Abstract
Objective
To determine if functional measures of ambulation can be accurately classified using
clinical measures; demographics; personal, psychosocial, and environmental factors;
and limb accelerations (LAs) obtained during sleep among individuals with chronic,
motor incomplete spinal cord injury (SCI) in an effort to guide future, longitudinal
predictions models.
Design
Cross-sectional, 1-5 days of data collection.
Setting
Community-based data collection.
Participants
Adults with chronic (>1 year), motor incomplete SCI (N=27).
Interventions
Not applicable.
Main Outcome Measures
Ambulatory ability based on the 10-m walk test (10MWT) or 6-minute walk test (6MWT)
categorized as nonambulatory, household ambulator (0.01-0.44 m/s, 1-204 m), or community
ambulator (>0.44 m/s, >204 m). A random forest model classified ambulatory ability
using input features including clinical measures of strength, sensation, and spasticity;
demographics; personal, psychosocial, and environmental factors including pain, environmental
factors, health, social support, self-efficacy, resilience, and sleep quality; and
LAs measured during sleep. Machine learning methods were used explicitly to avoid
overfitting and minimize the possibility of biased results.
Results
The combination of LA, clinical, and demographic features resulted in the highest
classification accuracies for both functional ambulation outcomes (10MWT=70.4%, 6MWT=81.5%).
Adding LAs, personal, psychosocial, and environmental factors, or both increased the
accuracy of classification compared with the clinical/demographic features alone.
Clinical measures of strength and sensation (especially knee flexion strength), LA
measures of movement smoothness, and presence of pain and comorbidities were among
the most important features selected for the models.
Conclusions
The addition of LA and personal, psychosocial, and environmental features increased
functional ambulation classification accuracy in a population with incomplete SCI
for whom improved prognosis for mobility outcomes is needed. These findings provide
support for future longitudinal studies that use LA; personal, psychosocial, and environmental
factors; and advanced analyses to improve clinical prediction rules for functional
mobility outcomes.
Keywords
List of abbreviations:
CPR (clinical prediction rule), LA (limb acceleration), OCA (overall classification accuracy), SCI (spinal cord injury), 6MWT (6-minute walk test), 10MWT (10-m walk test.)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Archives of Physical Medicine and RehabilitationAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Annual Statistical Report for the Spinal Cord Injury Model Systems.University of Alabama at Birmingham, Birmingham2019
- Facts and Figures at a Glance.University of Alabama at Birmingham, Birmingham2020
- Who wants to walk? Preferences for recovery after SCI: a longitudinal and cross-sectional study.Spinal Cord. 2008; 46: 500-506
- The health and life priorities of individuals with spinal cord injury: a systematic review.J Neurotrauma. 2012; 29: 1548-1555
- Longitudinal prediction of quality-of-life scores and locomotion in individuals with traumatic spinal cord injury.Arch Phys Med Rehabil. 2017; 98: 2385-2392
- The relationship between quality of life and change in mobility 1 year postinjury in individuals with spinal cord injury.Arch Phys Med Rehabil. 2011; 92: 1027-1033
- Gait training in acute spinal cord injury rehabilitation-utilization and outcomes among nonambulatory individuals: findings from the SCIRehab Project.Arch Phys Med Rehabil. 2018; 99: 1591-1598
- Understanding the mechanisms of recovery and/or compensation following injury.Neural Plast. 2017; 20177125057
- Physical determinants, emerging concepts, and training approaches in gait of individuals with spinal cord injury.J Neurotrauma. 2006; 23: 571-585
- Type and timing of rehabilitation following acute and subacute spinal cord injury: a systematic review.Global Spine J. 2017; 7: 175S-194S
- Rehabilitative training and plasticity following spinal cord injury.Exp Neurol. 2012; 235: 91-99
- Systematic scoping review protocol for clinical prediction rules (CPRs) in the management of patients with spinal cord injuries.BMJ Open. 2019; 9e025076
- The practical application of clinical prediction rules: a commentary using case examples in surgical patients with degenerative cervical myelopathy.Global Spine J. 2015; 5: 457-465
- A simplified clinical prediction rule for prognosticating independent walking after spinal cord injury: a prospective study from a Canadian multicenter spinal cord injury registry.Spine J. 2017; 17: 1383-1392
- A clinical prediction rule for ambulation outcomes after traumatic spinal cord injury: a longitudinal cohort study.Lancet. 2011; 377: 1004-1010
- External validation study of a clinical prediction rule for ambulation outcomes after traumatic spinal cord injury.Texas Medical Center Dissertations; Dallas, TX. 2013;
- Validation of the Dutch clinical prediction rule for ambulation outcomes in an inpatient setting following traumatic spinal cord injury.Spinal Cord. 2016; 54: 614-618
- Correction: validation of a clinical prediction rule for ambulation outcome after non-traumatic spinal cord injury.Spinal Cord. 2020; 58: 631
- Clinical utility during inpatient rehabilitation of a clinical prediction rule for ambulation prognosis following spinal cord injury.J Spinal Cord Med. 2021 Mar 11; ([Epub ahead of print])
- The effect of age and injury severity on clinical prediction rules for ambulation among individuals with spinal cord injury.Spine J. 2020; 20: 1666-1675
- Highlighting discrepancies in walking prediction accuracy for patients with traumatic spinal cord injury: an evaluation of validated prediction models using a Canadian Multicenter Spinal Cord Injury Registry.Spine J. 2019; 19: 703-710
- Predicting outcomes after spinal cord injury.Phys Med Rehabil Clin N Am. 2020; 31: 331-343
- Outcome prediction in spinal cord injury: myth or reality.World Neurosurg. 2020; 140: 574-590
- Developing artificial neural network models to predict functioning one year after traumatic spinal cord injury.Arch Phys Med Rehabil. 2016; 97: 1663-1668
- Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients.Spine J. 2020; 20: 213-224
- Lower extremity outcome measures: considerations for clinical trials in spinal cord injury.Spinal Cord. 2018; 56: 628-642
- Outcome measures for gait and ambulation in the spinal cord injury population.J Spinal Cord Med. 2008; 31: 487-499
- Predictive modeling of outcomes after traumatic and nontraumatic spinal cord injury using machine learning: review of current progress and future directions.Neurospine. 2019; 16: 678-685
- Psychological resources in spinal cord injury: a systematic literature review.Spinal Cord. 2012; 50: 188-201
- Health locus of control and attributions of cause and blame in adjustment to spinal cord injury.Spinal Cord. 2010; 48: 598-602
- Spinal cord injury, coping and psychological adjustment: a literature review.Spinal Cord. 2009; 47: 778-782
- Association of various comorbidity measures with spinal cord injury rehabilitation outcomes.Arch Phys Med Rehabil. 2013; 94: S75-S86
- Role of body weight in therapy participation and rehabilitation outcomes among individuals with traumatic spinal cord injury.Arch Phys Med Rehabil. 2013; 94: S125-S136
- Grade 4 in manual muscle testing: the problem with submaximal strength assessment.Clin Rehabil. 1997; 11: 36-41
- Considerations and practical options for measuring muscle strength: a narrative review.Biomed Res Int. 2019; 20198194537
- Reliability and validity of the sensory component of the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI): a systematic review.Top Spinal Cord Inj Rehabil. 2015; 21: 241-249
- Clinical assessment of spasticity in children with cerebral palsy: a critical review of available instruments.Dev Med Child Neurol. 2006; 48: 64-73
- The inter rater reliability of the original and of the Modified Ashworth Scale for the assessment of spasticity in patients with spinal cord injury.Spinal Cord. 1996; 34: 560-564
- Biering-Sorensen F. Modified Ashworth Scale and spasm frequency score in spinal cord injury: reliability and correlation.Spinal Cord. 2016; 54: 702-708
- Motor and sensory recovery following incomplete paraplegia.Arch Phys Med Rehabil. 1994; 75: 67-72
- Graded histological and locomotor outcomes after spinal cord contusion using the NYU weight-drop device versus transection.Exp Neurol. 1996; 139: 244-256
- Plasticity after spinal cord injury: relevance to recovery and approaches to facilitate it.Neurotherapeutics. 2011; 8: 283-293
- Estimation of muscle strength from actigraph data in Duchenne muscular dystrophy.Pediatr Int. 2014; 56: 748-752
- Neurophysiological correlates of sleep leg movements in acute spinal cord injury.Clin Neurophysiol. 2015; 126: 333-338
- Sleep-related periodic leg movements associated with spinal cord lesions.Mov Disord. 1996; 11: 719-722
- Sleep apnea and periodic leg movements in the first year after spinal cord injury.Sleep Med. 2015; 16: 59-66
- Changes in sleep and wake in response to different sleeping surfaces: a pilot study.Appl Ergon. 2012; 43: 386-391
- Body movements during night sleep and their relationship with sleep stages are further modified in very old subjects.Brain Res Bull. 2008; 75: 66-69
- Influence of age alone, and age combined with pinprick, on recovery of walking function in motor complete, sensory incomplete spinal cord injury.Arch Phys Med Rehabil. 2016; 97: 1635-1641
- Patterns of sacral sparing components on neurologic recovery in newly injured persons with traumatic spinal cord injury.Arch Phys Med Rehabil. 2016; 97: 1647-1655
- Validity of the walking scale for spinal cord injury and other domains of function in a multicenter clinical trial.Neurorehabil Neural Repair. 2007; 21: 539-550
- Interrater reliability of a Modified Ashworth Scale of muscle spasticity.Phys Ther. 1987; 67: 206-207
- Updates for the International Standards for Neurological Classification of Spinal Cord Injury.Phys Med Rehabil Clin N Am. 2014; 25: 505-517
Centers for Disease Control and Prevention; National Center for Health Statistics. NCHS urban-rural classification scheme for counties. Available at: https://www.cdc.gov/nchs/data_access/urban_rural.htm. Accessed August 1, 2020.
