Table 1.

Description of the real-world data sets

	N (gender)	Age	Diagnosis	ELH	ELH grade	Data Quality
D1	105 (50 male)	50.4 ± 17.1 range 19–84	32% VM (n = 33) 28% MD (n= 29) 18% NV (n = 19) 17% VP (n = 18) 3% BVP (n = 4) 2% BPPV (n = 2)	97 out of 210 ears 46.2%	0.7 ± 0.8 Range 0–3	1.1 ± 0.3 Range 0.3–2.3
D3	10 (5 male)	46.8 ± 14.4 range 31–69	10% VM (n = 1) 70% MD (n = 7) 10% NV (n = 1) 10% BPPV (n = 1)	7 out of 20 ears 35%	0.7 ± 0.9 Range 0–2.5	1.1 ± 0.3 Range 0.3–1.6

D1 and D3 included data sets from consecutive patients from the interdisciplinary German Center for Vertigo and Balance Disorders (DSGZ), Munich, Germany. Included patients had presented with episodic vertigo attacks and undergone delayed intravenous gadolinium-enhanced magnetic resonance imaging of the inner ear (iMRI) as part of their indicated clinical diagnostic workup. Patients were clinically diagnosed according to the several international guidelines, most of the classification committee of the international Bárány Society (https://www.jvr-web.org/ICVD.html or https://www.baranysociety.nl) and included the diagnosis of VM [23], MD [24], VP [25], BPPV [26], BVP [1] and acute unilateral vestibulopathy/vestibular neuritis [2]. Grading of the ELH in the vestibulum and cochlea was based on criteria described previously [3], which constitutes a fusion of two classification systems [4, 5]. D1 and D3 did not differ significantly concerning age, gender, the grade of ELH, or data quality

 ± standard deviation, BPPV benign paroxysmal positional vertigo, BVP bilateral vestibulopathy, ELH endolymphatic hydrops, ELS endolymphatic space, iMRI delayed intravenous gadolinium-enhanced magnetic resonance imaging of the inner ear, MD Menière’s disease, N number of participants, VM vestibular migraine, VP vestibular paroxysmia