1
|
Wang Y, Zhang J, Yuan J, Li Q, Zhang S, Wang C, Wang H, Wang L, Zhang B, Wang C, Sun Y, Lu X. Application of a novel nested ensemble algorithm in predicting motor function recovery in patients with traumatic cervical spinal cord injury. Sci Rep 2024; 14:17403. [PMID: 39075134 PMCID: PMC11286788 DOI: 10.1038/s41598-024-65755-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Accepted: 06/24/2024] [Indexed: 07/31/2024] Open
Abstract
Traumatic cervical spinal cord injury (TCSCI) often causes varying degrees of motor dysfunction, common assessed by the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI), in association with the American Spinal Injury Association (ASIA) Impairment Scale. Accurate prediction of motor function recovery is extremely important for formulating effective diagnosis, therapeutic and rehabilitation programs. The aim of this study is to investigate the validity of a novel nested ensemble algorithm that uses the very early ASIA motor score (AMS) of ISNCSCI examination to predict motor function recovery 6 months after injury in TCSCI patients. This retrospective study included complete data of 315 TCSCI patients. The dataset consisting of the first AMS at ≤ 24 h post-injury and follow-up AMS at 6 months post-injury was divided into a training set (80%) and a test set (20%). The nested ensemble algorithm was established in a two-stage manner. Support Vector Classification (SVC), Adaboost, Weak-learner and Dummy were used in the first stage, and Adaboost was selected as second-stage model. The prediction results of the first stage models were uploaded into second-stage model to obtain the final prediction results. The model performance was evaluated using precision, recall, accuracy, F1 score, and confusion matrix. The nested ensemble algorithm was applied to predict motor function recovery of TCSCI, achieving an accuracy of 80.6%, a F1 score of 80.6%, and balancing sensitivity and specificity. The confusion matrix showed few false-negative rate, which has crucial practical implications for prognostic prediction of TCSCI. This novel nested ensemble algorithm, simply based on very early AMS, provides a useful tool for predicting motor function recovery 6 months after TCSCI, which is graded in gradients that progressively improve the accuracy and reliability of the prediction, demonstrating a strong potential of ensemble learning to personalize and optimize the rehabilitation and care of TCSCI patients.
Collapse
Affiliation(s)
- Yijin Wang
- North Sichuan Medical College, No. 234 Fuljiang Road, Shunqing District, Nanchong, 637100, Sichuan, People's Republic of China
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Jianjun Zhang
- North Sichuan Medical College, No. 234 Fuljiang Road, Shunqing District, Nanchong, 637100, Sichuan, People's Republic of China
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Jincan Yuan
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Qingyuan Li
- North Sichuan Medical College, No. 234 Fuljiang Road, Shunqing District, Nanchong, 637100, Sichuan, People's Republic of China
| | - Shiyu Zhang
- UCSI University, No. 1, Jalan UCSI, UCSI Heights, 56000, Cheras, Kuala Lumpur, Malaysia
| | - Chenfeng Wang
- Zhejiang University, No. 866 Yuhangtang Road, Xihu District, Hangzhou, 310058, Zhejiang, People's Republic of China
| | - Haibing Wang
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Liang Wang
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Bangke Zhang
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Can Wang
- North Sichuan Medical College, No. 234 Fuljiang Road, Shunqing District, Nanchong, 637100, Sichuan, People's Republic of China
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China
| | - Yuling Sun
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China.
| | - Xuhua Lu
- Department of Orthopedic Surgery, Changzheng Hospital, Naval Medical University, No. 415 Fengyang Road, Shanghai, 200003, People's Republic of China.
| |
Collapse
|
2
|
Dietz N, Alkin V, Agarwal N, Bjurström MF, Ugiliweneza B, Wang D, Sharma M, Drazin D, Boakye M. Polypharmacy in spinal cord injury: Matched cohort analysis comparing drug classes, medical complications, and healthcare utilization metrics with 24-month follow-up. J Spinal Cord Med 2024:1-10. [PMID: 39037335 DOI: 10.1080/10790268.2024.2375892] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 07/23/2024] Open
Abstract
OBJECTIVE Polypharmacy in spinal cord injury (SCI) is common and predisposes patients to increased risk of adverse events. Evaluation of long-term health consequences and economic burden of polypharmacy in patients with SCI is explored. DESIGN Retrospective cohort. METHODS The IBM Marketscan Research Databases claims-based dataset was queried to search for adult patients with SCI with a 2-year follow-up. PARTICIPANTS Two matched cohorts were analyzed: those with and without polypharmacy, analyzing index hospitalization, readmissions, payments, and health outcomes. RESULTS A total of 11 569 individuals with SCI were included, of which 7235 (63%) were in the polypharmacy group who took a median of 11 separate drugs over two years. Opioid analgesics were the most common medication, present in 57% of patients with SCI meeting the criteria of polypharmacy, followed by antidepressant medications (46%) and muscle relaxants (40%). Risk of pneumonia was increased for the polypharmacy group (58%) compared to the non-polypharmacy group (45%), as were urinary tract infection (79% versus 63%), wound infection (30% versus 21%), depression (76% versus 57%), and adverse drug events (24% versus 15%) at 2 years. Combined median healthcare payments were higher in polypharmacy at 2 years ($44 333 vs. $10 937, P < .0001). CONCLUSION Majority of individuals with SCI met the criteria for polypharmacy with nearly 60% of those prescribed opioids and taking drugs from high-risk side effect profiles. Polypharmacy in SCI was associated with a greater risk of pneumonia, depression, urinary tract infections, adverse drug events, and emergency room visits over two years with four times higher overall healthcare payments at 1-year post-injury.
Collapse
Affiliation(s)
- Nicholas Dietz
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky, USA
| | - Victoria Alkin
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky, USA
| | - Nitin Agarwal
- Department of Neurosurgery, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
| | | | | | - Dengzhi Wang
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky, USA
| | - Mayur Sharma
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky, USA
| | - Doniel Drazin
- Department of Neurosurgery, Pacific Northwest University of Health Sciences, Yakima, Washington, USA
| | - Maxwell Boakye
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky, USA
| |
Collapse
|
3
|
Alvi MA, Pedro KM, Quddusi AI, Fehlings MG. Advances and Challenges in Spinal Cord Injury Treatments. J Clin Med 2024; 13:4101. [PMID: 39064141 PMCID: PMC11278467 DOI: 10.3390/jcm13144101] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Revised: 07/03/2024] [Accepted: 07/05/2024] [Indexed: 07/28/2024] Open
Abstract
Spinal cord injury (SCI) is a debilitating condition that is associated with long-term physical and functional disability. Our understanding of the pathogenesis of SCI has evolved significantly over the past three decades. In parallel, significant advances have been made in optimizing the management of patients with SCI. Early surgical decompression, adequate bony decompression and expansile duraplasty are surgical strategies that may improve neurological and functional outcomes in patients with SCI. Furthermore, advances in the non-surgical management of SCI have been made, including optimization of hemodynamic management in the critical care setting. Several promising therapies have also been investigated in pre-clinical studies, with some being translated into clinical trials. Given the recent interest in advancing precision medicine, several investigations have been performed to delineate the role of imaging, cerebral spinal fluid (CSF) and serum biomarkers in predicting outcomes and curating individualized treatment plans for SCI patients. Finally, technological advancements in biomechanics and bioengineering have also found a role in SCI management in the form of neuromodulation and brain-computer interfaces.
Collapse
Affiliation(s)
- Mohammed Ali Alvi
- Institute of Medical Science, University of Toronto, Toronto, ON M5S 1A8, Canada; (M.A.A.); (K.M.P.); (A.I.Q.)
| | - Karlo M. Pedro
- Institute of Medical Science, University of Toronto, Toronto, ON M5S 1A8, Canada; (M.A.A.); (K.M.P.); (A.I.Q.)
- Department of Surgery and Spine Program, University of Toronto, Toronto, ON M5T 1P5, Canada
| | - Ayesha I. Quddusi
- Institute of Medical Science, University of Toronto, Toronto, ON M5S 1A8, Canada; (M.A.A.); (K.M.P.); (A.I.Q.)
| | - Michael G. Fehlings
- Institute of Medical Science, University of Toronto, Toronto, ON M5S 1A8, Canada; (M.A.A.); (K.M.P.); (A.I.Q.)
- Department of Surgery and Spine Program, University of Toronto, Toronto, ON M5T 1P5, Canada
- Division of Neurosurgery, Krembil Neuroscience Centre, Toronto Western Hospital, University Health Network, Toronto, ON M5T 2S8, Canada
| |
Collapse
|
4
|
Papadimos TJ. Prognostication: A fading Hippocratic art? Explore (NY) 2024; 20:103026. [PMID: 39002395 DOI: 10.1016/j.explore.2024.103026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2024] [Revised: 06/18/2024] [Accepted: 06/29/2024] [Indexed: 07/15/2024]
Abstract
Over the past 75 years modern medicine has advanced in its ability to diagnose and treat many diseases. However, the medical profession's ability to prognosticate the course and outcome of an illness has not satisfied the needs of many patients. Physicians must not lose the ability, or desire, to consider the whole person in relation to a patient's disease. We need to ask ourselves what person has the disease, not what disease the person has. Here I endeavor to demonstrate why Hippocrates valued prognostication highly, how its importance may have faded from the consciousness of current medical practice, and how modern technology is attempting to reinvent or revise it.
Collapse
Affiliation(s)
- Thomas John Papadimos
- Departments of Anesthesiology and Surgery, The University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, United States.
| |
Collapse
|
5
|
Voigtlaender S, Pawelczyk J, Geiger M, Vaios EJ, Karschnia P, Cudkowicz M, Dietrich J, Haraldsen IRJH, Feigin V, Owolabi M, White TL, Świeboda P, Farahany N, Natarajan V, Winter SF. Artificial intelligence in neurology: opportunities, challenges, and policy implications. J Neurol 2024; 271:2258-2273. [PMID: 38367046 DOI: 10.1007/s00415-024-12220-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Revised: 01/20/2024] [Accepted: 01/22/2024] [Indexed: 02/19/2024]
Abstract
Neurological conditions are the leading cause of disability and mortality combined, demanding innovative, scalable, and sustainable solutions. Brain health has become a global priority with adoption of the World Health Organization's Intersectoral Global Action Plan in 2022. Simultaneously, rapid advancements in artificial intelligence (AI) are revolutionizing neurological research and practice. This scoping review of 66 original articles explores the value of AI in neurology and brain health, systematizing the landscape for emergent clinical opportunities and future trends across the care trajectory: prevention, risk stratification, early detection, diagnosis, management, and rehabilitation. AI's potential to advance personalized precision neurology and global brain health directives hinges on resolving core challenges across four pillars-models, data, feasibility/equity, and regulation/innovation-through concerted pursuit of targeted recommendations. Paramount actions include swift, ethical, equity-focused integration of novel technologies into clinical workflows, mitigating data-related issues, counteracting digital inequity gaps, and establishing robust governance frameworks balancing safety and innovation.
Collapse
Affiliation(s)
- Sebastian Voigtlaender
- Systems Neuroscience Division, Max-Planck-Institute for Biological Cybernetics, Tübingen, Germany
- Virtual Diagnostics Team, QuantCo Inc., Cambridge, MA, USA
| | - Johannes Pawelczyk
- Faculty of Medicine, Ruprecht-Karls-University, Heidelberg, Germany
- Graduate Center of Medicine and Health, Technical University Munich, Munich, Germany
| | - Mario Geiger
- Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA
- NVIDIA, Zurich, Switzerland
| | - Eugene J Vaios
- Department of Radiation Oncology, Duke University Medical Center, Durham, NC, USA
| | - Philipp Karschnia
- Department of Neurosurgery, Ludwig-Maximilians-University and University Hospital Munich, Munich, Germany
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Merit Cudkowicz
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Jorg Dietrich
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA
| | - Ira R J Hebold Haraldsen
- Department of Neurology, Division of Clinical Neuroscience, Oslo University Hospital, Oslo, Norway
| | - Valery Feigin
- National Institute for Stroke and Applied Neurosciences, Auckland University of Technology, Auckland, New Zealand
| | - Mayowa Owolabi
- Center for Genomics and Precision Medicine, College of Medicine, University of Ibadan, Ibadan, Nigeria
