Research Papers

Welcome to our publication page! Here you'll find a collection of our latest research.

Patient Recruitment

Preprint

Matching Patients to Clinical Trials with Large Language Models

LLM, Prompting, Patient-Trial Matching

KDD'20

COMPOSE: Cross-modal pseudo-siamese network for patient trial matching

Patient-Trial Matching, EHR

AAAI'20

Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment

Patient-Trial Macthing, EHR

Trial Design

EMNLP'23

AutoTrial: Prompting Language Models for Clinical Trial Design

LLM, Instruction Tuning, Eligibility Criteria

EMNLP'22

Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision

Trial Search, Contrastive Learning, Dense Retrieval

ACM-BCB'23

SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning

Trial Outcome, Sequential Learning

Patterns

HINT: Hierarchical Interaction Network for Clinical Trial Outcome Predictions

Trial Outcome, Graph Neural Network

Multimodal Model

ICLR'24

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graph

Foundation Model, Multimodal AI, Biomedical AI, Knowledge Graph

EMNLP'22

MedCLIP: Contrastive Learning from Unpaired Medical Images and Text

Vision-Language Model, Multimodal AI, Clinical Note, X-Ray

Clinical Predictive Model

Preprint

UniPredict: Large Language Models are Universal Tabular Predictors

Tabular Learning, Patient Outcome, LLM, Instruction Tuning

Preprint

MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement

Tabular Learning, Patient Outcome, LLM, Data-Centric AI

NeurIPS'22

TransTab: Learning Transferable Tabular Transformers Across Tables

Tabular Learning, Patient Outcome, Transfer Learning

JAMIA

STAN: Spatio-Temporal Attention Network for Pandemic Prediction using Real-World Evidence

Pandemic Prediction, Graph Neural Network, Real-World Evidence

Nature Communications

Evidence-driven spatiotemporal COVID-19 hospitalization prediction with Ising dynamics

Pandemic Prediction, Spatio-temporal Prediction

WWW'22

PopNet: Real-Time Population-Level Disease Prediction with Data Latency

Population Health Prediction, Graph Neural Network, Spatio-temporal Prediction

Synthetic Patient Generation

KDD'23

TWIN: Personalized Clinical Trial Digital Twin Generation

Ditial Twin, Variational Autoencoder

EMNLP'22

PromptEHR: Conditional Electronic Healthcare Records Generation with Prompt Learning

LLM, Instruction Tuning, EHR

JAMIA

SynTEG: a framework for temporal structured electronic health data simulation

EHR, Generative Adversarial Network

AAAI'20

CONAN: Complementary Pattern Augmentation for Rare Disease Detection

EHR, Generative Adversarial Network