Abstract
BackgroundThis study evaluates the accuracy of an automated classification tool of single attacks of the two major primary headache disorders migraine and tension-type headache used in an electronic headache diary.MethodsOne hundred two randomly selected reported headache attacks from an electronic headache-diary of patients using the medical app M-sense were classified by both a neurologist with specialisation in headache medicine and an algorithm, constructed based on the ICHD-3 criteria for migraine and tension-type headache. The level of agreement between the headache specialist and the algorithm was compared by using a kappa statistic. Cases of disagreement were analysed in a disagreement validity assessment.ResultThe neurologist and the algorithm classified migraines with aura (MA), migraines without aura (MO), tension-type headaches (TTH) and non-migraine or non-TTH events. Of the 102 headache reports, 86 cases were fully agreed on, and 16 cases not, making the level of agreement unweighted kappa 0.74 and representing a substantial level of agreement. Most cases of disagreement (12 out of 16) were due to inadvertent mistakes of the neurologist identified in the disagreement validity assessment. The second most common reason (3 out of 16) was insufficient information for classification by the neurologist.ConclusionsThe substantial level of agreement indicates that the classification tool is a valuable instrument for automated evaluation of electronic headache diaries, which can thereby support the diagnostic and therapeutic clinical processes. Based on this study’s results, additional diagnostic functionalities of primary headache management apps can be implemented. Finally, future research can use this classification algorithm for large scale database analysis for epidemiological studies.
Highlights
This study evaluates the accuracy of an automated classification tool of single attacks of the two major primary headache disorders migraine and tension-type headache used in an electronic headache diary
The substantial level of agreement indicates that the classification tool is a valuable instrument for automated evaluation of electronic headache diaries, which can thereby support the diagnostic and therapeutic clinical processes
In this paper, we present an algorithm that applies the International Classification of Headache Disorders (ICHD)-3 criteria to single headache events recorded in a migraine management app’s database
Summary
This study evaluates the accuracy of an automated classification tool of single attacks of the two major primary headache disorders migraine and tension-type headache used in an electronic headache diary. Despite being one of the most prevalent disorders worldwide, the two major primary headache disorders of migraines and tension-type headaches (TTH) remain underdiagnosed and undertreated in Europe and other parts of the world [1, 2]. Guidelines recommend different drug therapies, second, changes in frequency and phenomenology over time can indicate chronic headache conditions, and medication overuse. The automated classification of large sets of migraine and tension-type headache can shed some light on the co-occurrence of both conditions and the transformation of headache features during the progression into chronification or remission from chronic form. The correct application of this extensive set of evidence-based classification criteria can be time-consuming and challenging, especially in primary care settings [4]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call