CEHR-BERT: Incorporating temporal information from structured EHR data to improve prediction tasks

COVID-19 EHR data analysis pipeline

KDD2020 paper; Identifying Sepsis Subphenotypes via Time-Aware Multi-Modal Auto-Encoder

Pipeline of Data Extraction, Preprocessing, Representation, and Training for MIMIC-III

attribute-based access control implementation for EHRs

Official implementation of TACCO (Task-guided Co-clustering).

LLM graph-RAG SQL generator for large databases with poor documentation

Official implementation of "FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records" (MLHC 2024)

Controllable Sequence Editing for Counterfactual Generation

Collection of bio-medical and clinical ner models in spacy, stanza, flair with some utility files

Code for "Generating Clinically Realistic EHR Data via a Hierarchy- and Semantics-Guided Transformer"

JAMIA: A Novel Generative Multi-Task Representation Learning Approach for Predicting Postoperative Complications in Cardiac Surgery Patients

This repository hosts a cutting-edge deep learning model developed to predict 6-month incident heart failure utilizing electronic health records (EHRs). Heart failure is a multifaceted medical condition characterized by its significant impact on patients' well-being and healthcare systems.

This pilot project deploys a supplemental OMOP table to map external measures of rurality (RUCC and RUCA).

EHR data engineering using MIMIC-IV and K-MIMIC

BERT style transformer model on CMS synthetic EHR data for diagnosis and procedure prediction in PyTorch

In this project, we will create a deep learning model trained on EHR data (Electronic Health Records) to find suitable patients for testing a new diabetes drug.

HealthDatum is an electronic health record system that provides easy means of managing clinical data.

Electronic Health Record Analysis using SQLite

Exploratory Data Analysis of synthetic COVID-19 patient data generated by Synthea, focusing on patient demographics, healthcare encounters, and prevalent conditions.