Variable interactions in risk factors for dementia

Abstract

Abstract-Current estimates predict 1 in 3 people born today will develop dementia, suggesting a major impact on future population health. As such, research needs to connect specialist clinicians, data scientists and the general public. The In-MINDD project seeks to address this through the provision of a Profiler, a socio-technical information system connecting all three groups. The public interact, providing raw data; data scientists develop and refine prediction algorithms; and clinicians use in-built services to inform decisions. Common across these groups are Risk Factors, used for dementia-free survival prediction. Risk interactions could greatly inform prediction but determining these interactions is a problem underpinned by massive numbers of possible combinations. Our research employs a machine learning approach to automatically select best performing hyperparameters for prediction and learns variable interactions in a non-linear survival-analysis paradigm. Demonstrating effectiveness, we evaluate this approach using longitudinal data with a relatively small sample size.

A Machine Learning Approach towards Detecting Dementia based on its Modifiable Risk Factors

“…Their best overall accuracies range between 65% and 92%. Moreover, the results of this study were better than a previous study that used a machine learning approach with modifiable risk factors, where their best accuracy reaches 75.24% only [15]. However, this is not considered as a complete comparison as the other studies used different datasets.…”

“…Two main studies used machine learning techniques to detect dementia's risk factors and predict dementia risk accordingly [15], [16]. Both studies applied their analysis to one longitudinal cohort study with a relatively small size (i.e., 840 and 746 subjects respectively).…”

“…Both studies applied their analysis to one longitudinal cohort study with a relatively small size (i.e., 840 and 746 subjects respectively). O'Donoghue, et al [15] applied a non-linear dementia survival prediction model with a multilayer perceptron (MLP), which is an artificial neural network (ANN), and used both modifiable and non-modifiable risk factors defined in the In-MINDD project [5]. They also examined the hidden layers to extract different clusters of risk factors and explore different interactions between them.…”

Prevalence and population attributable fractions of potentially modifiable risk factors for dementia in Canada: a cross-sectional analysis of the Canadian Longitudinal Study on Aging

“…The differences between the magnitude of the weighted multiplicative and additive combined PAFs are meaningful and ultimately rooted in strong assumptions of the form of interactivity of risk factors within individuals. Interactions between multiple risk factors for dementia is highly complex and the form of the interactions likely vary by each distinct set of risk factors present 26,30,31 . While we believe these combined PAF estimates are useful benchmarks, we have limited evidence on how multiple modifiable risk factors for dementia interact with each other and more research on dementia risk factor interaction could improve future estimation of their combined impact.…”