A Knowledge Graph Framework for Longitudinal Congenital Heart Disease Modeling
Hang Xu, Lila Cunge, Zhengyang Ming, Siyan Chen, Majid Husain, Pierangelo Renella, Gentian Lluri, J. Paul Finn, William Hsu, Kim-Lien Nguyen · 2026
Read A Knowledge Graph Framework for Longitudinal Congenital Heart Disease Modeling by Hang Xu, Lila Cunge, Zhengyang Ming, Siyan Chen, Majid Husain, Pierangelo Renella, Gentian Lluri, J. Paul Finn, William Hsu, Kim-Lien Nguyen (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13660652.txt.
Description
Hang Xu and co-authors turn a lifetime of heart records into a map a computer can walk in a 2026 paper. Congenital heart disease unfolds over decades: diagnoses, staged surgeries, and clinic visits in a long, branching story. Standard machine learning flattens that story into static snapshots, losing the plot that clinicians actually reason with.
Their framework builds a knowledge graph linking patients, encounters, diagnoses, and procedures in true time order. Text-style weighting and embedding methods then read each patient's path through the graph as a document, producing representations that preserve sequence and context. Applied to a magnetic resonance imaging cohort, the paths carried clinically meaningful patterns. A test case, spotting single-ventricle physiology from the record trail, showed the approach can classify retrospectively with the story intact. The authors offer the graph as infrastructure for trajectory-aware cardiology.
Catalog record
| CREATOR | Hang Xu, Lila Cunge, Zhengyang Ming, Siyan Chen, Majid Husain, Pierangelo Renella, Gentian Lluri, J. Paul Finn, William Hsu, Kim-Lien Nguyen |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |