Exploring the benefits of Artificial Intelligence in Healthcare

Welcome to AI Health Lab | iSchool + Dell Med @ UT Austin

AI Health Lab is led by Prof. Ying Ding from School of information, and Prof. Justin Rousseau from Dell Medical School at the University of Texas at Austin. AI Health Lab  is made up of scholars and students from different fields and disciplines. We focus on cutting-edge research on AI in health and data-driven science of science. Our research is concentrated but not limited to the following topics:

AI in Health

● Developing Human-centered AI approaches for medical imaging diagnosis.
● Building and mining Knowledge Graphs for healthcare.
● Creating AI approaches for health risk prediction.

AI in Medicine

● Building and mining knowledge graphs for drug discovery.
● Developing deep graph mining algorithms for drug discovery.

Data-Driven Science of Science

● Understanding team collaboration and success.
● Using big literature data to understand science (e.g., inequality, novelty, diversity).

AI Health Podcast

In this channel, we interview the foremost experts on Explainable AI in Health. 

Projects

A portal about researchers, universities, and bio entities related to COVID-19. In this portal, you will know who is working on which biological entities relate to COVID-19, and the institutional profile on research related to COVID-19 (researchers, papers, and biological entities).

An open-source human-centered medical imaging diagnosis tool adding the prior knowledge of radiologists into the deep learning algorithms to enable automatic or semi-automatic generation of diagnosis notes based on medical images.

Introducing two unique positive sampling strategies specifically tailored for EHR data...

A project aims to investigate socioeconomic and racial disparities in healthcare services during the global COVID-19 pandemic. Funded by Gates Foundation.

Publications

Prior Knowledge Enhances Radiology Report Generation

In this work, we propose to mine and represent the associations among medical findings in an informative knowledge graph and incorporate this prior knowledge with radiology report generation to help improve the quality of generated reports.

Through the integration of credible multi-source data, we could create connections among the bio-entities, authors, articles, affiliations, and funding.

Contrastive Learning Improves Critical Event Prediction in COVID-19 Patients

Contrastive loss (CL) improves the performance of CEL especially in imbalanced electronic health records (EHR) data for COVID-19 analyses.

Events