Comparative study of machine learning methods for modeling associations between risk factors and future dementia cases

A substantial portion of dementia risk can be attributed to modifiable risk factors that can be affected by lifestyle changes. Identifying the contributors to dementia risk could prove valuable. Recently, machine learning methods have been increasingly applied to healthcare data. Several studies have attempted to predict dementia progression by using such techniques. This study aimed to compare the performance of different machine-learning methods in modeling associations between known cognitive risk factors and future dementia cases. A subset of the AGES-Reykjavik Study dataset was analyzed using three machine-learning methods: logistic regression, random forest, and neural networks. Data were collected twice, approximately five years apart. The dataset included information from 1,491 older adults who underwent a cognitive screening process and were considered to have healthy cognition at baseline. Cognitive risk factors included in the models were based on demographics, MRI data, and other health-related data. At follow-up, participants were re-evaluated for dementia using the same cognitive screening process. Various performance metrics for all three machine learning algorithms were assessed. The study results indicate that a random forest algorithm performed better than neural networks and logistic regression in predicting the association between cognitive risk factors and dementia. Compared to more traditional statistical analyses, machine-learning methods have the potential to provide more accurate predictions about which individuals are more likely to develop dementia than others.

Exposure factors associated with dementia among older adults in Iceland: the AGES-Reykjavik study

The study aimed to assess whether factors related to cognitive performance were associated with the development of dementia. Additionally, the study aimed to establish whether cognitive performance at baseline or change in cognition between baseline and follow-up (five-year period) had a stronger association with whether an individual would fulfill a dementia criterion at follow-up. The data was collected from 2002 to 2011. Logistic regression was applied to the AGES-Reykjavik Study epidemiological data. The analysis, which builds upon previous data analyses of the same dataset, included 1,491 participants between the ages of 66 and 90. All those included were considered to have normal cognition at baseline; 8.2% (n = 123) of them fulfilled a dementia criterion at follow-up five years later. The study's results indicated that being high on cognitive reserve factors reduced the risk of developing dementia. Compared to other known dementia risk factors, cognitive reserve factors (education level, participation in leisure activities, and self-reported health) were more likely than others to have an association with dementia. Additionally, the study's findings showed that cognitive performance at baseline, rather than change in cognition between baseline and follow-up five years later, had a stronger association with dementia at the follow-up assessment. Together, these findings support the notion that promoting high cognitive reserve throughout the lifespan and reaching high cognitive performance is important in reducing dementia risk.

Cognition and brain health among older adults in Iceland: the AGES-Reykjavik study

The paper aimed to compare how factors previously identified as predictive factors for cognitive decline and dementia related to cognitive performance on the one hand and brain health on the other. To that aim, multiple linear regression was applied to the AGES-Reykjavik study epidemiological data. Additionally, a regression analysis was performed for change in cognition over 5 years, using the same exposure factors. The study ran from 2002 to 2011, and the sample analyzed included 1707 participants between the ages of 66 and 90. The data contains MR imaging, cognitive testing, background data, and physiological measurements. Overall, we conclude that risk factors linked to dementia relate differently to cognition and brain health. Mobility, physical strength, alcohol consumption, coronary artery disease, and hypertension were associated with cognition and brain volume. Smoking, depression, diabetes, and body fat percentage were only associated with brain volume, not cognitive performance. Modifiable factors previously linked to cognitive reserve, such as educational attainment, participation in leisure activities, multilingualism and good self-reported health, were associated with cognitive function but did not relate to brain volume. These findings show that, within the same participant pool, cognitive reserve proxy variables have a relationship with cognitive performance but have no association with relative brain volume measured simultaneously.