Comparing algorithms for assessing upper limb use with inertial measurement units.

The various existing measures to quantify upper limb use from wrist-worn inertial measurement units can be grouped into three categories: 1) Thresholded activity counting, 2) Gross movement score and 3) machine learning. However, there is currently no direct comparison of all these measures on a single dataset. While machine learning is a promising approach to detecting upper limb use, there is currently no knowledge of the information used by machine learning measures and the data-related factors that influence their performance. The current study conducted a direct comparison of the 1) thresholded activity counting measures, 2) gross movement score,3) a hybrid activity counting and gross movement score measure (introduced in this study), and 4) machine learning measures for detecting upper-limb use, using previously collected data. Two additional analyses were also performed to understand the nature of the information used by machine learning measures and the influence of data on the performance of machine learning measures. The intra-subject random forest machine learning measure detected upper limb use more accurately than all other measures, confirming previous observations in the literature. Among the non-machine learning (or traditional) algorithms, the hybrid activity counting and gross movement score measure performed better than the other measures. Further analysis of the random forest measure revealed that this measure used information about the forearm's orientation and amount of movement to detect upper limb use. The performance of machine learning measures was influenced by the types of movements and the proportion of functional data in the training/testing datasets. The study outcomes show that machine learning measures perform better than traditional measures and shed some light on how these methods detect upper-limb use. However, in the absence of annotated data for training machine learning measures, the hybrid activity counting and gross movement score measure presents a reasonable alternative. We believe this paper presents a step towards understanding and optimizing measures for upper limb use assessment using wearable sensors.

Physiological and Metabolic Responses of Amateur Spinal Cord Injured Wheelchair Racers Participating in a Marathon: A Pilot Observational Study.

OBJECTIVES: We analyzed exercise-related changes in cardiac troponins and other physiological and metabolic parameters in amateur wheelchair racers with spinal cord injury (SCI) participating in a marathon event. METHODS: This pilot, prospective, observational study was conducted at a community marathon event. Fifteen community-living individuals with SCI who had registered to participate in the marathon were recruited for the study. Participants with SCI used manually propelled wheelchairs (n=5) or tricycles (n=10). The outcome measures were high-sensitivity cardiac troponin-T levels (hs-cTnT), heart rate, and metabolic parameters, including body temperature, serum electrolytes, and urine osmolality. These parameters were compared with 15 age- and race-distance-matched non-SCI runners who participated in the same marathon. RESULTS: Participants with SCI had a higher median (inter-quartile range) baseline hs-cTnT level [13.7 ng/L (10.3-25)] than did runners [4.2 ng/L (3.2-8.7; P <0.001)]. Post-race values of hs-cTnT were elevated in participants with SCI [28.0 ng/L (19.0-48.2)] and in runners [41.5 ng/L (18.4-87.1, P= 0.7)]; however, there was no significant difference between the two groups. Other parameters were not significantly different between SCI participants and runners. CONCLUSION: Post-race hs-cTnT levels of amateur SCI participants were elevated but were not significantly different from those of runners. Other race-induced physiological and metabolic changes in SCI participants were comparable to those of runners. The high baseline hs-cTnT levels in participants with SCI observed in this study warrant further research.

Quantification of the relative arm use in patients with hemiparesis using inertial measurement units.

INTRODUCTION: Accelerometry-based activity counting for measuring arm use is prone to overestimation due to non-functional movements. In this paper, we used an inertial measurement unit (IMU)-based gross movement (GM) score to quantify arm use. METHODS: In this two-part study, we first characterized the GM by comparing it to annotated video recordings of 5 hemiparetic patients and 10 control subjects performing a set of activities. In the second part, we tracked the arm use of 5 patients and 5 controls using two wrist-worn IMUs for 7 and 3 days, respectively. The IMU data was used to develop quantitative measures (total and relative arm use) and a visualization method for arm use. RESULTS: From the characterization study, we found that GM detects functional activities with 50-60% accuracy and eliminates non-functional activities with >90% accuracy. Continuous monitoring of arm use showed that the arm use was biased towards the dominant limb and less paretic limb for controls and patients, respectively. CONCLUSIONS: The gross movement score has good specificity but low sensitivity in identifying functional activity. The at-home study showed that it is feasible to use two IMU-watches to monitor relative arm use and provided design considerations for improving the assessment method.Clinical trial registry number: CTRI/2018/09/015648.

Survival in persons with traumatic spinal cord injury receiving structured follow-up in South India.

OBJECTIVE: To assess the survival in persons with traumatic spinal cord injury (SCI) receiving structured follow-up in South India. DESIGN: Retrospective study. SETTING: Rehabilitation center. PARTICIPANTS: Persons with traumatic SCI (N=490) residing within a 100-km radius of the institute who were managed and regularly followed up by the rehabilitation center between the years 1981 and 2011. INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: Survival rates and mortality risk factors. Measures were estimated using the product limit (Kaplan-Meier) method and the Cox model. RESULTS: The survival rate after SCI was 86% after 5 years, 71% after 15 years, and 58% after 25 years. Survival of persons with complete high cervical injury is substantially low compared with other levels of SCI. Level of injury and extent of lesion (Frankel classification and/or American Spinal Injury Association Impairment Scale) play a significant role in predicting survival of this population. CONCLUSIONS: Survival rates of regularly followed-up persons with SCI from this study show promising results, though survival rates are lesser when compared with studies from developed countries. Better understanding of the predictors, causes of deaths, comprehensive rehabilitation, community integration, and regular follow-up could possibly assist in improving survival rates.