Simple and Reliable Magnetic Resonance Imaging Parameter to Predict Postoperative Ambulatory Function in Patients With Metastatic Epidural Spinal Cord Compression

Kim, Young-Hoon; Ha, Kee-Yong; Park, Hyung-Youl; Cho, Chang‐Hee; Kim, Hun-Chul; Heo, Young Jin; Kim, Sang Il

doi:10.1177/21925682211000322

Cited by 4 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, and as this and previous studies show, the degree of neurological recovery of affected patients is heterogenous ( 31 , 32 ). To address this rift, many efforts have been directed at determining clinical variables that predict neurological outcome after surgery, like using radiological parameters including the cord compression ratio to estimate return of ambulatory function ( 33 ). This is intended to aid prudent surgical decision-making by weighing-out potential benefits of decompression/debulking surgery and potential instrumentation against the multimorbidity-driven complications these procedures may inflict upon subsequently bed-ridden patients.…”

Section: Discussionmentioning

confidence: 99%

Spinal oncologic paraparesis: Analysis of neurological and surgical outcomes in patients with intramedullary, extramedullary, and extradural tumors

et al. 2023

View full text Add to dashboard Cite

ObjectivesParaparesis due to oncologic lesions of the spine warrants swift neurosurgical intervention to prevent permanent disability and hence maintain independence of affected patients. Clinical parameters that predict a favorable outcome after surgical intervention could aid decision-making in emergency situations.MethodsPatients who underwent surgical intervention for paraparesis (grade of muscle strength <5 according to the British Medical Research Council grading system) secondary to spinal neoplasms between 2006 and 2020 were included in a single-center retrospective analysis. Pre- and postoperative clinical data were collected. The neurological status was assessed using the modified McCormick Disability Scale (mMcC) Score. In a univariate analysis, patients with favorable (discharge mMcC improved or stable at <3) and non-favorable outcome (discharge mMcC deteriorated or stable at >2) and different tumor anatomical compartments were statistically compared.Results117 patients with oncologic paraparesis pertaining to intramedullary lesions (n=17, 15%), intradural extramedullary (n=24, 21%) and extradural lesions (n=76, 65%) with a mean age of 65.3 ± 14.6 years were included in the analysis. Thoracic tumors were the most common (77%), followed by lumbar and cervical tumors (13% and 12%, respectively). Surgery was performed within a mean of 36±60 hours of admission across all tumors and included decompression over a median of 2 segments (IQR:1-3) and mostly subtotal tumor resection (n=83, 71%). Surgical and medical complications were documented in 9% (n=11) and 7% (n=8) of cases, respectively. The median hospital length-of-stay was 9 (7-13) days. Upon discharge, the median mMcC score had improved from 3 to 2 (p<0.0001). At last follow-up (median 180; IQR 51-1080 days), patients showed an improvement in their mean Karnofsky Performance Score (KPS) from 51.7±18.8% to 65.3±20.4% (p<0.001). Localization in the intramedullary compartment, a high preoperative mMcC score, in addition to bladder and bowel dysfunction were associated with a non-favorable outcome (p<0.001).ConclusionThe data presented on patients with spinal oncologic paraparesis provide a risk-benefit narrative that favors surgical intervention across all etiologies. At the same time, they outline clinical factors that confer a less-favorable outcome like intramedullary tumor localization, a high McCormick score and/or bladder and bowel abnormalities at admission.

show abstract

Section: Discussionmentioning

confidence: 99%

Spinal oncologic paraparesis: Analysis of neurological and surgical outcomes in patients with intramedullary, extramedullary, and extradural tumors

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Previous studies have proposed models to predict ambulatory status following spinal metastasis surgery that were developed using conventional statistical meth-ods. Numerous studies have demonstrated the efficacy of spinal metastasis surgery in improving ambulatory function using various clinical, radiographic, and treatmentrelated factors [26][27][28]. Several studies have identified successful factors for postoperative ambulation.…”

Section: Discussionmentioning

confidence: 99%

Development of Machine-Learning Models to Predict Ambulation Outcomes Following Spinal Metastasis Surgery

