{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T14:53:10Z","timestamp":1792853590944,"version":"4.5.0"},"reference-count":36,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T00:00:00Z","timestamp":1709856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Education","award":["2022R1I1A1A01059442"],"award-info":[{"award-number":["2022R1I1A1A01059442"]}]},{"name":"Ministry of Education","award":["No. HI22C1302"],"award-info":[{"award-number":["No. HI22C1302"]}]},{"name":"Ministry of Health and Welfare of South Korea","award":["2022R1I1A1A01059442"],"award-info":[{"award-number":["2022R1I1A1A01059442"]}]},{"name":"Ministry of Health and Welfare of South Korea","award":["No. HI22C1302"],"award-info":[{"award-number":["No. HI22C1302"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Predicting gait recovery after a spinal cord injury (SCI) during an acute rehabilitation phase is important for planning rehabilitation strategies. However, few studies have been conducted on this topic to date. In this study, we developed a deep learning-based prediction model for gait recovery after SCI upon discharge from an acute rehabilitation facility. Data were collected from 405 patients with acute SCI admitted to the acute rehabilitation facility of Korea University Anam Hospital between June 2008 and December 2022. The dependent variable was Functional Ambulation Category at the time of discharge (FAC-DC). Seventy-one independent variables were selected from the existing literature: basic information, International Standards for Neurological Classification of SCI scores, neurogenic bladders, initial FAC, and somatosensory-evoked potentials of the lower extremity. Recurrent neural network (RNN), linear regression (LR), Ridge, and Lasso methods were compared for FAC-DC prediction in terms of the root-mean-squared error (RMSE). RNN variable importance, which is the RMSE gap between a complete RNN model and an RNN model excluding a certain variable, was used to evaluate the contribution of this variable. Based on the results of this study, the performance of the RNN was far better than that of LR, Ridge, and Lasso. The respective RMSEs were 0.3738, 2.2831, 1.3161, and 1.0246 for all the participants; 0.3727, 1.7176, 1.3914, and 1.3524 for those with trauma; and 0.3728, 1.7516, 1.1012, and 0.8889 for those without trauma. In terms of RNN variable importance, lower-extremity motor strength (right and left ankle dorsiflexors, right knee extensors, and left long toe extensors) and the neurological level of injury were ranked among the top five across the boards. Therefore, initial FAC was the seventh, third, and ninth most important predictor for all participants, those with trauma, and those without trauma, respectively. In conclusion, this study developed a deep learning-based prediction model with excellent performance for gait recovery after SCI at the time of discharge from an acute rehabilitation facility. This study also demonstrated the strength of deep learning as an explainable artificial intelligence method for identifying the most important predictors.<\/jats:p>","DOI":"10.3390\/diagnostics14060579","type":"journal-article","created":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T03:52:11Z","timestamp":1709869931000},"page":"579","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Deep Learning-Based Prediction Model for Gait Recovery after a Spinal Cord Injury"],"prefix":"10.3390","volume":"14","author":[{"given":"Hyun-Joon","family":"Yoo","sequence":"first","affiliation":[{"name":"Korea University Research Institute for Medical Bigdata Science, Korea University, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0576-0098","authenticated-orcid":false,"given":"Kwang-Sig","family":"Lee","sequence":"additional","affiliation":[{"name":"AI Center, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bummo","family":"Koo","sequence":"additional","affiliation":[{"name":"School of Health and Environmental Science, Korea University College of Health Science, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chan-Woo","family":"Yong","sequence":"additional","affiliation":[{"name":"School of Health and Environmental Science, Korea University College of Health Science, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chae-Won","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Health and Environmental Science, Korea University College of Health Science, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"ref_1","unstructured":"Mayo Clinic (2023, November 01). Spinal Cord Injury. Updated on 2 October 2021. Available online: https:\/\/www.mayoclinic.org\/diseases-conditions\/spinal-cord-injury\/symptoms-causes\/syc-20377890."