Application of machine learning (ML) in neuroimaging is often constrained by the difficulty of assembling, sharing, and utilizing large, high-quality datasets. Synthetic data may address limitations in traditional data-sharing by enabling privacy-preserving image generation at scale. We evaluated whether: (1) a denoising diffusion probabilistic model (DDPM) could generate realistic synthetic lateral cervical spine radiographs, and (2) whether synthetic data could support transfer learning for anatomical landmark localization in low-data settings. We trained a DDPM on 4,963 radiographs from the Cervical Spine X-ray Atlas (CSXA) to generate synthetic images. Blinded expert validation involved six neuroradiologists and two spine fellowship-trained neurosurgeons reviewing 50 randomly selected image quartets, each containing one real and three synthetic images. Experts attempted to identify the real scan and rated the realism of each image on a four-point Likert scale. To assess privacy preservation and potential memorization, we performed a real-synthetic nearest-neighbor search using vision transformer image embeddings ranked by cosine similarity. We then generated pseudolandmarks for our curated synthetic dataset and trained a landmark-localization backbone. External evaluation was performed on the Cervical Lateral X-ray 34-point (CLX-34) dataset using a directly matched 22-landmark task, comparing fine-tuning from the synthetic backbone and de novo training on increasing amounts of CLX-34 data. Experts correctly identified the real image in 29.0

Study Design Cross-sectional, web-based international survey study.Objectives To assess spine surgeons' perspectives on the importance of Enhanced Recovery After Surgery (ERAS) components and barriers to implementing ERAS programs in degenerative lumbar fusion.Methods In May 2024, a web-based survey was distributed to AOSpine members. The survey covered eight ERAS components derived from the 2021 consensus statement for perioperative care in lumbar fusion. Respondents selected up to three components with the biggest perceived impact on recovery and up to three with the greatest room for improvement. Responses were summarized in a priority matrix. Demographics, perceived barriers, and implementation support needs were analyzed using descriptive statistics.Results The survey was accessed by 400 individuals, yielding 322 responses (80.5%) and a 76.7% completion rate. Respondents represented academic (50.6%), private (28.9%), and local/community hospitals (20.5%) worldwide. ERAS components perceived to have the biggest impact on recovery were multimodal opioid-sparing analgesia (73.3%), early mobilization (63.8%), and preoperative education & counselling (58.6%), which were also identified as having the greatest room for improvement (39.4%, 41.4%, and 62.6%, respectively). Key barriers were the absence of clear protocols and guidelines (56.2%), staff shortages (53.8%), and difficulties coordinating implementation and adherence (43.0%).Conclusion Multimodal opioid-sparing analgesia, early mobilization, and preoperative education & counselling were identified as ERAS components with the biggest perceived impact on patient recovery and the greatest room for improvement. Targeted efforts in these domains may represent an important opportunity to enhance perioperative care and support the implementation of ERAS programs in lumbar spinal fusion.

Study Design/SettingScoping review.ObjectiveTo map the landscape of endoscopic spine surgery research, identify areas of clinical application, and highlight evidence gaps to guide future studies.MethodsFollowing PRISMA-ScR guidelines, systematic searches were performed across MEDLINE, EMBASE, CINAHL, and Cochrane Library (January 1, 2010-September 22, 2024). Eligible studies involved adults undergoing uniportal or biportal endoscopic spine surgery. Non-English studies, case reports (<5 patients), and abstracts were excluded. Two reviewers independently screened studies, with conflicts resolved by the senior author.ResultsA total of 1193 studies including 877 285 patients were identified, with publications increasing markedly over the past decade. Most studies were low-level evidence, primarily case series (49.3%) and retrospective cohorts (33.2%). Clinical effectiveness without comparison groups was common (35.3%). Lumbar disc herniation (47.3%) and uniportal endoscopy (83.9%) were the most studied pathology and technique, respectively. The transforaminal approach (50.4%) was more frequently evaluated than the interlaminar approach (30.0%). Outcomes often included pain scores (85.5%) and complication/readmission rates (79.5%). Few studies examined learning curve (0.8%), economic impact (0.7%), or neuromonitoring (0.5%). Research on enabling technologies such as navigation, robotics, and augmented reality accounted for 3% of studies.ConclusionsThe literature on spine endoscopy is expanding but remains dominated by low-level evidence focused on lumbar uniportal transforaminal approaches. High-quality studies are needed to advance the field.

