Abstract
Precise history taking is the key to develop a first assumption on the diagnosis of vestibular disorders. Particularly in the primary care setting, algorithms are needed, which are based on a small number of questions and variables only to guide appropriate diagnostic decisions. The aim of this study is to identify a set of such key variables that can be used for preliminary classification of the most common vestibular disorders. A four-step approach was implemented to achieve this aim: (1) we conducted an online expert survey to collect variables that are meaningful for medical history taking, (2) we used qualitative content analysis to structure these variables, (3) we identified matching variables of the patient registry of the German Center for Vertigo and Balance Disorders, and (4) we used classification trees to build a classification model based on these identified variables and to analyze if and how these variables contribute to the classification of common vestibular disorders. We included a total of 1,066 patients with seven common vestibular disorders (mean age of 51.1 years, SD = 15.3, 56 female). Functional dizziness was the most frequent diagnosis (32.5), followed by vestibular migraine (20.2) and Menière's disease (13.3). Using classification trees, we identified eight key variables which can differentiate the seven vestibular disorders with an accuracy of almost 50. The key questions comprised attack duration, rotational vertigo, hearing problems, turning in bed as a trigger, doing sport or heavy household chores as a trigger, age, having problems with walking in the dark, and vomiting. The presented algorithm showed a high-face validity and can be helpful for taking initial medical history in patients with vertigo and dizziness. Further research is required to evaluate if the identified algorithm can be applied in the primary care setting and to evaluate its external validity.
Item Type: | Journal article |
---|---|
Keywords: | Vertigo; diagnosis; machine learning; surveys and questionnaires; clinical decision-making |
Faculties: | Medicine > Institute for Medical Information Processing, Biometry and Epidemiology Medicine > Institute for Medical Information Processing, Biometry and Epidemiology > Epidemiology of Vertigo and Dizziness |
Research Centers: | Münchner Zentrum für Gesundheitswissenschaften (MC-Health) |
Subjects: | 600 Technology > 610 Medicine and health |
URN: | urn:nbn:de:bvb:19-epub-75745-8 |
ISSN: | 1664-2295 |
Item ID: | 75745 |
Date Deposited: | 30. Apr 2021, 13:00 |
Last Modified: | 08. Dec 2023, 14:38 |