Incidence and prevalence of dementia associated with transient ischaemic attack and stroke: analysis of the population-based Oxford Vascular Study

Abstract

Background: Risk of dementia after stroke is a major concern for patients and carers. Reliable data for risk of dementia, particularly after transient ischaemic attack or minor stroke, are scarce. We studied the risks of, and risk factors for, dementia before and after transient ischaemic attack and stroke.

Methods: The Oxford Vascular Study is a prospective incidence study of all vascular events in a population of 92 728 people residing in Oxfordshire, UK. Patients with transient ischaemic attack or stroke occurring between April 1, 2002, and March 31, 2012, were ascertained with multiple methods, including assessment in a dedicated daily emergency clinic and daily review of all hospital admissions. Pre-event and post-event (incident) dementia were diagnosed at initial assessment and during 5-years' follow-up on the basis of cognitive testing supplemented by data obtained from hand searches of all hospital and primary care records. We assessed the association between post-event dementia and stroke severity (as measured with the US National Institutes of Health Stroke Scale [NIHSS] score), location (ie, dysphasia), previous events, markers of susceptibility or reserve (age, low education, pre-morbid dependency, leucoaraiosis), baseline cognition, and vascular risk factors with Cox regression models adjusted for age, sex, and education. We compared incidence and prevalence of dementia in our population with published UK population age-matched and sex-matched rates.

Findings: Among 2305 patients (mean age 74·4 years [SD 13·0]), 688 (30%) had transient ischaemic attacks and 1617 (70%) had strokes. Pre-event dementia was diagnosed in 225 patients; prevalence was highest in severe stroke (ie, NIHSS >10) and lowest in transient ischaemic attack. Of 2080 patients without pre-event dementia, 1982 (95%) were followed up to the end of study or death. Post-event dementia occurred in 432 of 2080 patients during 5 years of follow-up. The incidence of post-event dementia at 1 year was 34·4% (95% CI 29·7-41·5) in patients with severe stroke (NIHSS score >10), 8·2% (6·2-10·2) in those with minor stroke (NIHSS score <3), and 5·2% (3·4-7·0) in those with transient ischaemic attack. Compared with the UK age-matched and sex-matched population, the 1-year standardised morbidity ratio for the incidence of dementia was 47·3 (95% CI 35·9-61·2), 5·8 (4·4-7·5), and 3·5 (2·5-4·8), respectively. Consequently, prevalence of dementia in 1-year survivors was brought forward by approximately 25 years in those who had severe strokes, 4 years in those who had minor strokes, and 2 years in those who had transient ischaemic attacks. 5-year risk of dementia was associated with age, event severity, previous stroke, dysphasia, baseline cognition, low education, pre-morbid dependency, leucoaraiosis, and diabetes (p<0·0001 for all comparisons, except for previous stroke [p=0·006]).

Interpretation: The incidence of dementia in patients who have had a transient ischaemic attack or stroke varies substantially depending on clinical characteristics including lesion burden and susceptibility factors. Incidence of dementia is nearly 50 times higher in the year after a major stroke compared with that in the general population, but excess risk is substantially lower after transient ischaemic attack and minor stroke.

Funding: Wellcome Trust, Wolfson Foundation, British Heart Foundation, National Institute for Health Research, and the National Institute for Health Research Oxford Biomedical Research Centre.

Figure 1

Prevalence of pre-event dementia in patients without previous stroke (A), all patients (B), and patients with previous stroke (C), by stroke severity, and in all patients stratified by age and stroke severity (D); and cumulative incidence of dementia, 1 year and 5 years post-event, in patients without previous stroke (E), all patients (F), and patients with previous stroke (G), by stroke severity, and in all patients stratified by age and stroke severity (H) The event is the index transient ischaemic attack or stroke. Patients with pre-event dementia were excluded from estimates of the cumulative incidence of post-event dementia. In (E)–(H), each pair of bars represents the 1-year (left) and 5-year (right) cumulative incidence of dementia. Error bars represent 95% CIs. Note that estimates differ slightly from those shown in figure 2 because the estimates shown here were derived from lifetable analyses. TIA=transient ischaemic attack. NIHSS=US National Institutes of Health Stroke Scale.

Figure 2

Kaplan-Meier curves of cumulative incidence of post-event dementia up to 5-years' follow-up, stratified by event severity The event is the index transient ischaemic attack or stroke. Patients with and without previous stroke were included, but those with pre-event dementia were excluded. TIA=transient ischaemic attack. NIHSS=US National Institutes of Health Stroke Scale.

Figure 3

Prevalence of any dementia in patients 1 year after transient ischaemic attack or stroke and in the UK general population (A), and baseline prevalence of vascular risk factors (B), by age group The event is the index transient ischaemic attack or stroke. (A) Patients with pre-event or post-event dementia are included. Minor stroke was defined as a US National Institutes of Health Stroke Scale score of less than 3, whereas major stroke was defined as a score of 3 or higher. UK population prevalence data are age-matched and sex-matched data calculated from UK population estimates from the Medical Research Council Cognitive Function and Ageing Study., (B) Vascular risk factors included were hypertension, diabetes, hypercholesterolaemia, and current smoking.