Background:Prolonged length of stay (LOS) after elective spine surgery is associated with an increased risk of in-hospital complications and higher healthcare costs. This ambispective cohort study investigates the association between poor postoperative pain control and prolonged LOS, while adjusting for known risk factors and perioperative adverse events. Methods:Consecutive adult patients undergoing elective spine surgery were enrolled. The primary outcome was prolonged LOS (≥75th percentile; ≥6 days). The primary independent variable was poor pain control on postoperative day 1 (POD1; mean numeric rating scale >4 in the first 24 hours after surgery). Baseline demographics, surgical characteristics, and perioperative adverse events were collected. Univariable and multivariable logistic regression analyses with multiple imputation were performed to investigate the relationship between poor pain control and prolonged LOS. Results:In 1,078 patients, the mean LOS was 4.8 days, and 57% of patients experienced poor pain control. Multivariable analyses revealed poor pain control was independently associated with prolonged LOS (OR 1.83 [95% CI = 1.16-2.89], p = .009), after adjusting for age (p = .27), female sex (p = .002), perioperative blood transfusion (p = .030), postoperative airway/breathing/circulation adverse events (p < .001), constipation (p = .013), urinary tract infection (p = .002), urinary retention (p < .001), hematoma (p < .001), surgical site infection (p < .001), neurologic deterioration (p < .001), POD1 morphine equivalent dose (p < .001), preoperative disability score (p = .04), ASA physical status score (p = .03), smoking status (p = .03), surgical levels (p < .001), estimated blood loss (p = .012), intraoperative dural tears (p = .04), and fusion surgery (p < .001). Conclusions:Poor POD1 pain control was independently associated with prolonged LOS. Improved postoperative pain experience may lead to reduced LOS after elective spine surgery.

BACKGROUND AND IMPORTANCE:Paradoxical herniation (PH) is a rare but life-threatening complication after decompressive hemicraniectomy (DHC) performed to treat refractory intracranial hypertension. Although most cases occur subacutely or after cerebrospinal fluid (CSF) diversion, acute presentations without preceding CSF manipulation are uncommon and may be underrecognized.CLINICAL PRESENTATION:We report the case of a 45-year-old woman who developed acute PH after undergoing DHC for severe vasogenic edema after resection of a parieto-occipital meningioma. After initial postoperative neurological improvement, she experienced rapid neurological deterioration. Imaging demonstrated cerebellar tonsillar herniation and brain shift away from the craniectomy site, consistent with PH. Trendelenburg positioning resulted in prompt neurological improvement, confirming the diagnosis. We additionally performed a systematic review of reported cases of PH after tumor resection.CONCLUSION:PH should be considered in patients with fluctuating or worsening neurological status after DHC, even in the absence of prior CSF diversion. Early recognition is critical, as standard intracranial pressure-lowering therapies may exacerbate herniation. Management requires immediate cessation of such therapies, initiation of intracranial pressure-augmenting measures, and prompt cranioplasty as definitive treatment.

This study aimed to estimate the effects of preoperative psychological health on postoperative outcomes in patients undergoing surgery for cervical spondylotic radiculopathy. This retrospective cohort study included data from patients enrolled in the Canadian Spine Outcomes and Research Network who underwent anterior cervical discectomy and fusion for radiculopathy. Preoperative psychological health was measured with the Patient Health Questionnaire-8 (PHQ-8), and depression and severe psychological symptomology were measured with the Mental Component Score of the Short Form Survey-12 (MCS). Surgical outcomes comprised trajectory subgroups for neck pain and arm pain (numeric rating scales) and disability (neck disability index) measured preoperatively and 3, 12, and 24 months after surgery. For each outcome, patients were dichotomized as following either a poor or a fair-to-excellent trajectory. Average treatment effects were estimated with doubly robust propensity score models using inverse probability of treatment weights accounting for multiple confounders. We included data from 352 patients (43.8% female). Approximately half (52.1%) of patients were identified as depressed based on the PHQ-8, while 61.8% and 33.1% were classified as experiencing depression or severe psychological symptomology, respectively, on the MCS. In fully adjusted models, patients with PHQ-8-measured depression were at increased risk of poor postoperative outcomes for disability (risk ratio[95% CI] = 6.73[1.85 to 24.45]) and neck pain (RR[95% CI] = 1.90[1.09 to 3.32]). Patients with MCS-measured depression were at elevated risk of a poor disability outcome (RR[95% CI] = 2.77[1.30 to 5.90]). Patients reporting severe psychological symptomatology had an increased likelihood of poor disability, neck pain, and arm pain outcomes (RR[95% CI] = 1.82 [1.17 to 2.82] to 2.84[1.58 to 5.09]). These findings highlight the high prevalence of negative psychological features and their impacts on neck surgery outcomes. Future research should prioritize the development and evaluation of preoperative interventions to optimize psychological well-being and improve surgical outcomes in this population.

