Analysis of combined clinical and diffusion basis spectrum imaging metrics to predict the outcome of chronic cervical spondylotic myelopathy following cervical decompression surgery

J Neurosurg Spine, 2022 · DOI: 10.3171/2022.3.SPINE2294 · Published: October 1, 2022

Spinal Cord Injury Surgery Bioinformatics

Simple Explanation

Cervical spondylotic myelopathy (CSM) is a common spinal cord injury where the spinal cord is compressed. The study uses a new MRI technique, diffusion basis spectrum imaging (DBSI), to better see white matter damage. The goal is to predict how well patients with CSM will recover after surgery using DBSI and clinical data. The researchers used a support vector machine (SVM) to analyze clinical data and DBSI metrics. The SVM was trained to predict patient outcomes based on changes in mJOA scale scores after surgery. The results suggest that combining clinical information with DBSI metrics can more accurately predict patient outcomes after surgery for CSM compared to using clinical information with traditional DTI metrics.

Study Duration

12–24 months

Participants

50 patients with CSM and 20 healthy controls

Evidence Level

Not specified

Key Findings

1
The SVM trained with clinical and DBSI metrics achieved an accuracy of 88.1% and an area under the curve of 0.95 in predicting patient outcomes.
2
DBSI metrics, along with clinical presentation, could serve as a surrogate in prognosticating outcomes of patients with CSM.
3
DBSI metrics can classify CSM disease severity consistent with clinical guidelines with high accuracy.

Research Summary

This study investigates the use of Diffusion Basis Spectrum Imaging (DBSI) in combination with clinical metrics to predict outcomes of cervical decompression surgery for Cervical Spondylotic Myelopathy (CSM). The study found that a support vector machine (SVM) trained with both clinical and DBSI metrics demonstrated higher accuracy in predicting patient outcomes compared to using clinical and Diffusion Tensor Imaging (DTI) metrics. The findings suggest that DBSI metrics, combined with clinical data, show promise as a predictor of functional recovery in patients with CSM and could potentially aid surgeons in determining the suitability and timing of surgery.

Practical Implications

Improved Outcome Prediction

Combining clinical and DBSI metrics provides a more accurate prediction of patient outcomes following cervical decompression surgery for CSM, enabling better informed clinical decision-making.

Personalized Treatment

The ability to predict surgical outcomes using DBSI and clinical data can help identify which patients are most likely to benefit from surgery and guide personalized treatment plans.

Optimized Surgical Timing

Clinical+DBSI-SVM could help surgeons identify an optimum time during the disease progression for surgery.

Study Limitations

1
The study did not explore cortical or subcortical areas of the brain in the DBSI analysis.
2
The data set was unbalanced among patient outcomes determined using postoperative clinical assessments.
3
This study used data from a small sample size collected by a single institution.

Your Feedback

Was this summary helpful?

Back to Spinal Cord Injury