Predictive Capability of an iPad-Based Medical Device (mex) for the Diagnosis of Vertigo and Dizziness.

BACKGROUND

Making the correct diagnosis of patients presenting with vertigo and dizziness in clinical practice is often challenging.

OBJECTIVE

In this study we examined the performance of the iPad based program mex in the prediction of different clinical vertigo and dizziness diagnoses and as a diagnostic tool to distinguish between them.

PATIENTS AND METHODS

The data collection was done in the outpatient clinic of the German Center of Vertigo and Balance Disorders. The "gold standard diagnosis" was defined as the clinical diagnosis of the specialist during the visit of the patient based on standardized history and clinical examination. Another independent and blinded physician finalized each patient's case in the constellatory diagnostic system of mex based on an algorithm using all available clinical information. These diagnoses were compared to the "gold standard" by retrospective review of the charts of the patients. The accuracy provided by mex was defined as the number of correctly classified diagnoses. In addition, the probability of being test positive when a disease was present (sensitivity), of being test negative when a disease was absent (specificity), of having the disease when the test is positive (positive predictive value) and of not having the disease when the test is negative (negative predictive value) for the most common diagnoses were reported. Sixteen possible different vertigo and dizziness diagnoses could be provided by mex.

RESULTS

A total of 610 patients (mean age 58.1 ± 16.3 years, 51.2% female) were included. The accuracy for the most common diagnoses was between 82.1 and 96.6% with a sensitivity of 40 to 80.5% and a specificity of more than 80%. When analyzing the quality of mex in a multiclass problem for the six most common clinical diagnoses, the sensitivity, specificity, positive and negative predictive values were as follows: Bilateral vestibulopathy (81.6, 97.1, 71.1, and 97.5%), Menière's disease (77.8, 97.6, 87.0, and 95.3%), benign paroxysmal positional vertigo (61.7, 98.3, 86.6, and 93.4%), downbeat nystagmus syndrome (69.6, 97.7, 71.1, and 97.5%), vestibular migraine (34.7, 97.8, 76.1, and 88.3%), and phobic postural vertigo (80.5, 82.5, 52.5, and 94.6%).

CONCLUSION

This study demonstrates that mex is a new and easy approach to screen for different diagnoses. With the high specificity and negative predictive value, the system helps to rule out differential diagnoses and can therefore also lead to a cost reduction in the health care system. However, the sensitivity was unexpectedly low, especially for vestibular migraine. All in all, this device can only be a complementary tool, in particular for non-experts in the field.