Predicting Brain Amyloid Status Using the National Institute of Health Toolbox (NIHTB) for Assessment of Neurological and Behavioral Function.

BACKGROUND: Amyloid-beta (Aß) plaque is a neuropathological hallmark of Alzheimer's disease (AD). As anti-amyloid monoclonal antibodies enter the market, predicting brain amyloid status is critical to determine treatment eligibility. OBJECTIVE: To predict brain amyloid status utilizing machine learning approaches in the Advancing Reliable Measurement in Alzheimer's Disease and Cognitive Aging (ARMADA) study. DESIGN: ARMADA is a multisite study that implemented the National Institute of Health Toolbox for Assessment of Neurological and Behavioral Function (NIHTB) in older adults with different cognitive ability levels (normal, mild cognitive impairment, early-stage dementia of the AD type). SETTING: Participants across various sites were involved in the ARMADA study for validating the NIHTB. PARTICIPANTS: 199 ARMADA participants had either PET or CSF information (mean age 76.3 ± 7.7, 51.3% women, 42.3% some or complete college education, 50.3% graduate education, 88.9% White, 33.2% with positive AD biomarkers). MEASUREMENTS: We used cognition, emotion, motor, sensation scores from NIHTB, and demographics to predict amyloid status measured by PET or CSF. We applied LASSO and random forest models and used the area under the receiver operating curve (AUROC) to evaluate the ability to identify amyloid positivity. RESULTS: The random forest model reached AUROC of 0.74 with higher specificity than sensitivity (AUROC 95% CI:0.73 - 0.76, Sensitivity 0.50, Specificity 0.88) on the held-out test set; higher than the LASSO model (0.68 (95% CI:0.68 - 0.69)). The 10 features with the highest importance from the random forest model are: picture sequence memory, cognition total composite, cognition fluid composite, list sorting working memory, words-in-noise test (hearing), pattern comparison processing speed, odor identification, 2-minutes-walk endurance, 4-meter walk gait speed, and picture vocabulary. Overall, our model revealed the validity of measurements in cognition, motor, and sensation domains, in associating with AD biomarkers. CONCLUSION: Our results support the utilization of the NIH toolbox as an efficient and standardizable AD biomarker measurement that is better at identifying amyloid negative (i.e., high specificity) than positive cases (i.e., low sensitivity).

NMR metabolomic modeling of age and lifespan: A multicohort analysis.

Metabolomic age models have been proposed for the study of biological aging, however, they have not been widely validated. We aimed to assess the performance of newly developed and existing nuclear magnetic resonance spectroscopy (NMR) metabolomic age models for prediction of chronological age (CA), mortality, and age-related disease. Ninety-eight metabolic variables were measured in blood from nine UK and Finnish cohort studies (N ≈31,000 individuals, age range 24-86 years). We used nonlinear and penalized regression to model CA and time to all-cause mortality. We examined associations of four new and two previously published metabolomic age models, with aging risk factors and phenotypes. Within the UK Biobank (N ≈102,000), we tested prediction of CA, incident disease (cardiovascular disease (CVD), type-2 diabetes mellitus, cancer, dementia, and chronic obstructive pulmonary disease), and all-cause mortality. Seven-fold cross-validated Pearson's r between metabolomic age models and CA ranged between 0.47 and 0.65 in the training cohort set (mean absolute error: 8-9 years). Metabolomic age models, adjusted for CA, were associated with C-reactive protein, and inversely associated with glomerular filtration rate. Positively associated risk factors included obesity, diabetes, smoking, and physical inactivity. In UK Biobank, correlations of metabolomic age with CA were modest (r = 0.29-0.33), yet all metabolomic model scores predicted mortality (hazard ratios of 1.01 to 1.06/metabolomic age year) and CVD, after adjustment for CA. While metabolomic age models were only moderately associated with CA in an independent population, they provided additional prediction of morbidity and mortality over CA itself, suggesting their wider applicability.