An Open Internet-based Survey and Natural Language Processing Project Analysing Written Monologues by Headache Patients (NLPH-OPEN)

NLP Headache Open: an Open Internet-based Survey and Natural Language Processing Project Analysing Written Monologues by Headache Patients

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.

Study Overview

• Status: Completed
• Conditions: Migraine Disorders; Headache Disorders; Tension-Type Headache; Cluster Headache; TACS; Secondary Headache Disorder
• Intervention / Treatment: Other: Questionnaires

• Study Type: Observational
• Enrollment (Actual): 1150

Contacts and Locations

Study Locations

• Belgium
  • Ghent, Belgium, 9000
    • University Hospital, Ghent: Department of Neurology

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Patients with headache disorders

Description

Inclusion Criteria:

• 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

Study Plan

How is the study designed?

Design Details

• Observational Models: Ecologic or Community
• Time Perspectives: Cross-Sectional

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Participants; Participants filling in the questionnaires	Other: Questionnaires; Headache attack descriptions, Headache related disability descriptions, Questionnaires, MIDAS, MSQv2.1, SF36

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Lexical diversity and differences between migraine and cluster headache	Chi-square measurement of a word token used by migraine patients versus cluster headache patients	through study completion, an average of 1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of machine learning experiments for the correct classification of headache disorders	Machine learning experiments to investigate the potential to build modelling algorithms that accurately classify the self-given diagnosis by the patient based on text.	through study completion, an average of 1 year
F1 scores of machine learning experiments for the correct classification of headache disorders	Machine learning experiments to investigate the potential to build modelling algorithms that accurately classify the self-given diagnosis by the patient based on text.	through study completion, an average of 1 year
Word counts	Counts of word tokens of different headache disorder groups	through study completion, an average of 1 year
Sentences counts	Counts of sentence tokens of different headache disorder groups	through study completion, an average of 1 year
Paragraph counts	Counts of paragraph tokens of different headache disorder groups	through study completion, an average of 1 year
Term-frequency inverse document frequency scores (TF-IDF)	TF-IDF scores of word tokens of different headache disorder groups	through study completion, an average of 1 year
Migraine Disabillity Assessment [MIDAS] score calculation with text input	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.	through study completion, an average of 1 year
Migraine Specific Questionaire versie 2.1 [MSQv2.1] score calculation with text input	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.	through study completion, an average of 1 year
RAND SF-36 Dutch version score calculation with text input	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.	through study completion, an average of 1 year

Collaborators and Investigators

• Sponsor: University Hospital, Ghent

Study record dates

Study Major Dates

• Study Start (Actual): October 11, 2021
• Primary Completion (Actual): December 31, 2023
• Study Completion (Actual): January 1, 2024

Study Registration Dates

• First Submitted: October 1, 2021
• First Submitted That Met QC Criteria: November 29, 2021
• First Posted (Actual): December 10, 2021

Study Record Updates

• Last Update Posted (Actual): May 16, 2024
• Last Update Submitted That Met QC Criteria: May 14, 2024
• Last Verified: May 1, 2024

More Information

Terms related to this study

• Keywords: Migraine; Headache; Natural Language Processing
• Additional Relevant MeSH Terms: Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Pain; Neurologic Manifestations; Headache Disorders, Primary; Trigeminal Autonomic Cephalalgias; Migraine Disorders; Headache; Headache Disorders, Secondary; Tension-Type Headache; Headache Disorders; Cluster Headache
• Other Study ID Numbers: BC-10635

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No