An Open Internet-based Survey and Natural Language Processing Project Analysing Written Monologues by Headache Patients
- Conditions
- Cluster HeadacheSecondary Headache DisorderTACSHeadache DisordersTension-Type HeadacheMigraine Disorders
- Interventions
- Other: Questionnaires
- Registration Number
- NCT05153876
- Lead Sponsor
- University Hospital, Ghent
- Brief Summary
Headache disorders are among the most prevalent medical conditions worldwide. The diagnosis of headache disorders is based on medical history taking. Digital solutions such as natural language processing (NLP) may be of aid to understand the linguistic aspects of headache attack and headache related disability descriptions by patients. Participants will provide a written description of their headache disorder. The results will hopefully lead to a better understanding of the potential use of NLP in headache disorders.
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- COMPLETED
- Sex
- All
- Target Recruitment
- 1150
- 18 year or older
- Have a headache disorder with at least one headache attack over the last three months
- voluntary participation
- accepted the patient information sheet and gave informed consent
Not provided
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Arm && Interventions
Group Intervention Description Participants Questionnaires Participants filling in the questionnaires
- Primary Outcome Measures
Name Time Method Lexical diversity and differences between migraine and cluster headache through study completion, an average of 1 year Chi-square measurement of a word token used by migraine patients versus cluster headache patients
- Secondary Outcome Measures
Name Time Method F1 scores of machine learning experiments for the correct classification of headache disorders through study completion, an average of 1 year Machine learning experiments to investigate the potential to build modelling algorithms that accurately classify the self-given diagnosis by the patient based on text.
RAND SF-36 Dutch version score calculation with text input through study completion, an average of 1 year Machine learning experiments to investigate the potential to build modelling algorithms that accurately predict the impact score from RAND SF-36 Dutch version based on text.
Accuracy of machine learning experiments for the correct classification of headache disorders through study completion, an average of 1 year Machine learning experiments to investigate the potential to build modelling algorithms that accurately classify the self-given diagnosis by the patient based on text.
Word counts through study completion, an average of 1 year Counts of word tokens of different headache disorder groups
Sentences counts through study completion, an average of 1 year Counts of sentence tokens of different headache disorder groups
Paragraph counts through study completion, an average of 1 year Counts of paragraph tokens of different headache disorder groups
Migraine Specific Questionaire versie 2.1 [MSQv2.1] score calculation with text input through study completion, an average of 1 year Machine learning experiments to investigate the potential to build modelling algorithms that accurately predict the impact score from Migraine Specific Questionaire versie 2.1 \[MSQv2.1\] based on text.
Term-frequency inverse document frequency scores (TF-IDF) through study completion, an average of 1 year TF-IDF scores of word tokens of different headache disorder groups
Migraine Disabillity Assessment [MIDAS] score calculation with text input through study completion, an average of 1 year Machine learning experiments to investigate the potential to build modelling algorithms that accurately predict the impact score from Migraine Disabillity Assessment \[MIDAS\] based on text.
Trial Locations
- Locations (1)
University Hospital, Ghent: Department of Neurology
🇧🇪Ghent, Belgium