UK Biobank Rare Disease Comorbidity Patterns Identified via Hierarchical Clustering

A 684.4 KB PDF data sheet describes a machine learning analysis of comorbidity patterns in rare disease patients. The study applied hierarchical clustering to UK Biobank diagnosis data, identifying 12 comorbidity clusters for the rare disease group and 14 for the no rare disease group. The author is Benjamin Mark Connor, and the data sheet was last updated on 2026-05-04.

Use Cases

• Identifying unique comorbidity patterns in rare disease patients based on the described hierarchical clustering results.
• Comparing disease progression and etiology between rare disease and general populations based on the described comorbidity clusters.
• Informing clinical management strategies for rare diseases based on the detected patterns of multiple diseases.
• Prioritizing interventions for patient care based on the unique comorbidity patterns observed.

Strengths

• Analysis is based on diagnosis data from the UK Biobank, a major biomedical database.
• The study identified a specific number of clusters: 12 for the rare disease group and 14 for the control group.

Limitations

• The underlying dataset is not provided; only a 684.4 KB PDF summary of results is available.
• Column-level documentation is absent; field semantics must be inferred from the description.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

UK Biobank

Collection Method

Hierarchical clustering applied to diagnosis data.

Freshness

Last updated 2026-05-04 05:32:46; freshness should be verified.

Geography

United Kingdom