clinicalBERT

Clinical prediction tool

This repository provides pre-trained models and scripts for predicting hospital readmission based on clinical notes using the BERT framework.

ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission (CHIL 2020 Workshop)

GitHub

386 stars
14 watching
100 forks
Language: Jupyter Notebook
last commit: almost 4 years ago
Linked from 2 awesome lists

clinicalberthospital-readmissionprediction

Backlinks from these awesome lists:

Related projects:

RepositoryDescriptionStars
emilyalsentzer/clinicalbertProvides clinical BERT embeddings for natural language processing tasks in healthcare680
dmis-lab/biobertProvides pre-trained language representation models for biomedical text mining tasks1,970
ncbi-nlp/bluebertPre-trained language models for biomedical natural language processing tasks560
naver/biobert-pretrainedProvides pre-trained weights for a biomedical language representation model672
aphp/edsnlpA modular NLP framework that extracts information from French clinical notes using rule-based and deep learning techniques.117
ymcui/macbertImproves pre-trained Chinese language models by incorporating a correction task to alleviate inconsistency issues with downstream tasks646
cerlymarco/medium_notebookA collection of Jupyter Notebooks that document various time series forecasting techniques and models used in data science and machine learning.2,087
kexinhuang12345/deeppurposeA toolkit for molecular modeling and prediction tasks using deep learning988
kevinjalbert/master-thesisAn investigation into methods for predicting mutation scores based on source code and test suite metrics using machine learning techniques3
michael-wzhu/promptcblueA large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain328
davidcpage/cifar10-fastDemonstrates training a small ResNet on CIFAR10 with a specific configuration and benchmarking setup536
christophm/rulefitAn algorithm implementation for rule-based prediction using gradient boosting and L1 regularization.411
ragulpr/wtte-rnnA framework for predicting time to event and churn using recurrent neural networks with Weibull distribution769
zygmuntz/kaggle-cifarCode for training and predicting on the CIFAR-10 image classification dataset using CUDA-convnet architecture.44
bplaye/nnk_dtiAn open-source project evaluating deep learning methods for predicting ligands and drugs in chemogenomics3