CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks
-
Updated
Oct 4, 2022 - Python
CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks
Prototypes for EHR-sequencing and temporal phenotyping. Key methods: sequence models, LSTM, attention mechanism, cluster analysis, word & document embeddings, and other NLP methods.
Machine Learning for COVID-19 Data Analysis Project
Classification of EHR data with BERT
A customized version of the Relational Aware Graph Attention Network for large scale EHR records.
Convert arbitrary EHR extracts to FHIR.
Python functions to facilitate the pre-processing of data for ML tasks in a clinical context
Backend for a distributed electronic health records system
A tool to query relational EHR databases
General purpose script for looking for over and under represented EHR facts in an i2b2 patient-set. Can be used for finding healthcare outcomes disparities, comorbidities, and who knows what else. The name is a portmanteau of Chi-squared and phenotype.
Estimate sentiment in clinical notes via keywords or deep learning models
DjangoEHR is an Electronic Health Records (EHR) system developed using the Django web framework. This project aims to provide healthcare professionals with a robust and secure platform for managing patient records, appointments, and medical information.
Repository for the Paper: „On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series“
Official repo for "Characterizing Stigmatizing Language in Medical Records" (ACL 2023)
Graph representation learning with GNNs for predicting disease risk from family EHRs
The OMOP Common Data Model(v6) implemented in Django (v3)
Add a description, image, and links to the ehr topic page so that developers can more easily learn about it.
To associate your repository with the ehr topic, visit your repo's landing page and select "manage topics."