A Predictive Model for Automatic Detection of Loneliness and Social Isolation Using Machine Learning

Amado Scott Bello-Valle, Alicia Martínez-Rebollar, Wendy Sánchez, Hugo Estrada-Esquivel


In Mexico, elderly is the group with the highest growth rate in the entire country. In 2010, the elderly represented 8.8% of the population and it is estimated that by 2050, they will represent 28% of the estimated population. This demographic change represents several challenges for current social programs that intend to maintain the independence of elderly in families and in their community. The problem of the development of emotional and psychological disorders in older adults can be associated with the prevalence of affective, cognitive, and behavioral disorders. In most cases, these medical conditions are not properly diagnosed or treated. This situation is currently a research topic of novel approaches to improve the well-being and quality of life of this segment of the population. The objective of research work presented in this paper is to develop a predictive model of loneliness and social isolation from the information obtained from the monitoring of the daily activities of an older adult.


Predictive model, loneliness, social isolation, elderly

Full Text: PDF