KDD 2024 | FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction

Official implementation of SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction

PRISM: Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration for EHR Data Sparsity Mitigation

[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".

[CIKM'23] The official implementation code of DiffuASR.

SynthEHRella is a benchmarking package used for evaluating synthetic Electronic Health Records (EHR) data generation methods.

Source code of the paper titled "Unity in Diversity: Collaborative Pre-training Across Multimodal Medical Sources".

Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval

Code to generate realistic synthetic healthcare data with diffusion models

Pytorch implementation of “Learnable Prompt as Pseudo-Imputation (PAI)”

Code for CTO: A Large Clinical Trial Outcome and QA Dataset

Diffusion Models for Generative Outfit Recommendation

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

GLBench: A Comprehensive Benchmark for Graphs with Large Language Models

Repository for the paper 'MDS-ED: Multimodal Decision Support in the Emergency Department – a benchmark dataset based on MIMIC-IV'.

A benchmark for few-shot evaluation of foundation models for electronic health records (EHRs)

The official implementation of Achieving Cross Modal Generalization with Multimodal Unified Representation (NeurIPS '23)

Source code of our SIGIR'24 paper titled "Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients".

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

OMOP standardization pipeline for ICU databases

A collection of AI models tailored for healthcare applications.