模型基礎：基於distilbert-base-uncased構建。
• 訓練數據集：使用Maccrobat數據集進行訓練，數據集鏈接：https://figshare.com/articles/dataset/MACCROBAT2018/9764942 。
• 碳排放：訓練過程中的碳排放為0.0279399890043426千克。
• 訓練時間：訓練耗時30.16527分鐘。
• 使用的GPU：1 x GeForce RTX 3060 Laptop GPU。

💻 使用示例

基礎用法

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("d4data/biomedical-ner-all")
model = AutoModelForTokenClassification.from_pretrained("d4data/biomedical-ner-all")

pipe = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple") # pass device=0 if using gpu
pipe("""The patient reported no recurrence of palpitations at follow-up 6 months after the ablation.""")

📚 詳細文檔

查看本模型及相應Python庫的講解教程視頻：https://youtu.be/xpiDPdBpS18

📄 許可證

本模型採用Apache-2.0許可證。

👨‍🔬 作者信息

本模型是Deepak John Reji和Shaina Raza開展的“生物醫學領域的人工智能”研究課題的一部分。如果您使用了本項目的代碼、模型或數據集，請在以下倉庫點星支持：

https://github.com/dreji18/Bio-Epidemiology-NER

💗 支持作者

如果您想支持作者，可以點擊下面的按鈕請作者喝咖啡：

測試樣例

以下是一些測試用的文本樣例：

• 示例1：

CASE: A 28-year-old previously healthy man presented with a 6-week history of palpitations.
The symptoms occurred during rest, 2–3 times per week, lasted up to 30 minutes at a time and were associated with dyspnea.
Except for a grade 2/6 holosystolic tricuspid regurgitation murmur (best heard at the left sternal border with inspiratory accentuation), physical examination yielded unremarkable findings.

• 示例2：

A 63-year-old woman with no known cardiac history presented with a sudden onset of dyspnea requiring intubation and ventilatory support out of hospital.
She denied preceding symptoms of chest discomfort, palpitations, syncope or infection.
The patient was afebrile and normotensive, with a sinus tachycardia of 140 beats/min.

• 示例3：

A 48 year-old female presented with vaginal bleeding and abnormal Pap smears.
Upon diagnosis of invasive non-keratinizing SCC of the cervix, she underwent a radical hysterectomy with salpingo-oophorectomy which demonstrated positive spread to the pelvic lymph nodes and the parametrium.
Pathological examination revealed that the tumour also extensively involved the lower uterine segment.