},{"key":"ref_2","unstructured":"National Institute of Health (2023, November 01). Spinal Cord Injury. Updated on 20 January 2023, Available online: https:\/\/www.ninds.nih.gov\/health-information\/disorders\/spinal-cord-injury."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1097\/BRS.0000000000004417","article-title":"Spinal cord injury: The global incidence, prevalence, and disability From the Global Burden of Disease Study 2019","volume":"47","author":"Ding","year":"2022","journal-title":"Spine"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"4","DOI":"10.5535\/arm.23020","article-title":"Spinal cord injury fact sheet in Korea","volume":"47","author":"Kim","year":"2023","journal-title":"Ann. Rehabil. Med."},{"key":"ref_5","first-page":"317","article-title":"Physical activity, quality of life, and functional autonomy of adults with spinal cord injuries","volume":"30","author":"Kawanishi","year":"2013","journal-title":"Adapt. Phys. Act. Q."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"175S","DOI":"10.1177\/2192568217703084","article-title":"Type and timing of rehabilitation following acute and subacute spinal cord injury: A systematic review","volume":"7","author":"Burns","year":"2017","journal-title":"Glob. Spine J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"141","DOI":"10.3389\/fnhum.2014.00141","article-title":"Who is going to walk? A review of the factors influencing walking recovery after spinal cord injury","volume":"8","author":"Scivoletto","year":"2014","journal-title":"Front. Hum. Neurosci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1016\/S0140-6736(10)62276-3","article-title":"A clinical prediction rule for ambulation outcomes after traumatic spinal cord injury: A longitudinal cohort study","volume":"377","author":"Hosman","year":"2011","journal-title":"Lancet"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2916","DOI":"10.1089\/neu.2017.5576","article-title":"Electrophysiological multimodal assessments improve outcome prediction in traumatic cervical spinal cord injury","volume":"35","author":"Hupp","year":"2018","journal-title":"J. Neurotrauma"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1136\/jnnp.67.5.567","article-title":"Prognosis and recovery in ischaemic and traumatic spinal cord injury: Clinical and electrophysiological evaluation","volume":"67","author":"Iseli","year":"1999","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"102046","DOI":"10.1016\/j.jcot.2022.102046","article-title":"Machine learning in clinical diagnosis, prognostication, and management of acute traumatic spinal cord injury (SCI): A systematic review","volume":"35","author":"Dietz","year":"2022","journal-title":"J. Clin. Orthop. Trauma"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.spinee.2019.09.007","article-title":"Development of an unsupervised machine learning algorithm for the prognostication of walking ability in spinal cord injury patients","volume":"20","author":"DeVries","year":"2020","journal-title":"Spine J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1089\/neu.2017.5321","article-title":"Use of regression tree analysis for predicting the functional outcome after traumatic spinal cord injury","volume":"38","author":"Facchinello","year":"2021","journal-title":"J. Neurotrauma"},{"key":"ref_14","first-page":"737","article-title":"Talbott. Convolutional neural network\u2013based automated segmentation of the spinal cord and contusion injury: Deep learning biomarker correlates of motor impairment in acute spinal cord injury","volume":"40","author":"McCoy","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A review of recurrent neural networks: LSTM cells and network architectures","volume":"31","author":"Yu","year":"2019","journal-title":"Neural Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1093\/ptj\/64.1.35","article-title":"Clinical gait assessment in the neurologically impaired. Reliability and meaningfulness","volume":"64","author":"Holden","year":"1984","journal-title":"Phys. Ther."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"11","DOI":"10.3171\/2012.4.AOSPINE1245","article-title":"Clinical predictors of neurological outcome, functional status, and survival after traumatic spinal cord injury: A systematic review","volume":"17","author":"Wilson","year":"2012","journal-title":"J. Neurosurg. Spine"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1089\/neu.2012.2417","article-title":"A clinical prediction model for long-term functional outcome after traumatic spinal cord injury based on acute clinical and imaging factors","volume":"29","author":"Wilson","year":"2012","journal-title":"J. Neurotrauma"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.46292\/sci2702-1","article-title":"International Standards for Neurological Classification of Spinal Cord Injury: Revised 2019","volume":"27","author":"Rupp","year":"2021","journal-title":"Top. Spinal Cord Inj. Rehabil."