- 2013 NCHS urban-rural classification scheme for counties.US Department of Health and Human Services, Hyattsville2014
- Do communities matter after rehabilitation? The effect of socioeconomic and urban stratification on well-being after spinal cord injury.Arch Phys Med Rehabil. 2011; 92: 464-471
- How are race, cultural, and psychosocial factors associated with outcomes in veterans with spinal cord injury?.Arch Phys Med Rehabil. 2017; 98: 1812-1820
Cleeland CS, Ryan K. The brief pain inventory. Pain Research Group; Available at: http://www.npcrc.org/files/news/briefpain_long.pdf. Accessed March 1, 2020
- The international spinal cord injury pain basic data set.Spinal Cord. 2008; 46: 818-823
- Craig Hospital inventory of environmental factors, version 3.0.Craig Hospital Research Department, Englewood CO2001
- The MOS 36-item short-form health survey (SF-36). I. Conceptual framework and item selection.Med Care. 1992; 30: 473-483
- The MOS social support survey.Soc Sci Med. 1991; 32: 705-714
- Reexamining the validity and dimensionality of the Moorong Self-Efficacy Scale: improving its clinical utility.Arch Phys Med Rehabil. 2016; 97: 2130-2136
- The Pittsburgh sleep quality index as a screening tool for sleep dysfunction in clinical and non-clinical samples: a systematic review and meta-analysis.Sleep Med Rev. 2016; 25: 52-73
- Dysfunctional sleep in persons with spinal cord injuries and disorders.Spinal Cord. 2012; 50: 682-685
- Sleep duration as a correlate of smoking, alcohol use, leisure-time physical inactivity, and obesity among adults: United States, 2004-2006.NCHS Health & Stats, Washington, DC2008
- Fatigue and spinal cord injury: a qualitative analysis.Spinal Cord. 2009; 47: 44-49
- Gabapentin effect on neuropathic pain compared among patients with spinal cord injury and different durations of symptoms.Spine (Phila Pa 1976). 2003; 28 ([discussion 6-7]): 341-346
- Validity of sleep log compared with actigraphic sleep-wake state II.Psychiatry Clin Neurosci. 1999; 53: 183-184
- Measuring resilience after spinal cord injury: development, validation and psychometric characteristics of the SCI-QOL Resilience item bank and short form.J Spinal Cord Med. 2015; 38: 366-376
- Relationship between quality of life and self-efficacy in persons with spinal cord injuries.Arch Phys Med Rehabil. 2007; 88: 1643-1648
- Environmental factors and their role in participation and life satisfaction after spinal cord injury.Arch Phys Med Rehabil. 2004; 85: 1793-1803
- Quantifying environmental factors: a measure of physical, attitudinal, service, productivity, and policy barriers.Arch Phys Med Rehabil. 2004; 85: 1324-1335
- Psychosocial issues in spinal cord injury: a review.Spinal Cord. 2012; 50: 382-389
- Psychological contributions to functional independence: a longitudinal investigation of spinal cord injury rehabilitation.Arch Phys Med Rehabil. 2011; 92: 597-602
- Accelerometer data collection and processing criteria to assess physical activity and other outcomes: a systematic review and practical considerations.Sports Med. 2017; 47: 1821-1845
- Automatic sleep/wake identification from wrist activity.Sleep. 1992; 15: 461-469
- Validation of the use of Actigraph GT3X accelerometers to estimate energy expenditure in full time manual wheelchair users with spinal cord injury.Spinal Cord. 2013; 51: 898-903
- Actigraphy as a measure of physical activity for wheelchair users with spinal cord injury.Nurs Res. 2004; 53: 136-143
- The feasibility of sleep assessment by actigraph in patients with tetraplegia.Spinal Cord. 2007; 45: 765-770
- Accuracy of the Actigraph wGT3x-BT for step counting during inpatient spinal cord rehabilitation.Spinal Cord. 2019; 57: 571-578
- In-lab versus at-home activity recognition in ambulatory subjects with incomplete spinal cord injury.J Neuroeng Rehabil. 2017; 14: 10
- Activity recognition using a single accelerometer placed at the wrist or ankle.Med Sci Sports Exerc. 2013; 45: 2193-2203
- Correction: design and validation of a periodic leg movement detector.PLoS One. 2015; 10e0138205
- The PAM-RL ambulatory device for detection of periodic leg movements: a validation study.Sleep Med. 2005; 6: 407-413
- A study on human activity recognition using accelerometer data from smartphones.Procedia Comput Sci. 2014; 34: 450-457
