RESUMO
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).
Assuntos
Doença de Alzheimer , Peptídeos beta-Amiloides , Encéfalo , Disfunção Cognitiva , Humanos , Idoso , Feminino , Masculino , Doença de Alzheimer/diagnóstico , Disfunção Cognitiva/diagnóstico , Peptídeos beta-Amiloides/líquido cefalorraquidiano , Estados Unidos , Biomarcadores , Tomografia por Emissão de Pósitrons , Aprendizado de Máquina , Idoso de 80 Anos ou mais , National Institutes of Health (U.S.) , Testes Neuropsicológicos , Placa AmiloideRESUMO
BACKGROUND: Many Alzheimer's Disease (AD) clinical trials have failed to demonstrate treatment efficacy on cognition. It is conceivable that a complex disease like AD may not have the same treatment effect due to many heterogeneities of disease processes and individual traits. OBJECTIVES: We employed an individual-level treatment response (ITR) approach to determine the characteristics of treatment responders and estimated time saved in cognitive decline using the Internet-based Conversational Engagement Clinical Trial (I-CONECT) behavioral intervention study as a model. DESIGN AND SETTING: I-CONECT is a multi-site, single-blind, randomized controlled trial aimed to improve cognitive functions through frequent conversational interactions via internet/webcam. The experimental group engaged in video chats with study staff 4 times/week for 6 months; the control group received weekly 10-minute check-in phone calls. PARTICIPANTS: Out of 186 randomized participants, current study used 139 participants with complete information on both baseline and 6-month follow-up (73 with mild cognitive impairment (MCI), 66 with normal cognition; 64 in the experimental group, and 75 in the control group). MEASUREMENTS: ITR scores were generated for the Montreal Cognitive Assessment (MoCA) (global cognition, primary outcome) and Category Fluency Animals (CFA) (semantic fluency, secondary outcome) that showed significant efficacy in the trial. ITR scores were generated through 300 iterations of 3-fold cross-validated random forest models. The average treatment difference (ATD) curve and the area between the curves (ABC) were estimated to measure the heterogeneity of treatment responses. Responder traits were identified using SHapley Additive exPlanations (SHAP) and decision tree models. The time saved in cognitive decline was explored to gauge clinical meaningfulness. RESULTS: ABC statistics showed substantial heterogeneity in treatment response with MoCA but modest heterogeneity in treatment response with CFA. Age, cognitive status, time spent with family and friends, education, and personality were important characteristics that influenced treatment responses. Intervention group participants in the upper 30% of ITR scores demonstrated potential delays of 3 months in semantic fluency (CFA) and 6 months in global cognition (MoCA), assuming a 5-fold faster natural cognitive decline compared to the control group during the post-treatment period. CONCLUSIONS: ITR-based analyses are valuable in profiling treatment responders for features that can inform future trial design and clinical practice. Reliably measuring time saved in cognitive decline is an area of ongoing research to gain insight into the clinical meaningfulness of treatment.