Data science approaches to the study of multimorbidity patterns at older ages

Introduction One key factor to construct appropriate and sustainable healthcare plans for aging populations is the possibility of identifying precise multimorbidity patterns and seizing their progression in time, so that groups of individuals with different degrees of vulnerability can be recognized and provided with assistance in a timely manner. The primary objective of this work is to characterize the complex network of multimorbidities among older adults in Europe identifying common multimorbidity clusters and their associations with demographic variables such as age and gender. The analysis utilizes data from the Survey on Health, Aging and Retirement in Europe (SHARE), wave 7 and wave 9, combining empirical data with innovative methodological approaches, based on the application of Mixed Graphical Models (MGM). MGM networking methods excel in identifying both direct and indirect relationships between multimorbidities considering the entire network of conditions simultaneously. This can reveal dependencies and interactions that may not be apparent through conventional statistical analyses.