Geographic distribution of vestibular schwannomas in West Scotland between 2000-2015

Abstract

Background: Although the natural history of vestibular schwannomas (VS) has been previously studied, few studies have investigated associated epidemiological factors, primarily because of the lack of large available cohorts.

Objective: The objective of this study was to perform a multi-scale geographical analysis of the period prevalence of VS in West Scotland from 2000 to 2015.

Methods: Adults diagnosed with sporadic VS were identified through the National Health Services of West Scotland database and geocoded to the unit postcode. To assess whether the cohort of VS cases could be pooled into a period prevalence measure, the locations of VS cases were analyzed by sex using Cross-L and Difference-K functions. VS period prevalence was examined at two aggregate spatial scales: the postcode district and a coarser scale of NHS Health Boards. The spatial structure of period prevalence within each level of spatial aggregation was measured using univariate global and local Moran's I. Bivariate local Moran's I was used to examine the between-scale variability in period prevalence from the postcode district level to the NHS Health Boards levels. Prior to spatial autocorrelation analyses, the period prevalence at the postcode district was tested for stratified spatial heterogeneity within the NHS Health Boards using Wang's q-Statistic.

Results: A total of 512 sporadic VS were identified in a population of over 3.1 million. Between 2000 and 2015, VS period prevalence was highest within the NHS Health Boards of Greater Glasgow and Clyde, Ayrshire and Arran and the Western Isles. However, at the NHS scale, period prevalence exhibited no spatial autocorrelation globally or locally. At the district scale, Highland exhibited the most unusual local spatial autocorrelation. Bivariate local Moran's I results indicated general stability of period prevalence across the postcode district to Health Boards scales. However, locally, some postcode districts in Greater Glasgow and Clyde, Ayrshire and Arran exhibited unusually low district to zone spatial autocorrelation in period prevalence, as did the southern parts of the Western Isles. Some unusually high period prevalence values between the postcode district to Health Board scale were found in Tayside, Forth Valley and Dumfries and Galloway.

Conclusion: Geographic variability in VS in West Scotland was identified in this patient population, showing that there are areas, even remote, with unusually high or low period prevalence. This can be partially attributed to links between primary and tertiary care. Potential genetic or environmental risk factors that may contribute to geographic variation in this disease within Scotland are also a possibility but require further investigation.

Fig 1. Neighbor graphs illustrating the connectivity used at the zone (a) and district level (b) for modelling spatial interaction within the spatial weights matrices used in calculating spatial autocorrelation measures.

Fig 2. a) Cross-L function between the locations of male and female VS cases with pointwise simulation envelopes based on 199 simulations, b) Difference-K functions (male-female) with pointwise simulation envelopes from 199 random labeling of 239 male VS points.

Fig 3. Period prevalence (SPP) of patients presenting with VS to the National Health Services of West of Scotland a) by NHS Health Boards with board names for reference and b) by postcode districts with settlements named within text.

Note the different scales for period prevalence between a and b.

Fig 4. a) Univariate local Moran’s I cluster map of period prevalence (PP) at the district level; b) Bivariate local Moran’s I cluster map of period prevalence (PP) across the district-zone level.

Different color schemes are used between a and b to highlight that the univariate and bivariate local Moran’s I are interpreted differently.