Patients with severe traumatic brain injury (TBI) are at high risk of venous thromboembolism (VTE). However, the optimal timing for initiating chemical VTE prophylaxis (cVTEp) remains controversial due to concerns for intracranial hemorrhage progression. Five databases were searched (inception to October 2024) for studies evaluating early versus late cVTEp initiation in severe TBI (defined as Glasgow Coma Scale score ≤ 8 or Abbreviated Injury Scale score ≥ 3). Data were extracted independently and pooled using random-effects models. Early versus late cVTEp initiation and stratified analyses (for cutoffs at ≤ 24, ≤ 48, and ≤ 72 h) were performed, and odds ratios (ORs) were calculated. Outcomes included VTE, hemorrhage progression, neurosurgical intervention, and in-hospital mortality. Absolute risk reduction (ARR) was calculated using control event rates and ORs. Risk of bias was assessed by the Risk of Bias in Non-Randomized Studies-of Interventions tool. Twenty-one studies were included in the systematic review, with 14 (n = 24,401) included in the meta-analysis. Early compared to late cVTEp initiation was associated with lower odds of VTE (OR 0.47; 95

BACKGROUND AND OBJECTIVES: Degenerative cervical myelopathy (DCM) is the most common cause of spinal dysfunction globally. Despite surgical intervention, motor dysfunction may persist in many patients. The purpose of this study was to comprehensively examine specific spinal cord tract changes in patients with DCM, to better understand potential substrates for compensatory recovery of function. METHODS: Cervical spinal cord MRI scans with diffusion tensor imaging were performed in patients with DCM and in healthy volunteers. Spinal Cord Toolbox was used to register the PAM50 template, which includes a probabilistic atlas of the white matter tracts of the spinal cord, to the imaging data. Fractional anisotropy (FA) was extracted for each tract at C3 above the level of maximal compression and compared between patients with DCM and healthy volunteers and between patients with mild vs moderate to severe DCM. RESULTS: We included 25 patients with DCM (13 mild and 12 moderate to severe) and 6 healthy volunteers. FA was significantly reduced in DCM subjects relative to healthy volunteers for the lateral corticospinal tract (mild DCM vs healthy ∆ = −0.13, P = .018; moderate to severe DCM vs healthy ∆ = −0.11, P = .047), fasciculus gracilis (mild DCM vs healthy ∆ = −0.16, P = .010; moderate to severe DCM vs healthy ∆ = −0.13, P = .039), and fasciculus cuneatus (mild DCM vs healthy ∆ = −0.16, P = .007; moderate to severe DCM vs healthy ∆ = −0.15, P = .012). There were no differences in FA for all tracts between mild and moderate-to-severe DCM subjects. CONCLUSION: Patients with DCM had altered diffusion tensor imaging signal in their lateral corticospinal tract, fasciculus gracilis, and fasciculus cuneatus in comparison with healthy volunteers. These findings indicate that DCM is characterized by injury to these structures, which suggests that other tracts within the cord could potentially act as substrates for compensatory motor recovery.

Machine learning in neurosurgery is limited by challenges in assembling large, high-quality imaging datasets. Synthetic data offers a scalable, privacy-preserving solution. We evaluated the feasibility of generating realistic lateral cervical spine radiographs using a denoising diffusion probabilistic model (DDPM) trained on 4,963 images from the Cervical Spine X-ray Atlas. Model performance was monitored via training/validation loss and Frechet inception distance, and synthetic image quality was assessed in a blinded "clinical Turing test" with six neuroradiologists and two spine-fellowship trained neurosurgeons. Experts reviewed 50 quartets containing one real and three synthetic images, identifying the real image and rating realism on a 4-point Likert scale. Experts correctly identified the real image in 29

