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

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