DISNET

DISNET extracts and integrates signs, symptoms and diagnostic-test information from public textual sources (e.g., Wikipedia, PubMed) to generate disease–symptom associations for comparative and temporal analyses.

Key Features:

• Data Extraction: Periodic automated retrieval of textual information on signs, symptoms and diagnostic tests from public sources including Wikipedia and PubMed using text mining approaches.
• Customizable Disease Networks: Construction of configurable disease networks that represent relationships between diseases based on shared clinical manifestations.
• Validation and Accuracy: Evaluation of extracted diagnostically relevant terms through validation against source texts from Wikipedia and PubMed to assess extraction accuracy.

Scientific Applications:

• Disease Relationship Analysis: Comparative analysis of diseases based on shared phenotypic characteristics such as signs and symptoms.
• Temporal Tracking of Diagnostic Terminology: Monitoring changes in clinical diagnosis terms over time to study the evolution of medical knowledge.
• Epidemiology and Precision Medicine Research: Provision of structured disease–symptom associations to support epidemiological studies and personalized medicine analyses.

Methodology:

Automated retrieval of textual information from public sources (e.g., Wikipedia, PubMed), application of text mining and natural language processing to parse and interpret medical texts, and validation of extracted terms against source texts.