AI for Clinical Data Intelligence
Builds intelligent systems for understanding and analysing heterogeneous clinical data. It spans medical question answering, clinical representation learning, patient similarity search, and electronic health record analysis, transforming complex clinical data into actionable insights to support more accurate and efficient healthcare decision-making.
Pipeline Overview
Input Data
Electronic Health Records
Medical Knowledge Bases
Clinical Notes & Reports
Patient Queries
›
1
Encode
Learn multi-view representations from heterogeneous clinical records
LREC'24
›
2
Retrieve
Search for similar patients using a unified representation framework
DSE'23
›
3
Analyse
Extract clinical patterns via deep graph neural network reasoning
CIKM'21
›
4
Enrich
Incorporate contextual knowledge to enhance medical understanding
TKDE'21
›
5
Answer
Generate accurate responses to clinical questions via deep learning
WWW'20
›
Downstream Applications
Clinical Decision Support
Patient Risk Stratification
Medical Question Answering
Disease Diagnosis Support
Prediction Accuracy
Interpretability
Clinical Relevance
Scalability
Related Publications
LREC'24
MHGRL: An Effective Representation Learning Model for Electronic Health Records
LREC-COLING, 2024
DSE'23
A One-Size-Fits-Three Representation Learning Framework for Patient Similarity Search
Data Science and Engineering, 2023
CIKM'21
IMAS++: An Intelligent Medical Analysis System Enhanced with Deep Graph Neural Networks
CIKM, 2021
TKDE'21
How Context or Knowledge Can Benefit Healthcare Question Answering?
IEEE Transactions on Knowledge and Data Engineering, 2021
WWW'20
HqaDeepHelper: A Deep Learning System for Healthcare Question Answering
The Web Conference (WWW), 2020