- Neurology Unit, Department of Medicine, University of Ibadan, Ibadan, Nigeria
- Blossom Specialist Medical Center, Ibadan, Nigeria
- Lebanese American University of Beirut, Beirut, Lebanon
| | - Tara L White
- Department of Behavioral and Social Sciences, Brown University, Providence, RI, USA
| | | | | | | | - Sebastian F Winter
- Department of Neurology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
6
|
Karthik EN, Valosek J, Smith AC, Pfyffer D, Schading-Sassenhausen S, Farner L, Weber KA, Freund P, Cohen-Adad J. SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.01.03.24300794. [PMID: 38699309 PMCID: PMC11065035 DOI: 10.1101/2024.01.03.24300794] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/05/2024]
Abstract
Purpose To develop a deep learning tool for the automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury (SCI). Material and Methods This retrospective study included a cohort of SCI patients from three sites enrolled between July 2002 and February 2023. A deep learning model, SCIseg, was trained in a three-phase process involving active learning for the automatic segmentation of intramedullary SCI lesions and the spinal cord. The data consisted of T2-weighted MRI acquired using different scanner manufacturers with heterogeneous image resolutions (isotropic/anisotropic), orientations (axial/sagittal), lesion etiologies (traumatic/ischemic/hemorrhagic) and lesions spread across the cervical, thoracic and lumbar spine. The segmentations from the proposed model were visually and quantitatively compared with other open-source baselines. Wilcoxon signed-rank test was used to compare quantitative MRI biomarkers (lesion volume, lesion length, and maximal axial damage ratio) computed from manual lesion masks and those obtained automatically with SCIseg predictions. Results MRI data from 191 SCI patients (mean age, 48.1 years ± 17.9 [SD]; 142 males) were used for model training and evaluation. SCIseg achieved the best segmentation performance for both the cord and lesions. There was no statistically significant difference between lesion length and maximal axial damage ratio computed from manually annotated lesions and those obtained using SCIseg. Conclusion Automatic segmentation of intramedullary lesions commonly seen in SCI replaces the tedious manual annotation process and enables the extraction of relevant lesion morphometrics in large cohorts. The proposed model segments lesions across different etiologies, scanner manufacturers, and heterogeneous image resolutions. SCIseg is open-source and accessible through the Spinal Cord Toolbox.
Collapse
Affiliation(s)
- Enamundram Naga Karthik
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
- Mila - Quebec AI Institute, Montreal, QC, Canada
| | - Jan Valosek
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
- Mila - Quebec AI Institute, Montreal, QC, Canada
- Department of Neurosurgery, Faculty of Medicine and Dentistry, Palacký University Olomouc, Olomouc, Czechia
- Department of Neurology, Faculty of Medicine and Dentistry, Palacký University Olomouc, Olomouc, Czechia
| | - Andrew C Smith
- Department of Physical Medicine and Rehabilitation Physical Therapy Program, University of Colorado School of Medicine, Aurora, Colorado, USA
| | - Dario Pfyffer
- Spinal Cord Injury Center, Balgrist University Hospital, University of Zürich, Zürich, Switzerland
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, California, USA
| | | | - Lynn Farner
- Spinal Cord Injury Center, Balgrist University Hospital, University of Zürich, Zürich, Switzerland
| | - Kenneth A Weber
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, California, USA
| | - Patrick Freund
- Spinal Cord Injury Center, Balgrist University Hospital, University of Zürich, Zürich, Switzerland
- Department of Neurophysics, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany
| | - Julien Cohen-Adad
- NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
- Mila - Quebec AI Institute, Montreal, QC, Canada
- Functional Neuroimaging Unit, CRIUGM, Université de Montréal, Montreal, QC, Canada
- Centre de Recherche du CHU Sainte-Justine, Université de Montréal, Montreal, QC, Canada
| |
Collapse
|
7
|
