Utility of MRI in Quantifying Tissue Injury in Cervical Spondylotic Myelopathy

Assessing the predictive capability of machine learning models in determining clinical outcomes for patients with cervical spondylotic myelopathy treated with laminectomy and posterior spinal fusion

BACKGROUND

Cervical spondylotic myelopathy (CSM) is a prevalent degenerative condition resulting from spinal cord compression and injury. Laminectomy with posterior spinal fusion (LPSF) is a commonly employed treatment approach for CSM patients. This study aimed to assess the effectiveness of machine learning models (MLMs) in predicting clinical outcomes in CSM patients undergoing LPSF.

METHODS

A retrospective analysis was conducted on 329 CSM patients who underwent LPSF at our institution from Jul 2017 to Jul 2023. Neurological outcomes were evaluated using the modified Japanese Orthopaedic Association (mJOA) scale preoperatively and at the final follow-up. Patients were categorized into two groups based on clinical outcomes: the favorable group (recovery rates ≥ 52.8%) and the unfavorable group (recovery rates < 52.8%). Potential predictors for poor clinical outcomes were compared between the groups. Four MLMs-random forest (RF), logistic regression (LR), support vector machine (SVM), and k-nearest neighborhood (k-NN)-were utilized to predict clinical outcome. RF model was also employed to identify factors associated with poor clinical outcome.

RESULTS

Out of the 329 patients, 185 were male (56.2%) and 144 were female (43.4%), with an average follow-up period of 17.86 ± 1.74 months. Among them, 267 patients (81.2%) had favorable clinical outcomes, while 62 patients (18.8%) did not achieve favorable results. Analysis using binary logistic regression indicated that age, preoperative mJOA scale, and symptom duration (p < 0.05) were independent predictors of unfavorable clinical outcomes. All models performed satisfactorily, with RF achieving the highest accuracy of 0.922. RF also displayed superior sensitivity and specificity (sensitivity = 0.851, specificity = 0.944). The Area under the Curve (AUC) values for RF, Logistic LR, SVM, and k-NN were 0.905, 0.827, 0.851, and 0.883, respectively. The RF model identified preoperative mJOA scale, age, symptom duration, and MRI signal changes as the most significant variables associated with poor clinical outcomes in descending order.

CONCLUSIONS

This study highlighted the effectiveness of machine learning models in predicting the clinical outcomes of CSM patients undergoing LPSF. These models have the potential to forecast clinical outcomes in this patient population, providing valuable prognostic insights for preoperative counseling and postoperative management.

Beyond the aging spine - a systematic review of functional changes in the human brain in cervical spondylotic myelopathy

Cervical Spondylotic Myelopathy (CSM) is a degenerative condition that leads to loss of cervical spinal cord integrity, typically affecting the aged population. Emerging fMRI-based evidence suggests that the brain is also affected by CSM. This systematic review aimed to understand the usefulness of brain fMRI in CSM. A comprehensive literature search was conducted until March 2023 according to PRISMA guidelines. The inclusion criteria included original research articles in English, primarily studying the human brain's functional changes in CSM using fMRI with at least 5 participants. The extracted data from each study included demographics, disease severity, MRI machine characteristics, affected brain areas, functional changes, and clinical utilities. A total of 30 studies met the inclusion criteria. Among the fMRI methods, resting-state fMRI was the most widely used experimental paradigm, followed by motor tasks. The brain areas associated with motor control were most affected in CSM, followed by the superior frontal gyrus and occipital cortex. Functional changes in the brain were correlated to clinical metrics showing clinical utility. However, the evidence that a specific fMRI metric correlating with a clinical metric was "very low" to "insufficient" due to a low number of studies and negative results. In conclusion, fMRI can potentially facilitate the diagnosis of CSM by quantitatively interrogating the functional changes of the brain, particularly areas of the brain associated with motor control. However, this field is in its early stages, and more studies are needed to establish the usefulness of brain fMRI in CSM.

Systematic review protocol for complications following surgical decompression of degenerative cervical myelopathy

BACKGROUND

Degenerative Cervical Myelopathy (DCM) is one of the most common degenerative disorders of cervical spine and sources of cord dysfunction in adults. It usually manifests with neurologic presentations such as loss of dexterity and gait issues. Treatment for moderate and severe cases of DCM is surgical decompression of the region. There are many approaches available for surgical intervention which could be categorized into anterior and posterior based on the side of neck where operation takes place. Additionally, for certain cases the hybridized anterior-posterior combined surgery is indicated. While there are many technical differences between these approaches with each having its own advantages, the complications and safety profiles of them are not fully disclosed. This protocol aims to systematically search for current reports on complications of surgical decompression methods of DCM and pool them for robust evidence generation.

