Towards a Machine Learning Model for Detection of Dementia Using Lifestyle Parameters

Abstract

The study focuses on Alzheimer’s and dementia detection using machine learning, acknowledging their impact on cognitive health beyond normal aging. Data markers, rather than biomarkers, are preferred for diagnosis, allowing machine learning to play a role. The objective is to design and test a model for early dementia detection using lifestyle data from the National Health and Ageing Trends Study (NHATS). This could aid in flagging high-risk individuals and understanding aging-related parameter changes. Using NHATS data from 5000 individuals aged 60+, encompassing 1288 parameters over a decade, the study shortlists parameters relevant to dementia. Artificial neural networks and random forest techniques are employed to build a model that identifies key dementia-related parameters. Temporal analysis reveals features that exhibit declining social interactions, quality of life, and increased depression as individuals age. Results show the random forest model achieving an accuracy of 80% for dementia risk prediction, with precision, recall, and F1-score values of 0.76, 1, and 0.86, respectively. Temporal analysis offers insights into aging trends and elderly citizens’ lifestyles, using daily activities as parameters. The study concludes that NHATS data analysed using machine learning techniques aids in understanding aging trends and that machine learning models based on identified parameters can non-intrusively assist in clinical dementia diagnosis and trend-based detection.