Using Naturalistic Driving Data to Predict Mild Cognitive Impairment and Dementia: Preliminary Findings from the Longitudinal Research on Aging Drivers (LongROAD) Study

Emerging evidence suggests that atypical changes in driving behaviors may be early signals of mild cognitive impairment (MCI) and dementia. This study aims to assess the utility of naturalistic driving data and machine learning techniques in predicting incident MCI and dementia in older adults. Monthly driving data captured by in-vehicle recording devices for up to 45 months from 2977 participants of the Longitudinal Research on Aging Drivers study were processed to generate 29 variables measuring driving behaviors, space and performance. Incident MCI and dementia cases (n = 64) were ascertained from medical record reviews and annual interviews. Random forests were used to classify the participant MCI/dementia status during the follow-up. The F1 score of random forests in discriminating MCI/dementia status was 29% based on demographic characteristics (age, sex, race/ethnicity and education) only, 66% based on driving variables only, and 88% based on demographic characteristics and driving variables. Feature importance analysis revealed that age was most predictive of MCI and dementia, followed by the percentage of trips traveled within 15 miles of home, race/ethnicity, minutes per trip chain (i.e., length of trips starting and ending at home), minutes per trip, and number of hard braking events with deceleration rates ≥ 0.35 g. If validated, the algorithms developed in this study could provide a novel tool for early detection and management of MCI and dementia in older drivers.

Download Full-text

A Novel Ensemble-Based Machine Learning Algorithm to Predict the Conversion From Mild Cognitive Impairment to Alzheimer's Disease Using Socio-Demographic Characteristics, Clinical Information, and Neuropsychological Measures

Frontiers in Neurology ◽

10.3389/fneur.2019.00756 ◽

2019 ◽

Vol 10 ◽

Cited By ~ 6

Author(s):

Massimiliano Grassi ◽

Nadine Rouleaux ◽

Daniela Caldirola ◽

David Loewenstein ◽

Koen Schruers ◽

...

Keyword(s):

Machine Learning ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Learning Algorithm ◽

Clinical Information ◽

Demographic Characteristics ◽

Machine Learning Algorithm ◽

Neuropsychological Measures

Download Full-text

Comparison of Demographic Characteristics, Comorbidity, and Health Habits of Older Adults with Mild Cognitive Impairment and Older Adults with Normal Cognitive Function

Journal of Korean Academy of Nursing ◽

10.4040/jkan.2014.44.4.351 ◽

2014 ◽

Vol 44 (4) ◽

pp. 351 ◽

Cited By ~ 9

Author(s):

Myonghwa Park ◽

Mi Ra Sung ◽

Sun Kyung Kim ◽

Dong Young Lee

Keyword(s):

Older Adults ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Cognitive Function ◽

Demographic Characteristics ◽

Health Habits ◽

Normal Cognitive Function

Download Full-text

Race/Ethnic Disparities in Mild Cognitive Impairment and Dementia: The Northern Manhattan Study

10.1101/2020.11.07.20210872 ◽

2020 ◽

Author(s):

Clinton B. Wright ◽

Janet T. DeRosa ◽

Michelle P. Moon ◽

Kevin Strobino ◽

Charles DeCarli ◽

...

Keyword(s):

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

White Matter ◽

White Matter Hyperintensity ◽

Prevalence Rates ◽

Vascular Risk ◽

Community Based ◽

Diverse Community ◽

Race Ethnicity

ABSTRACTOBJECTIVEEstimate the prevalence of mild cognitive impairment (MCI) and probable dementia in the racially and ethnically diverse community-based Northern Manhattan Study cohort and examine sociodemographic, vascular risk factor, and brain imaging correlates.METHODSCases of MCI and probable dementia were adjudicated by a team of neuropsychologists and neurologists and prevalence was estimated across race/ethnic groups. Ordinal proportional odds models were used to estimate race/ethnic differences in prevalence rates for MCI or probable dementia adjusting for sociodemographic variables (model 1), model 1 plus potentially modifiable vascular risk factors (model 2), and model 1 plus structural imaging markers of brain integrity (model 3).RESULTSThere were 989 participants with cognitive outcome determinations (mean age 69 ± 9 years; 68% Hispanic, 16% Black, 14% White; 62% women; mean (±SD) follow-up five (±0.6) years). Prevalence rates for MCI (20%) and probable dementia (5%) were significantly different by race/ethnicity even after accounting for age and education difference across race-ethnic groups; Hispanic and Black participants had greater prevalence rates than Whites. Adjusting for sociodemographic and brain imaging factors explained the most variance in the race/ethnicity associations. White matter hyperintensity burden explained much of the disparity between Black and White, but not between Hispanic and White, participants.CONCLUSIONSIn this diverse community-based cohort, white matter hyperintensity burden partially explained disparities in MCI and dementia prevalence in Black but not Hispanic participants compared to Whites. Longer follow-up and incidence data are needed to further clarify these relationships.

Download Full-text

A Prediction Model for Mild Cognitive Impairment Using Random Forests

International Journal of Advanced Computer Science and Applications ◽

10.14569/ijacsa.2015.061202 ◽

2015 ◽

Vol 6 (12) ◽

Cited By ~ 8

Author(s):

Haewon Byeon

Keyword(s):

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Prediction Model ◽

Random Forests

Download Full-text

Food Insecurity Is Associated with Mild Cognitive Impairment among Middle-Aged and Older Adults in South Africa: Findings from a Nationally Representative Survey

Nutrients ◽

10.3390/nu11040749 ◽

2019 ◽

Vol 11 (4) ◽

pp. 749 ◽

Cited By ~ 5

Author(s):

Ai Koyanagi ◽

Nicola Veronese ◽

Brendon Stubbs ◽

Davy Vancampfort ◽

Andrew Stickley ◽

...

Keyword(s):

South Africa ◽

Older Adults ◽

Cognitive Impairment ◽

Mild Cognitive Impairment ◽

Food Insecurity ◽

Longitudinal Research ◽

World Health ◽

Multivariable Logistic Regression Analysis ◽

Adult Health ◽

Cross Sectional

There are no studies on the association between food insecurity and mild cognitive impairment (MCI). Thus, cross-sectional, community-based data on individuals aged ≥50 years from the World Health Organization’s Study on Global AGEing and Adult Health (SAGE) conducted in South Africa (2007–2008) were analyzed to assess this association. The definition of MCI was based on the National Institute on Ageing-Alzheimer’s Association criteria. Past 12-month food insecurity was assessed with two questions on frequency of eating less and hunger due to lack of food. Multivariable logistic regression analysis was conducted. The sample consisted of 3,672 individuals aged ≥50 years [mean (SD) age 61.4 (18.3); 56% females]. The prevalence of MCI was 8.5%, while 11.0% and 20.8% experienced moderate and severe food insecurity, respectively. After adjustment for potential confounders, moderate and severe food insecurity were associated with 2.82 (95%CI = 1.65–4.84) and 2.51 (95%CI = 1.63–3.87) times higher odds for MCI compared with no food insecurity, respectively. The OR for those aged ≥65 years with severe food insecurity was particularly high (OR = 3.87; 95%CI = 2.20–6.81). In conclusion, food insecurity was strongly associated with MCI among South African older adults. Future longitudinal research is required to assess whether addressing food insecurity may reduce risk of MCI and subsequent dementia.

Download Full-text