uf-hobi-informatics-lab Goto Github PK

2019_n2c2_track1_clinicalsts

source code for UFL team participated in 2019N2C2/OHNLP challenge Track-1 Clinical Sematic Text Similarity

2019_n2c2_track2_fhextraction

2019-n2c2-FH UF solution

adrd_risk_factor_knowledge_map

clinicaltransformerclassification

2022 N2C2 name entity classification

clinicaltransformermrc

Approaching Clinical NER as a MRC problem

clinicaltransformerner

a library for named entity recognition developed by UF HOBI NLP lab featuring SOTA algorithms

clinicaltransformerrelationextraction

A project for developing transformer-based models for clinical relation extraction

colorectal-cancer-predication

Prediction of colorectal cancer onset under 50 years old through a machine learning approach using real-world data

converter_2_0

Oneflorida data converter

converter_cluster

Source code of the OneFL+ dynamic virtual cluster software for PySpark processing

deeponet_t2d

ehrmappings

mappings between NDC2RXCUI and ICD2PheWas

gatorag

Use GatortronGPT for Retrieval Augmented Generation

gatortron

all scripts used in gatortron project

gatortrongpt

nlp-ml-training

A series of training of deep neural networks on natural language processing

nlpreprocessing

A comprehensive NLP preprocessing package for clinical notes sentence boundary detection, tokenization

quantitativesmokingstatusextractionnlptool

a rule-base NLP system to extract quantitative smoking information (e.g., pack-year) from clinical notes

rule-base-engine-py

Using rule-based algorithms to extract clinical entities of interest from clinical notes

rulebasesmokinginfoextractionpy

Python implementation of RuleBaseSmokingInfoExtraction java package

sdoh_soda

seqehr

develop deep learning-based models for learning structured EHR as a sequence

soda_docker

repo for pipeline development

target-conference-list

tweeta

tweetf0rm

A twitter crawler in Python

tweetspreprocess

convert raw tweets to preprocessed text according to the requirement of GloVe

umass18-challenge

MADE1.0 clinical NLP challange