- Accelerometry: providing an integrated, practical method for long-term, ambulatory monitoring of human movement.Physiol Meas. 2004; 25: R1-20
- Machine learning methods for classifying human physical activity from on-body accelerometers.Sensors (Basel). 2010; 10: 1154-1175
- A comprehensive assessment of gait accelerometry signals in time, frequency and time-frequency domains.IEEE Trans Neural Syst Rehabil Eng. 2014; 22: 603-612
- Walking during daily life can be validly and responsively assessed in subjects with a spinal cord injury.Neurorehabil Neural Repair. 2009; 23: 117-124
- Examination of sustained gait speed during extended walking in individuals with chronic stroke.Arch Phys Med Rehabil. 2013; 94: 2471-2477
- Are the 10 meter and 6 minute walk tests redundant in patients with spinal cord injury?.PLoS One. 2014; 9: e94108
- Gait speed in relation to categories of functional ambulation after spinal cord injury.Neurorehabil Neural Repair. 2009; 23: 343-350
- Predicting home and community walking activity poststroke.Stroke. 2017; 48: 406-411
- Scikit-learn: machine learning in Python.J Mach Learn Res. 2011; 12: 2825-2830
- Random forest ensembles for detection and prediction of Alzheimer's disease with a good between-cohort robustness.Neuroimage Clin. 2014; 6: 115-125
- Mixed effects trees and forests for clustered data.Montreal, Canada: HEC Montreal, Department of Management Sciences, 2010
- On over-fitting in model selection and subsequent selection bias in performance evaluation.J Mach Learn Res. 2010; 11: 2079-2107
- Bias in error estimation when using cross-validation for model selection.BMC Bioinformatics. 2006; 7: 91
- Machine learning algorithm validation with a limited sample size.PLoS One. 2019; 14e0224365
- A review on evaluation metrics for data classification evaluations.Int J Data Min Knowl Manage Process. 2015; 5: 1
- Association of mode of locomotion and independence in locomotion with long-term outcomes after spinal cord injury.J Spinal Cord Med. 2009; 32: 237-248
- Physical exercise for individuals with spinal cord injury: systematic review based on the international classification of functioning, disability, and health.J Sport Rehabil. 2019; 28: 505-516
- Short-term effects of core stability training on the balance and ambulation function of individuals with chronic spinal cord injury: a pilot randomized controlled trial.Minerva Med. 2019; 110: 216-223
- Effects of aerobic exercise training on fitness and walking-related outcomes in ambulatory individuals with chronic incomplete spinal cord injury.Spinal Cord. 2016; 54: 675-681
- Psychosocial factors associated with physical activity in ambulatory and manual wheelchair users with spinal cord injury: a mixed-methods study.Disabil Rehabil. 2017; 39: 187-192
- Daytime sleepiness, exercise, and physical function in older adults.J Sleep Res. 2007; 16: 60-65
- Poor sleep is associated with poorer physical performance and greater functional limitations in older women.Sleep. 2007; 30: 1317-1324
- More daytime sleeping predicts less functional recovery among older people undergoing inpatient post-acute rehabilitation.Sleep. 2008; 31: 1291-1300
- Daytime physical activity and sleep in hospitalized older adults: association with demographic characteristics and disease severity.J Am Geriatr Soc. 2015; 63: 1391-1400
- Random forest for bioinformatics.in: Zhang C Ma Y Ensemble machine learning. Springer US, Boston2012: 307-323
Article info
Publication history
Published online: April 07, 2021
Accepted:
February 7,
2021
Received in revised form:
January 21,
2021
Received:
October 10,
2020
Footnotes
Supported by the Office of the Assistant Secretary of Defense for Health Affairs through the Congressionally Directed Medical Research Programs, Spinal Cord Injury Research Program (award no. W81XWH-20-1-0724), National Center For Advancing Translational Sciences of the National Institutes of Health (award no. TL1TR001858), and Eunice Kennedy Shriver National Institute Of Child Health & Human Development of the National Institutes of Health (award nos. F30HD096828 and K23HD096134). Opinions, interpretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the Department of Defense or National Institutes of Health.
Disclosures: none
Identification
Copyright
© 2021 The American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.
