An expert system for headache diagnosis: the Computerized Headache Assessment tool (CHAT)

Area of Science:

• Neurology
• Medical Informatics

Background:

• Migraine is a prevalent chronic disorder impacting quality of life.
• Chronic daily headache syndromes are less recognized but more impairing than episodic migraine.
• Existing diagnostic tools for headache are limited, with few computerized options available.

Purpose of the Study:

• To develop and evaluate the accuracy and utility of a computerized headache assessment tool (CHAT).
• CHAT was designed to identify major primary headache disorders, differentiate daily from episodic types, and detect medication overuse.

Main Methods:

• CHAT was developed using an expert systems approach, with initial diagnostic branching based on headache frequency and duration.
• The tool was implemented on a website using Microsoft active server pages and a SQL-server database.
• Patients presenting with headache were recruited from urgent care and family practice waiting rooms to complete the online questionnaire.

Main Results:

• CHAT demonstrated high accuracy: 100% for episodic migraine, 85.7% for transformed migraine, and 100% for chronic tension-type headache.
• Medication overuse was correctly identified in 82.7% of cases.
• The system facilitated appropriate referrals, with a significant portion of referred migraine patients receiving a confirmed diagnosis and initiating therapy.

Conclusions:

• The expert system exhibits high diagnostic accuracy for primary headache disorders, including daily headache syndromes and medication overuse.
• CHAT, as part of disease management, improved patient diagnosis and treatment.
• System limitations include patient adoption, integration into clinical workflow, and differentiating transformed migraine.