Clinical and Functional Outcomes in Faller and Non-Faller Older Adults Clustered by Self-Organizing Maps: A Machine-Learning Approach

Abstract

A wide range of outcomes makes identifying clinical and functional features distinguishing older persons who fall from non-fallers challenging, especially for professionals with less clinical experience. Thus, this study aimed to map a high-dimensional and complex clinical and functional dataset and determine which outcomes better discriminate older adults with and without self-reported falls. For this, clinical, functional, and cognitive outcomes of 60 community-dwelling older adults classified as fallers and non-fallers were selected based on self-report of a single fall in the last 12 months. An unsupervised intelligent algorithm (Self-Organizing Maps—SOM) was used to cluster and topographically represent the data studied. The SOM model mapped and identified two different groups (topographic error: 0.00; sensitivity: 0.77; precision: 0.42; accuracy: 0.53; F1-score: 0.55) based on self-report of a single fall. We concluded that although two distinct groups were mapped and clustered by the SOM, participants were not necessarily fallers or non-fallers. The increased cost of cognitive demands regarding a motor task (Timed Up and Go Test) and the effect of the Trail Making Test (TMT) Part B regarding TMT Part A could discriminate the functional and cognitive patterns in community-dwelling older adults. Therefore, in clinical practice, identifying patterns involving the interaction between cognition and motor skills, even in once-only faller older adults, can be an efficient approach to assessment and, consequently, to compound intervention programs to prevent falls in this population.

Keywords

• falls
• artificial intelligence
• functional mobility
• unsupervised algorithm
• older adults