Brain-age predicts subsequent dementia in memory clinic patients

Abstract

AbstractINTRODUCTIONResearch into quantitative neuroimaging biomarkers of dementia risk rarely uses data representative of everyday clinic practice.METHODSWe analysed T1-weighted MRI scans from memory clinic patients (n=1140; 60.2% female and mean [SD] age of 70.0 [10.8] years) to derive ‘brain-age’, an index of age-related brain health. We determined which patients went on to develop dementia (n=476) via linkage to electronic health records.RESULTSCox regression indicated a 3% increased risk of dementia per brain-PAD year (brain-PAD = brain-age minus chronological age), HR(95% CI)=1.03(1.02, 1.04), p<0.001, adjusted for age, age2, sex, MMSE and normalised brain volume. Brain-PAD remained significant even with a minimum time-to-diagnosis of 3 years (HR=1.06) and with MMSE score ≥ 27 (HR=1.03).DISCUSSIONMemory clinic patients with older-appearing brains are more likely to receive a subsequent dementia diagnosis. These results from a ‘real-world’ dataset suggest quantitative neuroimaging biomarkers like brain-age could be readily used in the clinic.Research in ContextSYSTEMATIC REVIEWMultiple previous studies were identified that have modelled dementia risk using quantitative neuroimaging, however, screening of participants based on comorbidities and contraindications alongside sociodemographic and healthcare sampling biases, limits the generalisation of these studies to real-world clinical settings. To facilitate better translation from research to the clinic, datasets that are more representative of dementia patient groups are warranted.INTERPRETATIONBrain-age is an index of ‘biological’ age based on a quantitative analysis of T1-weighted MRI scans. Memory clinic patients with biologically older-appearing brains are more likely to receive a subsequent dementia diagnosis, independent of medical history, age, sex, MMSE score and normalised brain volumes. These findings suggest that brain-age has potential to be used early-on in memory clinics as a biomarker to aid detection of patients at high-risk of developing dementia.FUTURE DIRECTIONSDoes the addition of T2-weighted MRI scan information and/or localised brain-age values improve dementia prediction?