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wasiak, K., Frasu\u0144ska, J., and Tarnacka, B. (2024). Can the Initial Parameters of Functional Scales Predict Recovery in Patients with Complete Spinal Cord Injury? A Retrospective Cohort Study. Diagnostics, 14.","DOI":"10.3390\/diagnostics14020129"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1016\/j.wneu.2020.05.043","article-title":"Outcome prediction in spinal cord injury: Myth or reality","volume":"140","author":"Sharif","year":"2020","journal-title":"World Neurosurg."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1177\/21925682221095470","article-title":"Prognostic factors for respiratory dysfunction for cervical spinal cord injury and\/or cervical fractures in elderly patients: A multicenter survey","volume":"14","author":"Hirota","year":"2024","journal-title":"Glob. Spine J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"678","DOI":"10.14245\/ns.1938390.195","article-title":"Predictive Modeling of Outcomes After Traumatic and Nontraumatic Spinal Cord Injury Using Machine Learning: Review of Current Progress and Future Directions","volume":"16","author":"Khan","year":"2019","journal-title":"Neurospine"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.spinee.2021.08.003","article-title":"Development of a machine learning algorithm for predicting in-hospital and 1-year mortality after traumatic spinal cord injury","volume":"22","author":"Fallah","year":"2022","journal-title":"Spine J."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"E390","DOI":"10.1097\/BRS.0000000000004267","article-title":"Machine Learning-based Prediction of Prolonged Intensive Care Unit Stay for Critical Patients with Spinal Cord Injury","volume":"47","author":"Fan","year":"2022","journal-title":"Spine"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.apmr.2023.08.011","article-title":"Functional Outcome Prediction After Spinal Cord Injury Using Ensemble Machine Learning","volume":"105","author":"Kato","year":"2024","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"52","DOI":"10.3171\/2012.6.AOSPINE1287","article-title":"What do we currently know about thoracic spinal cord injury recovery and outcomes? A systematic review","volume":"17","author":"Bransford","year":"2012","journal-title":"J. Neurosurg. Spine"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1038\/sc.2015.193","article-title":"Investigation of measured and predicted resting energy needs in adults after spinal cord injury: A systematic review","volume":"54","author":"Nevin","year":"2016","journal-title":"Spinal Cord"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1080\/10790268.2016.1238184","article-title":"Predictors of functional outcomes in adults with traumatic spinal cord injury following inpatient rehabilitation: A systematic review","volume":"40","author":"AlHuthaifi","year":"2017","journal-title":"J. Spinal Cord Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1310\/sci2303-207","article-title":"Inflammatory stress effects on health and function after spinal cord injury","volume":"23","author":"Noller","year":"2017","journal-title":"Top. Spinal Cord Inj. Rehabil."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1177\/2151458517696680","article-title":"Spinal cord injury in the geriatric population: Risk factors, treatment options, and long-term management","volume":"8","author":"Ikpeze","year":"2017","journal-title":"Geriatr. Orthop. Surg. Rehabil."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e19","DOI":"10.3171\/2017.7.FOCUS17396","article-title":"Update on critical care for acute spinal cord injury in the setting of polytrauma","volume":"43","author":"Yue","year":"2017","journal-title":"Neurosurg. Focus"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e0197987","DOI":"10.1371\/journal.pone.0197987","article-title":"A scoping review of biopsychosocial risk factors and co-morbidities for common spinal disorders","volume":"13","author":"Green","year":"2018","journal-title":"PLoS ONE"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Hambly, B., Xu, R., and Yang, H. (2022). Recent advances in reinforcement learning in finance. arXiv.","DOI":"10.2139\/ssrn.3971071"},{"key":"ref_36","unstructured":"Yu, C., Liu, J., and Nemati, S. (2020). Reinforcement learning in healthcare: A survey. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/6\/579\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:10:47Z","timestamp":1760105447000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/14\/6\/579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,8]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["diagnostics14060579"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics14060579","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,8]]}}}