A mixed methods pilot randomised controlled trial to develop and evaluate the feasibility of a Mediterranean diet and lifestyle education intervention 'THINK-MED' among people with cognitive impairment

Background: Accumulating evidence supports the role of a Mediterranean diet (MD) in cognition, with a greater adherence to a MD associated with reduced dementia risk. It is important to understand how best to achieve behaviour change towards a MD, particularly in non-Mediterranean and high-risk populations. The aim of this study was to evaluate the feasibility of a MD and lifestyle education intervention (THINK-MED) among older adults with cognitive impairment. Methods: Qualitative interviews (Phase I), conducted with mild cognitive impairment (MCI) participants, evaluated the intervention materials to allow refinement before pilot testing. THINK-MED was a 12-month, pilot RCT (Phase II) whereby MCI participants were randomised into one of three groups: education on one occasion vs education staged and supported by a dietitian vs control. The primary outcome was a change in MD score. Secondary outcome measurements were collected to gather data on variability of the outcomes to inform a full trial power calculation and to test their acceptability. Slower recruitment rates necessitated a change in primary outcome to a revised focus primarily on feasibility. A sub-study of the same THINK-MED intervention and data collection measures was also conducted among community-dwelling participants with subjective cognitive impairment (SCI) (NCT03569319). Results: A total of 20 participants (n = 15 MCI; n = 5 SCI) were enrolled in the THINK-MED study. However, there were 10 (50%) participants (n = 9 MCI; n = 1 SCI) who withdrew from the study. Although, those who remained in the intervention rated and evaluated their experience as generally positive, recruitment and retention, especially from a MCI population, was extremely challenging. This highlights the complex needs of this heterogeneous clinical cohort. Recruiting participants from a community-based sample with SCI was more feasible, reaching a wider audience in a shorter time period. There were challenges relating to data collection and incompleteness, with the occurrence of missing data particularly among the questionnaire-based assessments. Conclusions: Owing to the challenges with recruitment and retention of older adults with cognitive impairment in this study, it is difficult to confirm if this intervention is feasible. This research has highlighted considerations for a future trial, including a review of the recruitment strategies used and prioritisation of the outcome measures assessed.