The impact of spine surgery on Health-Related Quality-of-Life (HRQoL) outcomes across common spinal degenerative diagnoses is not well characterised. A prospective observational study of patients enrolled in the Canadian Spine Outcomes and Research Network (CSORN) registry was performed. Baseline and 1-year post-operative Short Form-12 Physical Component Summary (PCS) and Mental Component Summary (MCS) scores were collated and compared to normative values from the Canadian General Population (CGP). The percentage of patients achieving the PCS Minimum Clinically Important Difference (MCID) was quantified. 5049 patients were included in the analysis. The mean pre-operative SF-12 PCS was 29.5 and MCS was 44.1. This improved to a mean PCS of 40.5 ( p < 0.001) and MCS of 49.3 ( p < 0.0001) at 1-year post-operatively. The mean pre-operative PCS was over 2 standard deviations (SD) lower than the normative mean of the CGP; this improved to being close to 1-SD from the normative CGP mean at 1-year post-operatively. Findings were similar across age- and sex-stratified subgroups. Across all conditions, 70–75% of patients achieved the PCS MCID. Fewer patients with cervical myelopathy achieved the PCS MCID (59%). In a surgical cohort, patients with degenerative spinal conditions demonstrate a profound reduction in PCS compared to their peers in the CGP. Spinal surgery was impactful in improving physical function HRQoL outcomes in the majority, but not typically to average population norms.

An abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the 'Save PDF' action button.

Background Degenerative cervical myelopathy (DCM) is the most common form of atraumatic spinal cord injury globally. Clinical guidelines regarding surgery for patients with mild DCM and minimal symptoms remain uncertain. This study aims to identify imaging and clinical predictors of neurological deterioration in mild DCM and explore pathophysiological correlates to guide clinical decision-making.Methods Patients with mild DCM underwent advanced MRI scans that included T2-weighted, diffusion tensor imaging and magnetisation transfer (MT) sequences, along with clinical outcome measures at baseline and 6-month intervals after enrolment. Quantitative MRI (qMRI) metrics were derived above and below maximally compressed cervical levels (MCCLs). Various machine learning (ML) models were trained to predict 6 month neurological deterioration, followed by global and local model interpretation to assess feature importance.Results A total of 49 patients were followed for a maximum of 2 years, contributing 110 6-month data entries. Neurological deterioration occurred in 38% of cases. The best-performing ML model, combining clinical and qMRI metrics, achieved a balanced accuracy of 83%, and an area under curve-receiver operating characteristic of 0.87. Key predictors included MT ratio (demyelination) above the MCCL in the dorsal and ventral funiculi and moderate tingling in the arm, shoulder or hand. qMRI metrics significantly improved predictive performance compared to models using only clinical (bal. acc=68.1%) or imaging data (bal. acc=57.4%).Conclusions Reduced myelin content in the dorsal and ventral funiculi above the site of compression, combined with sensory deficits in the hands and gait/balance disturbances, predicts 6-month neurological deterioration in mild DCM and may warrant early surgical intervention.

An abstract is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

BACKGROUND:Adjacent segment disease (ASD) is a known sequela of thoracolumbar instrumented fusions. Various surgical options are available to address ASD in patients with intractable symptoms who have failed conservative measures. However, the optimal treatment strategy for symptomatic ASD has not been established. We examined several clinical outcomes utilizing different surgical interventions for symptomatic ASD. METHODS:A retrospective review was performed for a consecutive series of patients undergoing revision surgery for thoracolumbar ASD between October 2011 and February 2022. Patients were treated with endoscopic decompression (N = 17), microdiscectomy (N = 9), lateral lumbar interbody fusion (LLIF; N = 26), or open laminectomy and fusion (LF; N = 55). The primary outcomes compared between groups were re-operation rates and numeric pain scores for leg and back at 2 weeks, 10 weeks, 6 months, and 12 months postoperation. Secondary outcomes included time to re-operation, estimated blood loss, and length of stay. RESULTS:Of the 257 patients who underwent revision surgery for symptomatic ASD, 107 patients met inclusion criteria with a minimum of 1-year follow-up. The mean age of all patients was 67.90 ± 10.51 years. There was no statistically significant difference between groups in age, gender, preoperative American Society of Anesthesiologists scoring, number of previously fused levels, or preoperative numeric leg and back pain scores. The re-operation rates were significantly lower in LF (12.7%) and LLIF cohorts (19.2%) compared with microdiscectomy (33%) and endoscopic decompression (52.9%; P = 0.005). Only LF and LLIF cohorts experienced significantly decreased pain scores at all 4 follow-up visits (2 weeks, 10 weeks, 6 months, and 12 months; P < 0.001 and P < 0.05, respectively) relative to preoperative scores. CONCLUSION:Symptomatic ASD often requires treatment with revision surgery. Fusion surgeries (either stand-alone lateral interbody or posterolateral with instrumentation) were most effective and durable with respect to alleviating pain and avoiding additional revisions within the first 12 months following revision surgery. CLINICAL RELEVANCE:This study emphasizes the importance of risk-stratifying patients to identify the least invasive approach that treats their symptoms and reduces the risk of future surgeries. LEVEL OF EVIDENCE: 3:

Degenerative Cervical Myelopathy (DCM) is the functional derangement of the spinal cord resulting from vertebral column spondylotic degeneration. Typical neurological symptoms of DCM include gait imbalance, hand/arm numbness, and upper extremity dexterity loss. Greater spinal cord compression is believed to lead to a higher rate of neurological deterioration, although clinical experience suggests a more complex mechanism involving spinal canal diameter (SCD). In this study, we utilized machine learning clustering to understand the relationship between SCD and different patterns of cord compression (i.e. compression at one disc level, two disc levels, etc.) to identify patient groups at risk of neurological deterioration. 124 MRI scans from 51 non-operative DCM patients were assessed through manual scoring of cord compression and SCD measurements. Dimensionality reduction techniques and k-means clustering established patient groups that were then defined with their unique risk criteria. We found that the compression pattern is unimportant at SCD extremes (<= 14.5 mm or > 15.75 mm). Otherwise, severe spinal cord compression at two disc levels increases deterioration likelihood. Notably, if SCD is normal and cord compression is not severe at multiple levels, deterioration likelihood is relatively reduced, even if the spinal cord is experiencing compression. We elucidated five patient groups with their associated risks of deterioration, according to both SCD range and cord compression pattern. Overall, SCD and focal cord compression alone do not reliably predict an increased risk of neurological deterioration. Instead, the specific combination of narrow SCD with multi-level focal cord compression increases the likelihood of neurological deterioration in mild DCM patients.

Postoperative infection after spinal deformity correction in pediatric patients is associated with significant costs. Identifying risk factors associated with postoperative infection would help surgeons identify high-risk patients that may require interventions to minimize infection risk. To investigate risk factors associated with 30-day postoperative infection in pediatric patients who have received posterior arthrodesis for spinal deformity correction. Retrospective review of prospectively collected data. The National Surgical Quality Improvement Program Pediatric database for years 2016–2021 was used for this study. Patients were included if they received posterior arthrodesis for scoliosis or kyphosis correction (CPT 22,800, 22,802, 22,804). Anterior only approaches were excluded. TThe outcome of interest was 30-day postoperative infection. Patient demographics and outcomes were analyzed using descriptive statistics. Multivariable logistic regression analysis using likelihood ratio backward selection method was used to identify significant risk factors for 30-day infection to create the Pediatric Scoliosis Infection Risk Score (PSIR Score). ROC curve analysis, predicted probabilities, and Hosmer Lemeshow goodness-of-fit test were done to assess the scoring system on a validation cohort. A total of 31,742 patients were included in the study. The mean age was 13.8 years and 68.7

BACKGROUND CONTEXT:A significant proportion of patients experience poorly controlled surgical pain and fail to achieve satisfactory clinical improvement after spine surgery. However, a direct association between these variables has not been previously demonstrated. PURPOSE:To investigate the association between poor postoperative pain control and patient-reported outcomes after spine surgery. STUDY DESIGN:Ambispective cohort study. PATIENT SAMPLE:Consecutive adult patients (≥18-years old) undergoing inpatient elective cervical or thoracolumbar spine surgery. OUTCOME MEASURE:Poor surgical outcome was defined as failure to achieve a minimal clinically important difference (MCID) of 30% improvement on the Oswestry Disability Index or Neck Disability Index at follow-up (3-months, 1-year, and 2-years). METHODS:Poor pain control was defined as a mean numeric rating scale score of >4 during the first 24-hours after surgery. Multivariable mixed-effects regression was used to investigate the relationship between poor pain control and changes in surgical outcomes while adjusting for known confounders. Secondarily, the Calgary Postoperative Pain After Spine Surgery (CAPPS) Score was investigated for its ability to predict poor surgical outcome. RESULTS:Of 1294 patients, 47.8%, 37.3%, and 39.8% failed to achieve the MCID at 3-months, 1-year, and 2-years, respectively. The incidence of poor pain control was 56.9%. Multivariable analyses showed poor pain control after spine surgery was independently associated with failure to achieve the MCID (OR 2.35 [95% CI=1.59-3.46], p<.001) after adjusting for age (p=.18), female sex (p=.57), any nicotine products (p=.041), ASA physical status >2 (p<.001), ≥3 motion segment surgery (p=.008), revision surgery (p=.001), follow-up time (p<.001), and thoracolumbar surgery compared to cervical surgery (p=.004). The CAPPS score was also found to be independently predictive of poor surgical outcome. CONCLUSION:Poor pain control in the first 24-hours after elective spine surgery was an independent risk factor for poor surgical outcome. Perioperative treatment strategies to improve postoperative pain control may lead to improved patient-reported surgical outcomes.

