Mining geriatric assessment data for in-patient fall prediction models and high-risk subgroups

Abstract

BackgroundHospital in-patient falls constitute a prominent problem in terms of costs and consequences. Geriatric institutions are most often affected, and common screening tools cannot predict in-patient falls consistently. Our objectives are to derive comprehensible fall risk classification models from a large data set of geriatric in-patients' assessment data and to evaluate their predictive performance (aim#1), and to identify high-risk subgroups from the data (aim#2).MethodsA data set of n = 5,176 single in-patient episodes covering 1.5 years of admissions to a geriatric hospital were extracted from the hospital's data base and matched with fall incident reports (n = 493). A classification tree model was induced using the C4.5 algorithm as well as a logistic regression model, and their predictive performance was evaluated. Furthermore, high-risk subgroups were identified from extracted classification rules with a support of more than 100 instances.ResultsThe classification tree model showed an overall classification accuracy of 66%, with a sensitivity of 55.4%, a specificity of 67.1%, positive and negative predictive values of 15% resp. 93.5%. Five high-risk groups were identified, defined by high age, low Barthel index, cognitive impairment, multi-medication and co-morbidity.ConclusionsOur results show that a little more than half of the fallers may be identified correctly by our model, but the positive predictive value is too low to be applicable. Non-fallers, on the other hand, may be sorted out with the model quite well. The high-risk subgroups and the risk factors identified (age, low ADL score, cognitive impairment, institutionalization, polypharmacy and co-morbidity) reflect domain knowledge and may be used to screen certain subgroups of patients with a high risk of falling. Classification models derived from a large data set using data mining methods can compete with current dedicated fall risk screening tools, yet lack diagnostic precision. High-risk subgroups may be identified automatically from existing geriatric assessment data, especially when combined with domain knowledge in a hybrid classification model. Further work is necessary to validate our approach in a controlled prospective setting.

Incidence and characteristic analysis of in-hospital falls after anesthesia

“…We identified four potential independent risk factors for the development of postanesthesia falls from the postanesthesia visit records, namely gender, age, ASA classification, and types of anesthesia techniques. Advanced age has been widely recognized as an independent risk factor for inpatient falls (Marschollek et al 2012 ; Oliver et al 2010 ). In traumatic patients, male gender is associated with high incidence of in-hospital falls (Brown et al 2013 ).…”

Prediction of fall events during admission using eXtreme gradient boosting: a comparative validation study

“…Using an XGB algorithm, this study proposed an automatic assessment tool to accurately detect high-risk groups. Other machine learning approaches have been attempted for identifying patients at risk of falling; however, a comparative validation with current fall risk assessment scales has never been involved 7 .…”

Association between respiratory tract infections and incidence of falls in nursing home residents

“…6, [31][32][33] In our study, 41% of the respondents experienced at least 1 fall during 1 year, but more than 16% of the falls resulted in fractures. Perhaps this large percentage is due to the large proportion of women in the study group (more than 80%).…”