Related Experiment Video
Updated: May 24, 2026
Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
Published on: September 8, 2023
Sub-Phenotyping of Pediatric Celiac Disease with Topological Data Analysis
Daniele Pala1, Giuseppe Albi2, Valentina Brembilla1
1Dept. of Management, Information and Production Engineering, University of Bergamo, Italy.
Insights
Topological Data Analysis identified new pediatric celiac disease (CD) sub-phenotypes. This data-driven approach reveals distinct patient groups based on serology, histology, and comorbidities for precision medicine.
Area of Science:
- Immunology
- Pediatric Gastroenterology
- Data Science
Background:
- Celiac disease (CD) is an autoimmune disorder triggered by gluten.
- Pediatric CD presents heterogeneously, challenging current classifications like the Oslo definitions.
- Need for refined sub-phenotyping in pediatric celiac disease.
Purpose of the Study:
- To introduce a Topological Data Analysis (TDA) framework for identifying novel, clinically relevant sub-phenotypes in pediatric CD.
- To leverage TDA for a data-driven approach to classify pediatric celiac disease patients.
- To uncover distinct patient subgroups beyond traditional symptom-based classifications.
Main Methods:
- Utilized a multicentric dataset comprising over 3,000 pediatric celiac disease patients.
- Applied Topological Data Analysis (TDA) using the TDA Mapper algorithm.
- Compared TDA Mapper results with standard clustering methods (DBSCAN, Agglomerative, K-Medoids).
Main Results:
- TDA Mapper revealed stable and interpretable communities within the pediatric CD cohort.
- These identified communities reflect distinct patterns in serology, histology, and clinical presentation.
- The TDA approach demonstrated superior ability to discern clinically meaningful subgroups compared to standard clustering.
Conclusions:
- Serology, histology, and comorbidities collectively define distinct pediatric celiac disease phenotypes.
- Topological Data Analysis offers a powerful framework for data-driven sub-phenotyping in pediatric CD.
- This approach supports the advancement of precision medicine strategies for celiac disease management in children.
Abstract:
Celiac Disease (CD) is an autoimmune disorder triggered by gluten ingestion in genetically susceptible individuals. Its heterogeneous presentation, especially in pediatric patients, limits the effectiveness of current symptom-based classifications such as the Oslo definitions. This study proposes a framework based on Topological Data Analysis (TDA) to identify new, clinically meaningful sub-phenotypes of pediatric CD. We used a multicentric dataset of over 3,000 children. Compared with standard clustering (DBSCAN, Agglomerative, K-Medoids), our TDA Mapper revealed stable, interpretable communities reflecting serological and clinical patterns. Results indicate that serology, histology, and comorbidities jointly define distinct pediatric phenotypes, supporting data-driven approaches for precision medicine in CD.
More Related Videos
06:01Visualization and Quantification of High-Dimensional Cytometry Data using Cytofast and the Upstream Clustering Methods FlowSOM and Cytosplore
Published on: December 12, 2019
05:12ExCYT: A Graphical User Interface for Streamlining Analysis of High-Dimensional Cytometry Data
Published on: January 16, 2019