BACKGROUND Percutaneous intradiscal hydrogel injection has been used to treat low-back pain (LBP) due to degenerative disc disease with or without mild radicular pain. Complications from these procedures are underreported. In this case lesson, the authors present a rare case of a patient with herniated intradiscal hydrogel following a minor trauma leading to neurological injury. OBSERVATIONS A 36-year-old female who had been previously treated with L4-5 and L5-S1 intradiscal hydrogel injections for LBP presented with painful, progressive right-sided lower-extremity weakness after experiencing a twisting trauma. Cross-sectional imaging results revealed a herniated hydrogel-based disc implant in the spinal canal. She underwent an urgent L4-5 laminectomy for decompression and removal of the herniated implant. A large annular defect was noted. Postoperatively, she had resolution of her right leg pain but experienced persistent right foot drop requiring an ankle-foot orthosis. LESSONS Herniated intradiscal hydrogel implants can lead to permanent neurological injury. While the risk factors for hydrogel herniation have not been elucidated, they can be related to pre-existing disruptions to the annulus and/or posterior longitudinal ligament, excess volume of hydrogel injection, and insufficient fixation time. Further research is needed to determine the safety and efficacy of this technology.

BACKGROUND CONTEXT:Degenerative cervical myelopathy (DCM) is the most common form of atraumatic spinal cord injury globally. Degeneration of spinal discs, bony osteophyte growth and ligament pathology results in physical compression of the spinal cord contributing to damage of white matter tracts and grey matter cellular populations. This results in an insidious neurological and functional decline in patients which can lead to paralysis. Magnetic resonance imaging (MRI) confirms the diagnosis of DCM and is a prerequisite to surgical intervention, the only known treatment for this disorder. Unfortunately, there is a weak correlation between features of current commonly acquired MRI scans ("community MRI, cMRI") and the degree of disability experienced by a patient. PURPOSE:This study examines the predictive ability of current MRI sequences relative to "advanced MRI" (aMRI) metrics designed to detect evidence of spinal cord injury secondary to degenerative myelopathy. We hypothesize that the utilization of higher fidelity aMRI scans will increase the effectiveness of machine learning models predicting DCM severity and may ultimately lead to a more efficient protocol for identifying patients in need of surgical intervention. STUDY DESIGN/SETTING:Single institution analysis of imaging registry of patients with DCM. PATIENT SAMPLE:A total of 296 patients in the cMRI group and 228 patients in the aMRI group. OUTCOME MEASURES:Physiologic measures: accuracy of machine learning algorithms to detect severity of DCM assessed clinically based on the modified Japanese Orthopedic Association (mJOA) scale. METHODS:Patients enrolled in the Canadian Spine Outcomes Research Network registry with DCM were screened and 296 cervical spine MRIs acquired in cMRI were compared with 228 aMRI acquisitions. aMRI acquisitions consisted of diffusion tensor imaging, magnetization transfer, T2-weighted, and T2*-weighted images. The cMRI group consisted of only T2-weighted MRI scans. Various machine learning models were applied to both MRI groups to assess accuracy of prediction of baseline disease severity assessed clinically using the mJOA scale for cervical myelopathy. RESULTS:Through the utilization of Random Forest Classifiers, disease severity was predicted with 41.8% accuracy in cMRI scans and 73.3% in the aMRI scans. Across different predictive model variations tested, the aMRI scans consistently produced higher prediction accuracies compared to the cMRI counterparts. CONCLUSIONS:aMRI metrics perform better in machine learning models at predicting disease severity of patients with DCM. Continued work is needed to refine these models and address DCM severity class imbalance concerns, ultimately improving model confidence for clinical implementation.