METHOD

Search will be carried out in PubMed, Scopus, and Cochrane databases for retrospective and prospective surgical series, cohorts, or trials being performed for DCM with at least a sample size of 20 patients. Query strings will be designed to capture reports with details of complications with no year limit. Studies not being original (e.g., review articles, case reports, etc.), not in English, having patients younger than 18-years-old, and not reporting at least one complication will be excluded. Two independent reviewers will review the titles and abstracts for first round of screening. Full text of retrieved studies from previous round will be screened again by the same reviewers. In case of discrepancy, the third senior reviewer will be consulted. Eligible studies will then be examined for data extraction where data will be recorded into standardized form. Cumulative incidence and 95% confidence intervals of complication will be then pooled based on generalized linear mixed models with consideration of approach of surgery as subgroups. Heterogeneity tests will be performed for assessment of risk of bias.

DISCUSSION

This systematic review is aimed at providing practical information for spine surgeons on the rates of complications of different surgical approaches of DCM decompression. Proper decision-making regarding the surgical approach in addition to informing patients could be facilitated through results of this investigation.

Evaluating tissue injury in cervical spondylotic myelopathy with spinal cord MRI: a systematic review

PURPOSE

Cervical Spondylotic Myelopathy (CSM) is a degenerative condition that leads to loss of cervical spinal cord (CSC) integrity. Various spinal cord Magnetic Resonance Imaging (MRI) methods can identify and characterize the extent of this damage. This systematic review aimed to evaluate the diagnostic, biomarker, and predictive utilities of different spinal cord MRI methods in clinical research studies of CSM. The aim was to provide a comprehensive understanding of the progress in this direction for future studies and effective diagnosis and management of CSM.

METHODS

A comprehensive literature search was conducted on PubMed and EMBASE from 2010 to 2022 according to PRISMA guidelines. Studies with non-human subjects, less than 3T magnetic field strength, non-clinical design, or not quantitatively focusing on the structural integrity of CSC were excluded. The extracted data from each study included demographics, disease severity, MRI machine characteristics, quantitative metrics, and key findings in terms of diagnostic, biomarker, and predictive utilities of each MRI method. The risk of bias was performed using the guide from AHRQ. The quality of evidence was assessed separately for each type of utility for different MRI methods using GRADE.

RESULTS

Forty-seven studies met the inclusion criteria, utilizing diffusion-weighted imaging (DTI) (n = 39), magnetization transfer (MT) (n = 6), MR spectroscopy (n = 3), and myelin water imaging (n = 1), as well as a combination of MRI methods (n = 12). The metric fractional anisotropy (FA) showed the highest potential in all facets of utilities, followed by mean diffusivity. Other promising metrics included MT ratio and intracellular volume fraction, especially in multimodal studies. However, the level of evidence for these promising metrics was low due to a small number of studies. Some studies, mainly DTI, also reported the usefulness of spinal cord MRI in mild CSM.

CONCLUSIONS

Spinal cord MRI methods can potentially facilitate the diagnosis and management of CSM by quantitatively interrogating the structural integrity of CSC. DTI is the most promising MRI method, and other techniques have also shown promise, especially in multimodal configurations. However, this field is in its early stages, and more studies are needed to establish the usefulness of spinal cord MRI in CSM.

Degenerative Cervical Myelopathy: An Overview

Degenerative cervical myelopathy (DCM) is a spinal condition of growing importance due to its increasing prevalence within the ageing population. DCM involves the degeneration of the cervical spine due to various processes such as disc ageing, osteophyte formation, ligament hypertrophy or ossification, as well as coexisting congenital anomalies. This article provides an overview of the literature on DCM and considers areas of focus for future research. A patient with DCM can present with a variety of symptoms ranging from mild hand paraesthesia and loss of dexterity to a more severe presentation of gait disturbance and loss of bowel/bladder control. Hoffman's sign and the inverted brachioradialis reflex are also important signs of this disease. The gold standard imaging modality is MRI which can identify signs of degeneration of the cervical spine. Other modalities include dynamic MRI, myelography, and diffusion tensor imaging. One important scoring system to aid with the diagnosis and categorisation of the severity of DCM is the modified Japanese Orthopaedic Association score. This considers motor, sensory, and bowel/bladder dysfunction, and categorises patients into mild, moderate, or severe DCM. DCM is primarily treated with surgery as this can halt disease progression and may even allow for neurological recovery. The surgical approach will depend on the location of degeneration, the number of cervical levels involved and the pathophysiological process. Surgical approach options include anterior cervical discectomy and fusion, corpectomy, or posterior approach (laminectomy ± fusion). Conservative management is also considered for some patients with mild or non-progressive DCM or for patients where surgery is not an option. Conservative treatment may include physical therapy, traction, or neck immobilisation. Future recommendations include research into the prevalence rate of DCM and if there is a difference between populations. Further research on the benefit of conservative management for patients with mild or non-progressive DCM would be recommended.

Management of Cervical Spinal Cord Injury without Major Bone Injury in Adults

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.