Pozin M, Najafali D, Naik A, MacInnis B, Subbarao N, Zuckerman SL, Arnold PM. Long-term assessment of the functional independence measure in sports-related spinal cord injury. J Spinal Cord Med 2024; 47:214-228. [PMID: 36977319 PMCID: PMC10885752 DOI: 10.1080/10790268.2023.2167903] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/30/2023] Open
Abstract
CONTEXT Patients with spinal cord injury (SCI) secondary to traumatic sports-related etiology potentially face loss of independence. The Functional Independence Measure (FIM) assesses the amount of assistance patients require and has shown sensitivity to changes in patient functional status post injury. OBJECTIVES We aimed to (1) examine long-term outcomes following sports-related SCI (SRSCI) using FIM scoring at the time of injury, one year, and five years post-injury, and (2) determine predictors of independence at one and five-year follow-up considering surgical and non-surgical management. Few studies have investigated the cohort analyzed in this study. METHODS The 1973-2016 National Spinal Cord Injury Model Systems (SCIMS) Database was used to develop a SRSCI cohort. The primary outcome of interest captured functional independence using a multivariate logistic regression, defined by FIM individual scores greater than or equal to six, evaluated at one and five years. RESULTS A total of 491 patients were analyzed, 60 (12%) were female, 452 (92%) underwent surgery. The cohort demographics were stratified by patients with and without spine surgery and evaluated for functional independence in FIM subcategories. Increased time spent in inpatient rehabilitation and FIM score at post-operative discharge were associated with greater likelihood of functional ability at both one and five-year follow-up. CONCLUSION Our study demonstrated that SRSCI patients are a unique subset of SCI patients for whom factors repeatedly associated with independence at one year follow-up were dissimilar to those associated with independence at five-year follow-up. Larger prospective studies should be conducted to establish guidelines for this unique subcategory of SCI patients.
Collapse
Affiliation(s)
- Michael Pozin
- Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
| | - Daniel Najafali
- Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
| | - Anant Naik
- Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
| | - Bailey MacInnis
- Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
| | - Natasha Subbarao
- Kansas City University College of Medicine, Joplin, Missouri, USA
| | - Scott L. Zuckerman
- Department of Neurosurgery, Vanderbilt University Medical Center, Nashville, Tennessee, USA
| | - Paul M. Arnold
- Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Urbana, Illinois, USA
- Department of Neurosurgery, Carle Foundation Hospital, Urbana, Illinois, USA
| |
Collapse
|
8
|
Agoston DV. Traumatic Brain Injury in the Long-COVID Era. Neurotrauma Rep 2024; 5:81-94. [PMID: 38463416 PMCID: PMC10923549 DOI: 10.1089/neur.2023.0067] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/12/2024] Open
Abstract
Major determinants of the biological background or reserve, such as age, biological sex, comorbidities (diabetes, hypertension, obesity, etc.), and medications (e.g., anticoagulants), are known to affect outcome after traumatic brain injury (TBI). With the unparalleled data richness of coronavirus disease 2019 (COVID-19; ∼375,000 and counting!) as well as the chronic form, long-COVID, also called post-acute sequelae SARS-CoV-2 infection (PASC), publications (∼30,000 and counting) covering virtually every aspect of the diseases, pathomechanisms, biomarkers, disease phases, symptomatology, etc., have provided a unique opportunity to better understand and appreciate the holistic nature of diseases, interconnectivity between organ systems, and importance of biological background in modifying disease trajectories and affecting outcomes. Such a holistic approach is badly needed to better understand TBI-induced conditions in their totality. Here, I briefly review what is known about long-COVID/PASC, its underlying-suspected-pathologies, the pathobiological changes induced by TBI, in other words, the TBI endophenotypes, discuss the intersection of long-COVID/PASC and TBI-induced pathobiologies, and how by considering some of the known factors affecting the person's biological background and the inclusion of mechanistic molecular biomarkers can help to improve the clinical management of TBI patients.
