The Trail Making test: a study of its ability to predict falls in the acute neurological in-patient population.

OBJECTIVE: To determine whether tests of cognitive function and patient-reported outcome measures of motor function can be used to create a machine learning-based predictive tool for falls. DESIGN: Prospective cohort study. SETTING: Tertiary neurological and neurosurgical center. SUBJECTS: In all, 337 in-patients receiving neurosurgical, neurological, or neurorehabilitation-based care. MAIN MEASURES: Binary (Y/N) for falling during the in-patient episode, the Trail Making Test (a measure of attention and executive function) and the Walk-12 (a patient-reported measure of physical function). RESULTS: The principal outcome was a fall during the in-patient stay ( n = 54). The Trail test was identified as the best predictor of falls. Moreover, addition of other variables, did not improve the prediction (Wilcoxon signed-rank P < 0.001). Classical linear statistical modeling methods were then compared with more recent machine learning based strategies, for example, random forests, neural networks, support vector machines. The random forest was the best modeling strategy when utilizing just the Trail Making Test data (Wilcoxon signed-rank P < 0.001) with 68% (± 7.7) sensitivity, and 90% (± 2.3) specificity. CONCLUSION: This study identifies a simple yet powerful machine learning (Random Forest) based predictive model for an in-patient neurological population, utilizing a single neuropsychological test of cognitive function, the Trail Making test.

A qualitative description of falls in a neuro-rehabilitation unit: the use of a standardised fall report including the International Classification of Functioning (ICF) to describe activities and environmental factors.

PURPOSE: Falls are a recognised problem for people with long-term neurological conditions but less is known about fall risk in young adults. This study describes fallers' and falls' characteristics in adults less than 60 years old, in a neuro-rehabilitation unit. METHODS: This single-centre, longitudinal, observational study included 114 consecutive admissions to a UK neuro-rehabilitation unit over 20 months. The demographic and clinical characteristics of eligible patients included age, sex, diagnosis, hospital length of stay and the Functional Independence Measure (FIM). Falls were recorded prospectively in a fall report, using the activities and environmental domains of the International Classification of Functioning (ICF). RESULTS: A total of 34 (30%) patients reported a fall, with 50% experiencing more than one fall. The majority of falls (60%) occurred during the first 2 weeks, during day-time (90%) and during mobile activities (70%). Overall, falls rate (95% confidence interval) was 1.33 (1.04 to 1.67) per 100 d of patient hospital stay. Factors associated with increased falls included becoming a walker during admission or being cognitively impaired. There were no serious fall-related injuries. CONCLUSION: The first 2 weeks of admission is a high risk time for fallers, in particular those who become walkers or are cognitively impaired. Prevention policies should be put in place based on fall characteristics. Implications for Rehabilitation The ICF is a valuable instrument for describing subject and environmental factors during a fall-event. Falls are frequent events but do not usually cause serious injuries during inpatient rehabilitation. There is an increased fall risk for subjects with cognitive impairments or those relearning how to walk.

Social cognition in Tourette's syndrome: intact theory of mind and impaired inhibitory functioning.

Although associations between social cognition involving theory of mind and non-social executive skills have frequently been reported, dissociations in performance have also been found. The present study was designed to examine social and non-social cognition in uncomplicated Tourette Syndrome (TS). Adult TS participants without comorbid diagnoses were compared to matched healthy control participants on social cognition measures involving theory of mind and empathy, and on non-social executive tasks. Participants with TS were found to make more errors than a matched control group on an inhibitory task, but did not differ on other executive measures or on the social cognition measures. The implications of the findings for our understanding of TS and of the relationship between social cognition and executive skills are discussed.