Related Experiment Video
Updated: Jun 16, 2025
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
DBSCAN and DBCV application to open medical records heterogeneous data for identifying clinically significant
Davide Chicco1,2, Luca Oneto3, Davide Cangelosi4
1Università di Milano-Bicocca, Milan, Italy. davidechicco@davidechicco.it.
Insights
Unsupervised machine learning, specifically DBSCAN, identified two clinically relevant patient subgroups in neuroblastoma data. This approach offers a valuable tool for analyzing rare disease datasets and potentially improving patient outcomes.
Area of Science:
- Biomedical Informatics
- Computational Intelligence
- Pediatric Oncology
Background:
- Neuroblastoma is a prevalent pediatric cancer, particularly affecting young children.
- High-risk stage four neuroblastoma has a low survival rate (40%), highlighting the need for improved treatments.
- Electronic health records (EHRs) offer rich data for computational analysis to identify patient subgroups.
Purpose of the Study:
- To apply unsupervised machine learning to identify clinically significant subgroups within neuroblastoma patient data.
- To evaluate the effectiveness of different clustering techniques for analyzing restricted EHR datasets.
- To determine if identified subgroups correlate with known clinical variables in neuroblastoma.
Main Methods:
- Utilized three open neuroblastoma datasets (Genoa, Shanghai, TARGET-NBL).
- Applied various unsupervised machine learning clustering techniques.
- Evaluated clustering performance using the Density-Based Clustering Validation (DBCV) index.
- Focused on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for its meaningful results.
Main Results:
- DBSCAN successfully identified two distinct patient clusters across all three datasets.
- Key clinical variables were found to significantly differentiate patients between the two identified clusters.
- The identified clusters demonstrated clinical relevance within the neuroblastoma literature.
Conclusions:
- DBSCAN, validated by DBCV, is a robust method for subgroup discovery in neuroblastoma EHR data.
- This unsupervised learning approach can aid health informatics researchers in analyzing rare disease patient data.
- The findings suggest potential for developing targeted therapies for identified patient subgroups.
Abstract:
Neuroblastoma is a common pediatric cancer that affects thousands of infants worldwide, especially children under five years of age. Although recovery for patients with neuroblastoma is possible in 80% of cases, only 40% of those with high-risk stage four neuroblastoma survive. Electronic health records of patients with this disease contain valuable data on patients that can be analyzed using computational intelligence and statistical software by biomedical informatics researchers. Unsupervised machine learning methods, in particular, can identify clinically significant subgroups of patients, which can lead to new therapies or medical treatments for future patients belonging to the same subgroups. However, access to these datasets is often restricted, making it difficult to obtain them for independent research projects. In this study, we retrieved three open datasets containing data from patients diagnosed with neuroblastoma: the Genoa dataset and the Shanghai dataset from the Neuroblastoma Electronic Health Records Open Data Repository, and a dataset from the TARGET-NBL renowned program. We analyzed these datasets using several clustering techniques and measured the results with the DBCV (Density-Based Clustering Validation) index. Among these algorithms, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) was the only one that produced meaningful results. We scrutinized the two clusters of patients' profiles identified by DBSCAN in the three datasets and recognized several relevant clinical variables that clearly partitioned the patients into the two clusters that have clinical meaning in the neuroblastoma literature. Our results can have a significant impact on health informatics, because any computational analyst wishing to cluster small data of patients of a rare disease can choose to use DBSCAN and DBCV rather than utilizing more common methods such as k-Means and Silhouette coefficient.
