Related Experiment Video
Updated: Jul 4, 2025
08:33
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
Published on: January 5, 2024
1.2K
Multi-Dimensional Validation of the Integration of Syntactic and Semantic Distance Measures for Clustering
Ayelet Goldstein1, Yuval Shahar2, Michal Weisman Raymond2
1Computer Science Department, Hadassah Academic College, Jerusalem 9101001, Israel.
Bioengineering (Basel, Switzerland)
|January 26, 2024
Summary
A new methodology, CDI-SSV, effectively clusters fibromyalgia patients into three distinct severity levels. This approach enhances patient classification and aids in personalized diagnosis and management.
Area of Science:
- Computational biology and bioinformatics
- Data science and machine learning
- Clinical informatics
Background:
- Accurate patient stratification is crucial for effective disease management, particularly in complex conditions like fibromyalgia.
- Existing clustering methodologies may lack robustness in identifying optimal patient subgroups and validating their clinical significance.
Purpose of the Study:
- To develop and validate a novel multi-dimensional methodology (CDI-SSV) for discovering and validating the optimal number of clusters.
- To apply the CDI-SSV methodology for clustering fibromyalgia patients and identifying distinct clinical profiles.
Main Methods:
- The CDI-SSV methodology integrates multiple clustering algorithms, syntactic distance measures (Silhouette Index, Calinski-Harabasz index, Davies-Bouldin index), stability assessment (adjusted Rand index), and iterative semantic validation.
- A supervised machine learning model with Shapley additive explanations (SHAP) was used for validation and interpretation of the discovered clusters.
- The methodology was applied to a dataset of 1370 fibromyalgia patients.
Main Results:
- The K-means algorithm demonstrated robustness, leading to the identification of k=3 clinically meaningful clusters representing distinct fibromyalgia severity levels.
- A random forest model achieved high accuracy (AUC: 0.994, accuracy: 0.946) in classifying patients into these clusters.
- SHAP analysis highlighted "functional problems" as a key differentiator for the most severe patient group.
Conclusions:
- The CDI-SSV methodology provides a robust framework for improving the classification of complex patient populations.
- The identified three-cluster solution offers a potential classification system for fibromyalgia patients, facilitating personalized diagnosis, management, and prognosis.
- This approach has the potential to enhance clinical care by providing evidence-based clinical markers for fibromyalgia.
