This is a retrospective cohort study based on data from five nursing homes which aims to appraise how physical and cognitive characteristics of nursing home residents were associated with the use of restraints, and to provide information on their prevalence in Spain. The goal was to assess, in a visual way, the possible interactions between the nursing homes residents’ characteristics and their association with the use of restraints. Motivation, risk factors, characteristics of the residents analysed by validated rating systems that assess mobility, level of dependence, cognitive condition and nutritional status, and their association with the use of restraints, were described by means of linear and non-linear multivariate approaches in the form of self-organised maps. Findings showed that the prevalence of restraints was high when compared to other developed countries. The visual analysis reinforced the knowledge that a greater impairment was associated with the use of restraints andvice versa. However, the residents’ characteristics were not always associated with the use of restraints. Subjective factors seem to play a relevant role in decision-making, so it is important to assess risk factors continuously and determine the actual need for the use of restraints from an individual perspective by basing the criteria on specific objectives, and on consistent, reproducible and reliable methods. Initiatives to minimise these subjective factors should be promoted. Likewise, a clear definition of physical restraints should be offered at each centre. In addition, effective legislation that clearly states the need, alternatives and motivation for the use of restraints is needed.