Big Data Analytical Approaches to the NACC Dataset

Abstract

Background Clinical trials increasingly aim to retard disease progression during pre-symptomatic phases of Mild Cognitive Impairment (MCI) and thus recruiting study participants at high risk for developing MCI is critical for cost-effective prevention trials. However, accurately identifying those who are destined to develop MCI is difficult. Collecting biomarkers is often expensive. Methods We used only non-invasive clinical variables collected in the National Alzheimer’s Coordinating Center (NACC) Uniform Data Sets version 2.0 and applied machine learning techniques to build a low-cost and accurate Mild Cognitive Impairment (MCI) conversion prediction calculator. Cross-validation and bootstrap were used to select as few variables as possible accurately predicting MCI conversion within 4 years. Results 31,872 unique subjects, 748 clinical variables and additional 128 derived variables in NACC data sets were used. 15 non-invasive clinical variables are identified for predicting MCI/aMCI/naMCI converters, respectively. Over 75% Receiver Operating Characteristic Area Under the Curves (ROC AUC) was achieved. By bootstrap we created a simple spreadsheet calculator which estimates the probability of developing MCI within 4 years with a 95% confidence interval. Conclusions We achieved reasonably high prediction accuracy using only clinical variables. The approach used here could be useful for study enrichment in pre-clinical trials where enrolling participants at risk of cognitive decline is critical for proving study efficacy, and also for developing a shorter assessment battery.

Version 3 of the National Alzheimer’s Coordinating Center’s Uniform Data Set

“…Early papers using the UDS were limited in terms of sample size and tended to focus on descriptions of the UDS sample or various methodological issues. In contrast, papers published using the UDS data in the first quarter of 2018 16–32 investigated a wide range of topics, such as inappropriate medication use among those with incident dementia 27 , TBI history and early age of onset in autopsy-confirmed AD 28 , big data approaches to preclinical trial enrichment 24 , and predicting sex differences in MCI and AD using data on white matter hyperintensities and hippocampal volume. 17 Thus, the demonstrated increase in publications using UDS data suggest that the UDS revisions described in this article have tailored the standardized data collection to measures that are more useful for researchers.…”

Antiviral therapy: Valacyclovir Treatment of Alzheimer’s Disease (VALAD) Trial: protocol for a randomised, double-blind,placebo-controlled, treatment trial

“…The study physician will complete the NACC (Version 2) Forms that take 35–40 min and include history, neurological exam with assessment of Parkinsonian signs, psychiatric assessment that includes the short version of the Geriatric Depression Scale and the Neuropsychiatric Inventory, Functional Activities Questionnaire (administered to the caregiver), vascular risk factors and the modified Hachinski ischaemic scale 45…”

“…Neuropsychological test battery (based on NACC-Uniform Data Set Version 3): Montreal Cognitive Assessment, Number Span Test Forward and Backward, Category Fluency for animals and vegetables, Craft Story21 immediate and delayed recall, Benson Complex Figure Immediate and Delayed Recall, Trail Making A and B, Multilingual Naming Test, Verbal Fluency F and L 45. This test battery is given for diagnostic purposes at baseline, 52 and 78 weeks.…”

The Pathology of Rapid Cognitive Decline in Clinically Diagnosed Alzheimer’s Disease

“…Thyroid disease is also not parsed out into hypo/hyperthyroidism in NACC; prospective data collection would be required to obtain this data. It should also be taken into consideration that the NACC database subject education is likely above the population average, thus potentially limiting the generalizability of results [25].…”