Collapse
Affiliation(s)
- Denes V. Agoston
- Department of Anatomy, Physiology, and Genetics, School of Medicine, Uniformed Services University, Bethesda, Maryland, USA
| |
Collapse
|
9
|
Maki S, Furuya T, Inoue M, Shiga Y, Inage K, Eguchi Y, Orita S, Ohtori S. Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis. J Clin Med 2024; 13:705. [PMID: 38337399 PMCID: PMC10856760 DOI: 10.3390/jcm13030705] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 01/14/2024] [Accepted: 01/18/2024] [Indexed: 02/12/2024] Open
Abstract
Spinal injuries, including cervical and thoracolumbar fractures, continue to be a major public health concern. Recent advancements in machine learning and deep learning technologies offer exciting prospects for improving both diagnostic and prognostic approaches in spinal injury care. This narrative review systematically explores the practical utility of these computational methods, with a focus on their application in imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI), as well as in structured clinical data. Of the 39 studies included, 34 were focused on diagnostic applications, chiefly using deep learning to carry out tasks like vertebral fracture identification, differentiation between benign and malignant fractures, and AO fracture classification. The remaining five were prognostic, using machine learning to analyze parameters for predicting outcomes such as vertebral collapse and future fracture risk. This review highlights the potential benefit of machine learning and deep learning in spinal injury care, especially their roles in enhancing diagnostic capabilities, detailed fracture characterization, risk assessments, and individualized treatment planning.
Collapse
Affiliation(s)
- Satoshi Maki
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
- Center for Frontier Medical Engineering, Chiba University, Chiba 263-8522, Japan
| | - Takeo Furuya
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| | - Masahiro Inoue
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| | - Yasuhiro Shiga
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| | - Kazuhide Inage
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| | - Yawara Eguchi
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| | - Sumihisa Orita
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
- Center for Frontier Medical Engineering, Chiba University, Chiba 263-8522, Japan
| | - Seiji Ohtori
- Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba 260-8670, Japan
| |
Collapse
|
10
|
Karabacak M, Margetis K. Precision medicine for traumatic cervical spinal cord injuries: accessible and interpretable machine learning models to predict individualized in-hospital outcomes. Spine J 2023; 23:1750-1763. [PMID: 37619871 DOI: 10.1016/j.spinee.2023.08.009] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/07/2023] [Revised: 06/28/2023] [Accepted: 08/13/2023] [Indexed: 08/26/2023]
Abstract
BACKGROUND CONTEXT A traumatic spinal cord injury (SCI) can cause temporary or permanent motor and sensory impairment, leading to serious short and long-term consequences that can result in significant morbidity and mortality. The cervical spine is the most commonly affected area, accounting for about 60% of all traumatic SCI cases. PURPOSE This study aims to employ machine learning (ML) algorithms to predict various outcomes, such as in-hospital mortality, nonhome discharges, extended length of stay (LOS), extended length of intensive care unit stay (ICU-LOS), and major complications in patients diagnosed with cervical SCI (cSCI). STUDY DESIGN Our study was a retrospective machine learning classification study aiming to predict the outcomes of interest, which were binary categorical variables, in patients diagnosed with cSCI. PATIENT SAMPLE The data for this study were obtained from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database, which was queried to identify patients who suffered from cSCI between 2019 and 2021. OUTCOME MEASURES The outcomes of interest of our study were in-hospital mortality, nonhome discharges, prolonged LOS, prolonged ICU-LOS, and major complications. The study evaluated the models' performance using both graphical and numerical methods. The receiver operating characteristic (ROC) and precision-recall curves (PRC) were used to assess model performance graphically. Numerical evaluation metrics included AUROC, balanced accuracy, weighted area under PRC (AUPRC), weighted precision, and weighted recall. METHODS The study employed data from the American College of Surgeons (ACS) Trauma Quality Program (TQP) database to identify patients with cSCI. Four ML algorithms, namely XGBoost, LightGBM, CatBoost, and Random Forest, were utilized to develop predictive models. The most effective models were then incorporated into a publicly available web application designed to forecast the outcomes of interest. RESULTS There were 71,661 patients included in the analysis for the outcome mortality, 67,331 for the outcome nonhome discharges, 76,782 for the outcome prolonged LOS, 26,615 for the outcome prolonged ICU-LOS, and 72,132 for the outcome major complications. The algorithms exhibited an AUROC value range of 0.78 to 0.839 for in-hospital mortality, 0.806 to 0.815 for nonhome discharges, 0.679 to 0.742 for prolonged LOS, 0.666 to 0.682 for prolonged ICU-LOS, and 0.637 to 0.704 for major complications. An open access web application was developed as part of the study, which can generate predictions for individual patients based on their characteristics. CONCLUSIONS Our study suggests that ML models can be valuable in assessing risk for patients with cervical cSCI and may have considerable potential for predicting outcomes during hospitalization. ML models demonstrated good predictive ability for in-hospital mortality and nonhome discharges, fair predictive ability for prolonged LOS, but poor predictive ability for prolonged ICU-LOS and major complications. Along with these promising results, the development of a user-friendly web application that facilitates the integration of these models into clinical practice is a significant contribution of this study. The product of this study may have significant implications in clinical settings to personalize care, anticipate outcomes, facilitate shared decision making and informed consent processes for cSCI patients.
