Complementary value of molecular, phenotypic and functional aging biomarkers in dementia prediction

DNA methylation age (MA), brain age (BA), and frailty index (FI) are putative aging biomarkers linked to dementia risk. We investigated their relationship and combined potential for prediction of stages of cognitive impairment and future risk of dementia using the ADNI database. Of several MA algorithms, DunedinPACE had the strongest association with neuropsychological tests and was included alongside BA and FI in predictive analyses. The pairwise correlations between age- and sex-adjusted measures for MA (aDundedinPACE), brain age (aBA), and frailty (aFI) were low (all <0.15). In a prediction model including age, sex, and aFI, we achieved an area under the curve (AUC) of 0.95 for differentiating cognitively normal controls (CN) from dementia patients in a held-out test set. The best models for CN vs. mild cognitive impairment (MCI) and MCI vs. dementia contained age, sex, aFI and aBA as predictors, and achieved out-of-sample AUCs of 0.82 and 0.83 respectively. When combined with clinical biomarkers (apolipoprotein E ε4 allele count, memory, executive function), a model including aBA and aFI predicted 5-year dementia risk among MCI patients with an out-of-sample AUC of 0.83. aDunedinPACE did not improve the predictions. FI had a stronger adverse effect on prognosis in males, while BA's impact was greater in females. Our findings highlight complementary value of BA and FI in dementia prediction. The results support a multidimensional view of dementia, including an intertwined relationship between the biomarkers, sex, and prognosis. The tested MA's limited contribution suggests caution in their use for individual risk assessment of dementia.