Chavalparit,

Wilartratsami,

Santipas

et al. 2023

Asian Spine J

View full text Add to dashboard Cite

Study Design: Retrospective cohort study.Purpose: This study aimed to develop machine-learning algorithms to predict ambulation outcomes following surgery for spinal metastasis.Overview of Literature: Postoperative ambulation status following spinal metastasis surgery is currently difficult to predict. The improved ability to predict this important postoperative outcome would facilitate management decision-making and help in determining realistic treatment goals.Methods: This retrospective study included patients who underwent spinal metastasis at a university-based medical center in Thailand between January 2009 and November 2021. Collected data included preoperative parameters and ambulatory status 90 and 180 days following surgery. Thirteen machine-learning algorithms, namely, artificial neural network, logistic regression, CatBoost classifier, linear discriminant analysis, extreme gradient boosting, extra trees classifier, random forest classifier, gradient boosting classifier, light gradient boosting machine, naïve Bayes, K-neighbor classifier, Ada boost classifier, and decision tree classifier were developed to predict ambulatory status 90 and 180 days following surgery. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1-score.Results: In total, 167 patients were enrolled. The number of patients classified as ambulatory 90 and 180 days following surgery was 140 (81.9%) and 137 (82.0%), respectively. The extreme gradient boosting algorithm was found to most accurately predict 180-day ambulatory outcome (AUC, 0.85; F1-score, 0.90), and the decision tree algorithm most accurately predicted 90-day ambulatory outcome (AUC, 0.94; F1-score, 0.88).Conclusions: Machine-learning algorithms were effective in predicting ambulatory status following surgery for spinal metastasis. Based on our data, the extreme gradient boosting and decision tree best predicted postoperative ambulatory status 180 and 90 days after spinal metastasis surgery, respectively.

show abstract

“…At present, the diagnosis of CSM is mainly based on clinical symptoms, signs, and clinical imaging. Magnetic resonance imaging (MRI) is an invaluable and irreplaceable modality for radiographic neurological assessment by visualizing the degree of spinal cord compression and the signal changes of the spinal cord ( 6 , 7 ).…”

Section: Introductionmentioning

confidence: 99%

Predictive Nomogram for Clinical Prognosis in Cervical Spondylotic Myelopathy With Intramedullary T2-Weighted Increased Signal Intensity: A Novel Digital Tool for Patient Prognosis Education

Wang

Yang

2022

Front. Public Health

View full text Add to dashboard Cite

AimsTo establish a predictive nomogram for clinical prognosis in cervical spondylotic myelopathy (CSM) with intramedullary T2-weighted increased signal intensity (ISI).MethodsThe clinical data of 680 patients with CSM with intramedullary T2-weighted ISI were retrospectively analyzed. The patients were divided into the modeling group (476) and the validation group (204) by using a random number table at a ratio of 7:3. The independent prognostic factors were screened using multivariate logistic regression analysis. The factors were subsequently incorporated into the establishment of the predictive nomogram. The area under the receiver operating characteristic (ROC) curve (AUC) was undertaken to estimate the discrimination of the predictive nomogram. The calibration curve and the Hosmer-Lemeshow test were used to assess the calibration of the predictive nomogram. The clinical usefulness of the predictive nomogram was evaluated by decision curve analysis (DCA).ResultsBased on the pre-operative Japanese Orthopedic Association (JOA) score, maximal canal compromise (MCC), and maximal spinal cord compression (MSCC), we established a predictive nomogram. The AUCs in the modeling group and validation group were 0.892 (95% CI: 0.861~0.924) and 0.885 (95% CI: 0.835~0.936), respectively, suggesting good discrimination of the nomogram. Calibration curves showed a favorable consistency between the predicted probability and the actual probability. In addition, the values of P of the Hosmer-Lemeshow were 0.253 and 0.184, respectively, suggesting good calibration of the nomogram. DCA demonstrated that the nomogram had good clinical usefulness.ConclusionWe established and validated a predictive nomogram for the clinical prognosis in CSM with intramedullary T2-weighted ISI. This predictive nomogram could help clinicians and patients identify high-risk patients and educate them about prognosis, thereby improving the prognosis of high-risk patients.

show abstract

Simple and Reliable Magnetic Resonance Imaging Parameter to Predict Postoperative Ambulatory Function in Patients With Metastatic Epidural Spinal Cord Compression

Cited by 4 publications

References 37 publications

Spinal oncologic paraparesis: Analysis of neurological and surgical outcomes in patients with intramedullary, extramedullary, and extradural tumors

Spinal oncologic paraparesis: Analysis of neurological and surgical outcomes in patients with intramedullary, extramedullary, and extradural tumors

Development of Machine-Learning Models to Predict Ambulation Outcomes Following Spinal Metastasis Surgery

Predictive Nomogram for Clinical Prognosis in Cervical Spondylotic Myelopathy With Intramedullary T2-Weighted Increased Signal Intensity: A Novel Digital Tool for Patient Prognosis Education

Contact Info

Product

Resources

About