The relationships between sedentary lifestyle, sitting behaviour, and low back pain (LBP) remain controversial. In this study, we investigated the relationship between back pain and occupational sitting habits in 64 call-centre employees. A textile pressure mat was used to evaluate and parameterise sitting behaviour over a total of 400 h, while pain questionnaires evaluated acute and chronic LBP. Seventy-five percent of the participants reported some level of either chronic or acute back pain. Individuals with chronic LBP demonstrated a possible trend (t-test not significant) towards more static sitting behaviour compared to their pain-free counterparts. Furthermore, a greater association was found between sitting behaviour and chronic LBP than for acute pain/disability, which is plausibly due to a greater awareness of pain-free sitting positions in individuals with chronic pain compared to those affected by acute pain.

To analyse and interpret gait patterns in pathological paediatric populations, accurate determination of the timing of specific gait events (e.g. initial contract - IC, or toe-off - TO) is essential. As currently used clinical identification methods are generally subjective, time-consuming, or limited to steps with force platform data, several techniques have been proposed based on processing of marker kinematics. However, until now, validation and standardization of these methods for use in diverse gait patterns remains lacking. 1) What is the accuracy of available kinematics-based identification algorithms in determining the timing of IC and TO for diverse gait signatures? 2) Does automatic identification affect interpretation of spatio-temporal parameters?. 3D kinematic and kinetic data of 90 children were retrospectively analysed from a clinical gait database. Participants were classified into 3 gait categories: group A (toe-walkers), B (flat IC) and C (heel IC). Five kinematic algorithms (one modified) were implemented for two different foot marker configurations for both IC and TO and compared with clinical (visual and force-plate) identification using Bland-Altman analysis. The best-performing algorithm-marker configuration was used to compute spatio-temporal parameters (STP) of all gait trials. To establish whether the error associated with this configuration would affect clinical interpretation, the bias and limits of agreement were determined and compared against inter-trial variability established using visual identification. Sagittal velocity of the heel (Group C) or toe marker configurations (Group A and B) was the most reliable indicator of IC, while the sagittal velocity of the hallux marker configuration performed best for TO. Biases for walking speed, stride time and stride length were within the respective inter-trial variability values. Automatic identification of gait events was dependent on algorithm-marker configuration, and best results were obtained when optimized towards specific gait patterns. Our data suggest that correct selection of automatic gait event detection approach will ensure that misinterpretation of STPs is avoided.

We propose a bottom-up, machine-learning approach, for the objective vestibular and balance diagnostic data of concussion patients, to provide insight into the differences in patients’ phenotypes, independent of existing diagnoses (unsupervised learning). Diagnostic data from a battery of validated balance and vestibular assessments were extracted from the database of the Swiss Concussion Center. The desired number of clusters within the patient database was estimated using Calinski-Harabasz criteria. Complex (self-organizing map, SOM) and standard (k-means) clustering tools were used, and the formed clusters were compared. A total of 96 patients (81.3% male, age (median [IQR]): 25.0[10.8]) who were expected to suffer from sports-related concussion or post-concussive syndrome (52[140] days between diagnostic testing and the concussive episode) were included. The cluster evaluation indicated dividing the data into two groups. Only the SOM gave a stable clustering outcome, dividing the patients in group-1 (n = 38) and group-2 (n = 58). A large significant difference was found for the caloric summary score for the maximal speed of the slow phase, where group-1 scored 30.7% lower than group-2 (27.6[18.2] vs. 51.0[31.0]). Group-1 also scored significantly lower on the sensory organisation test composite score (69.0[22.3] vs. 79.0[10.5]) and higher on the visual acuity (-0.03[0.33] vs. -0.14[0.12]) and dynamic visual acuity (0.38[0.84] vs. 0.20[0.20]) tests. The importance of caloric, SOT and DVA, was supported by the PCA outcomes. Group-1 tended to report headaches, blurred vision and balance problems more frequently than group-2 (>10% difference). The SOM divided the data into one group with prominent vestibular disorders and another with no clear vestibular or balance problems, suggesting that artificial intelligence might help improve the diagnostic process.

Neuromotor pathologies often cause motor deficits and deviations from typical locomotion, reducing the quality of life. Clinical gait analysis is used to effectively classify these motor deficits to gain deeper insights into resulting walking behaviours. To allow the ensemble averaging of spatio-temporal metrics across individuals during walking, gait events, such as initial contact (IC) or toe-off (TO), are extracted through either manual annotation based on video data, or through force thresholds using force plates. This study developed a deep-learning long short-term memory (LSTM) approach to detect IC and TO automatically based on foot-marker kinematics of 363 cerebral palsy subjects (age: 11.8 ± 3.2). These foot-marker kinematics, including 3D positions and velocities of the markers located on the hallux (HLX), calcaneus (HEE), distal second metatarsal (TOE), and proximal fifth metatarsal (PMT5), were extracted retrospectively from standard barefoot gait analysis sessions. Different input combinations of these four foot-markers were evaluated across three gait subgroups (IC with the heel, midfoot, or forefoot). For the overall group, our approach detected 89.7% of ICs within 16ms of the true event with a 18.5% false alarm rate. For TOs, only 71.6% of events were detected with a 33.8% false alarm rate. While the TOE|HEE marker combination performed well across all subgroups for IC detection, optimal performance for TO detection required different input markers per subgroup with performance differences of 5-10%. Thus, deep-learning LSTM based detection of IC events using the TOE|HEE markers offers an automated alternative to avoid operator-dependent and laborious manual annotation, as well as the limited step coverage and inability to measure assisted walking for force plate-based detection of IC events.