The objective of this study was to use machine learning to identify feelings of energy and fatigue using single-task walking gait. Participants (n = 126) were recruited from a university community and completed a single protocol where current feelings of energy and fatigue were measured using the Profile of Moods Survey–Short Form approximately 2 min prior to participants completing a two-minute walk around a 6 m track wearing APDM mobility monitors. Gait parameters for upper and lower extremity, neck, lumbar and trunk movement were collected. Gradient boosting classifiers were the most accurate classifiers for both feelings of energy (74.3%) and fatigue (74.2%) and Random Forest Regressors were the most accurate regressors for both energy (0.005) and fatigue (0.007). ANCOVA analyses of gait parameters comparing individuals who were high or low energy or fatigue suggest that individuals who are low energy have significantly greater errors in walking gait compared to those who are high energy. Individuals who are high fatigue have more symmetrical gait patterns and have trouble turning when compared to their low fatigue counterparts. Furthermore, these findings support the need to assess energy and fatigue as two distinct unipolar moods as the signals used by the algorithms were unique to each mood.

Balance and gait assessments are commonly implemented to screen for injury risks and function by clinicians. Recent evidence in older adults suggests that feelings of energy and fatigue influence gait and balance however, there is limited evidence on the influence of these moods on gait and balance in young adults. Therefore, the purpose of this study was to examine the relationship of self-reported feelings of fatigue and energy on characteristics of gait and balance in healthy young adults. Participants (n = 97) completed the experimental procedure in a single testing session. Feelings of energy and fatigue were measured using the 30-item Profile of Mood States-Short Form. Participants were fitted with inertial sensors then completed a modified Clinical Test for Sensory Interaction and Balance to assess balance and walked for 2 minutes around a 6m track. Backwards multiple linear regression models were used to test associations between selfreported fatigue and energy with balance and gait characteristics. The backwards regression models with gait characteristic predicted 9.1% and 20.0% variance for fatigue and energy, respectively. Feelings of fatigue significantly impacted balance variables only when subjects stood on a firm surface with their eyes open however, feelings of energy significantly influenced balance variables when eyes were open both on firm and a foam surface. Neither mood influenced balance in either of the vision occluded conditions. Findings suggest that feelings of fatigue and energy uniquely impact gait characteristics and balance of healthy young adults, furthering our understanding of energy and fatigue as separate moods.

Literature suggests that anxiety affects gait and balance among young adults. However, previous studies using machine learning (ML) have only used gait to identify individuals who report feeling anxious. Therefore, the purpose of this study was to identify individuals who report feeling anxious at that time using a combination of gait and quiet balance ML. Using a cross-sectional design, participants (n = 88) completed the Profile of Mood Survey-Short Form (POMS-SF) to measure current feelings of anxiety and were then asked to complete a modified Clinical Test for Sensory Interaction in Balance (mCTSIB) and a two-minute walk around a 6 m track while wearing nine APDM mobility sensors. Results from our study finds that Random Forest classifiers had the highest median accuracy rate (75%) and the five top features for identifying anxious individuals were all gait parameters (turn angles, variance in neck, lumbar rotation, lumbar movement in the sagittal plane, and arm movement). Post-hoc analyses suggest that individuals who reported feeling anxious also walked using gait patterns most similar to older individuals who are fearful of falling. Additionally, we find that individuals who are anxious also had less postural stability when they had visual input; however, these individuals had less movement during postural sway when visual input was removed.

Failure to obtain the recommended 7–9 h of sleep has been associated with injuries in youth and adults. However, most research on the influence of prior night’s sleep and gait has been conducted on older adults and clinical populations. Therefore, the objective of this study was to identify individuals who experience partial sleep deprivation and/or sleep extension the prior night using single task gait. Participants (n = 123, age 24.3 ± 4.0 years; 65% female) agreed to participate in this study. Self-reported sleep duration of the night prior to testing was collected. Gait data was collected with inertial sensors during a 2 min walk test. Group differences (9 h, poor sleepers; 7–9 h, good sleepers) in gait characteristics were assessed using machine learning and a post-hoc ANCOVA. Results indicated a correlation (r = 0.79) between gait parameters and prior night’s sleep. The most accurate machine learning model was a Random Forest Classifier using the top 9 features, which had a mean accuracy of 65.03%. Our findings suggest that good sleepers had more asymmetrical gait patterns and were better at maintaining gait speed than poor sleepers. Further research with larger subject sizes is needed to develop more accurate machine learning models to identify prior night’s sleep using single-task gait.