Collapse
Affiliation(s)
- Mert Karabacak
- Department of Neurosurgery, Mount Sinai Health System, 1468 Madison (Ave), New York, 10029 NY, USA
| | - Konstantinos Margetis
- Department of Neurosurgery, Mount Sinai Health System, 1468 Madison (Ave), New York, 10029 NY, USA
| |
Collapse
|
11
|
Amiri M, Kangatharan S, Brisbois L, Farahani F, Khasiyeva N, Burley M, Craven BC. Developing and Evaluating Data Infrastructure and Implementation Tools to Support Cardiometabolic Disease Indicator Data Collection. Top Spinal Cord Inj Rehabil 2023; 29:124-141. [PMID: 38174138 PMCID: PMC10759866 DOI: 10.46292/sci23-00018s] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2024]
Abstract
Background Assessment of aerobic exercise (AE) and lipid profiles among individuals with spinal cord injury or disease (SCI/D) is critical for cardiometabolic disease (CMD) risk estimation. Objectives To utilize an artificial intelligence (AI) tool for extracting indicator data and education tools to enable routine CMD indicator data collection in inpatient/outpatient settings, and to describe and evaluate the recall of AE levels and lipid profile assessment completion rates across care settings among adults with subacute and chronic SCI/D. Methods A cross-sectional convenience sample of patients affiliated with University Health Network's SCI/D rehabilitation program and outpatients affiliated with SCI Ontario participated. The SCI-HIGH CMD intermediary outcome (IO) and final outcome (FO) indicator surveys were administered, using an AI tool to extract responses. Practice gaps were prospectively identified, and implementation tools were created to address gaps. Univariate and bivariate descriptive analyses were used. Results The AI tool had <2% error rate for data extraction. Adults with SCI/D (n = 251; 124 IO, mean age 61; 127 FO, mean age 55; p = .004) completed the surveys. Fourteen percent of inpatients versus 48% of outpatients reported being taught AE. Fifteen percent of inpatients and 51% of outpatients recalled a lipid assessment (p < .01). Algorithms and education tools were developed to address identified knowledge gaps in patient AE and lipid assessments. Conclusion Compelling CMD health service gaps warrant immediate attention to achieve AE and lipid assessment guideline adherence. AI indicator extraction paired with implementation tools may facilitate indicator deployment and modify CMD risk.
Collapse
Affiliation(s)
- Mohammadreza Amiri
- KITE Research Institute, University Health Network, Toronto, ON, Canada
- ICON plc, Burlington, ON, Canada
| | - Suban Kangatharan
- KITE Research Institute, University Health Network, Toronto, ON, Canada
| | - Louise Brisbois
- KITE Research Institute, University Health Network, Toronto, ON, Canada
| | - Farnoosh Farahani
- KITE Research Institute, University Health Network, Toronto, ON, Canada
| | | | | | - B. Catharine Craven
- KITE Research Institute, University Health Network, Toronto, ON, Canada
- Department of Medicine, Temerty Faculty of Medicine, Toronto, ON, Canada
| |
Collapse
|
12
|
Nakajima H, Honjoh K, Watanabe S, Takahashi A, Kubota A, Matsumine A. Management of Cervical Spinal Cord Injury without Major Bone Injury in Adults. J Clin Med 2023; 12:6795. [PMID: 37959260 PMCID: PMC10650636 DOI: 10.3390/jcm12216795] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 10/24/2023] [Accepted: 10/25/2023] [Indexed: 11/15/2023] Open
Abstract
The incidence of cervical spinal cord injury (CSCI) without major bone injury is increasing, possibly because older people typically have pre-existing cervical spinal canal stenosis. The demographics, neurological injury, treatment, and prognosis of this type of CSCI differ from those of CSCI with bone or central cord injury. Spine surgeons worldwide are debating on the optimal management of CSCI without major bone injury. Therefore, this narrative review aimed to address unresolved clinical questions related to CSCI without major bone injury and discuss treatment strategies based on current findings. The greatest divide among spine surgeons worldwide hinges on whether surgery is necessary for patients with CSCI without major bone injury. Certain studies have recommended early surgery within 24 h after injury; however, evidence regarding its superiority over conservative treatment remains limited. Delayed MRI may be beneficial; nevertheless, reliable factors and imaging findings that predict functional prognosis during the acute phase and ascertain the necessity of surgery should be identified to determine whether surgery/early surgery is better than conservative therapy/delayed surgery. Quality-of-life assessments, including neuropathic pain, spasticity, manual dexterity, and motor function, should be performed to examine the superiority of surgery/early surgery to conservative therapy/delayed surgery.
