Towards successful aging classification using machine learning algorithms

Abstract

Background: Aging is a significant risk factor for a majority of chronic diseases and impairments. Increased medical costs brought about by the increasing aging population in the world increases the strain on families and communities. A positive and qualitative perspective on aging is successful aging (SA). Successful aging refers to the state of being free from diseases or impairments that hinder normal functioning, as observed from a biological perspective. This differs from typical aging, which is associated with a gradual decrease in both physical and cognitive capacities as individuals grow older. Methods: In this study, the geriatric data acquired from the Afe Babalola University Multi-System Hospital, Ado-Ekiti was initially prepared, and three fundamental machine learning (ML) techniques such as artificial neural networks, support vector machines, and Naive Bayes—were then constructed using the data from a sample of 2000 individuals. The Rowe and Kahn Model determined that the dataset was SA based on factors such as the absence of fewer than or equivalent to two diseases, quality of life, nutrition, and capacity for everyday activities. Results: According to the experimental findings, the predictive network Artificial Neural Network (ANN) performed better than other models in predicting SA with 100% accuracy, 100% sensitivity, and 100% precision. Conclusions: The results show that ML techniques are useful in assisting social and health policymakers in their decisions on SA. The presented ANN-based method surpasses the other ML models when it comes to classifying people into SA and non-SA categories.