Trail walking test for assessment of motor cognitive interference in older adults. Development and evaluation of the psychometric properties of the procedure

Activities of daily living (ADL), such as walking, often involve the added complexity of walking while doing other activities (i.e. dual task walking). A complex walking task may require a greater motor and mental capacity, resulting in decrements in gait performance not seen for simple walking tasks. The purpose of this study was to determine if the trail walking test (TWT), the mobile adaptation of the trail making test (TMT), could be a reliable and valid early detection tool to discriminate between non-fallers and fallers. This study examined dual task costs of a cognitive and a sensorimotor task (walking) in 94 older adults aged 50-81 years (average age M = 67.4 years, SD +/- 7.34). Based on the idea of the paper and pencil TMT, participants walked along a fixed pathway (TWT-1), stepped on targets with increasing sequential numbers (i.e. 1, 2, 3, TWT-2), and increasing sequential numbers and letters (i.e. 1, A, 2, B, 3, C, TWT-3). The dual task costs were calculated for each task. Additionally, the following tests were conducted: TMT, block tapping test (BTT), timed up and go (TUG) test, 30s chair rising test, 10 m walking time test with and without head turns, German physical activity questionnaire (German PAQ-50 +) and the activities-specific balance confidence (ABC-D) scale. The TWT performance times as well as errors increased with increasing age. Reliability coefficients were high (interclass correlation ICC > 0.90). Correlations between the different TWT conditions and potential falls-related predictors were moderate to high (r = -0.430 to 0.699). Of the participants 34 % reported falling in the past year. The stepwise logistic regression analysis revealed that the dual task costs for the numbers and letters (odds ratio OR 1.162, 95 % confidence interval CI 1.058-1.277, p = 0.002), the ABC-D (OR 0.767, 95 % CI 0.651-0.904, p = 0.002) and exercise (OR 1.027, 95 % CI 1.008-1.046, p = 0.006) were significantly related to falls and 91.6 % of cases were correctly classified. The results indicate that high-level cognitive processes interfere with automatic processes such as walking. The TWT which converts a relevant fall risk-associated standard neuropsychological test (TMT) with increasing cognitive load into a mobility task, was shown to be a feasible, reliable and valid tool for older adults to discriminate between non-fallers and fallers.