ICHD3 Primary Headache Syndromes Represented as a Diagnostic Matrix

A matrix representation of primary headache syndromes from the International Classification of Headache Disorders (ICHD3) enables automated diagnosis and analysis. The dataset encodes headache phenotypes and diagnostic characteristics as a biadjacency matrix, with results derived from bipartite projection and Markov clustering. It was published by Pengfei Zhang on figshare under a CC-BY-4.0 license.

Use Cases

• Automating headache diagnosis based on logical criteria encoded in the matrix.
• Analyzing relationships between headache phenotypes and characteristics using bipartite projection.
• Clustering headache diagnoses into groups via Markov clustering to understand classification fragmentation.
• Exploring the vector space representation of diagnoses using the 63 derived basis characteristics.

Strengths

• The dataset is derived from the ICHD3, described as the gold standard for clinical trials and research in headache medicine.
• The matrix representation allows for the calculation of 63 basis vectors, implying all diagnoses can be represented as linear combinations of these characteristics.
• Markov clustering yields 64 clusters, demonstrating the internal structure of the classification, such as migraine being composed of 1 cluster while paroxysmal hemicrania breaks into 9.

Limitations

• The dataset is very small at 2.6 KB, indicating limited scope and likely containing only the derived matrix, not raw patient data.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for certain analyses.

Provenance

Source

figshare

Collection Method

Derived from translating ICHD3 diagnostic criteria into true/false statements to construct a phenotype-characteristic matrix.

Freshness

Last updated 2026-05-11 14:55:36; freshness should be verified.