Collapse
Affiliation(s)
- Hideaki Nakajima
- Department of Orthopaedics and Rehabilitation Medicine, University of Fukui Faculty of Medical Sciences, 23-3 Matsuoka Shimoaizuki, Eiheiji-cho, Yoshida-gun, Fukui 910-1193, Japan; (K.H.); (S.W.); (A.T.); (A.K.); (A.M.)
| | | | | | | | | | | |
Collapse
|
13
|
Boakye M, Ball T, Dietz N, Sharma M, Angeli C, Rejc E, Kirshblum S, Forrest G, Arnold FW, Harkema S. Spinal cord epidural stimulation for motor and autonomic function recovery after chronic spinal cord injury: A case series and technical note. Surg Neurol Int 2023; 14:87. [PMID: 37025529 PMCID: PMC10070319 DOI: 10.25259/sni_1074_2022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2022] [Accepted: 02/14/2023] [Indexed: 03/19/2023] Open
Abstract
Background:
Traumatic spinal cord injury (tSCI) is a debilitating condition, leading to chronic morbidity and mortality. In recent peer-reviewed studies, spinal cord epidural stimulation (scES) enabled voluntary movement and return of over-ground walking in a small number of patients with motor complete SCI. Using the most extensive case series (n = 25) for chronic SCI, the present report describes our motor and cardiovascular and functional outcomes, surgical and training complication rates, quality of life (QOL) improvements, and patient satisfaction results after scES.
Methods:
This prospective study occurred at the University of Louisville from 2009 to 2020. scES interventions began 2–3 weeks after surgical implantation of the scES device. Perioperative complications were recorded as well as long-term complications during training and device related events. QOL outcomes and patient satisfaction were evaluated using the impairment domains model and a global patient satisfaction scale, respectively.
Results:
Twenty-five patients (80% male, mean age of 30.9 ± 9.4 years) with chronic motor complete tSCI underwent scES using an epidural paddle electrode and internal pulse generator. The interval from SCI to scES implantation was 5.9 ± 3.4 years. Two participants (8%) developed infections, and three additional patients required washouts (12%). All participants achieved voluntary movement after implantation. A total of 17 research participants (85%) reported that the procedure either met (n = 9) or exceeded (n = 8) their expectations, and 100% would undergo the operation again.
Conclusion:
scES in this series was safe and achieved numerous benefits on motor and cardiovascular regulation and improved patient-reported QOL in multiple domains, with a high degree of patient satisfaction. The multiple previously unreported benefits beyond improvements in motor function render scES a promising option for improving QOL after motor complete SCI. Further studies may quantify these other benefits and clarify scES’s role in SCI patients.
Collapse
Affiliation(s)
- Maxwell Boakye
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| | - Tyler Ball
- Department of Neurosurgery, Vanderbilt University, Nashville,
| | - Nicholas Dietz
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| | - Mayur Sharma
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| | - Claudia Angeli
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| | - Enrico Rejc
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| | - Steven Kirshblum
- Department of Physical Medicine Rehabilitation, Rutgers, Newark, New Jersey,
| | - Gail Forrest
- Department of Physical Medicine Rehabilitation, Rutgers, Newark, New Jersey,
| | - Forest W. Arnold
- Department of Infectious Diseases, University of Louisville, Louisville, United States
| | - Susan Harkema
- Department of Neurosurgery, University of Louisville, Louisville, Kentucky,
| |
Collapse
|