Prediction Models in Degenerative Spine Surgery: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

To review the existing literature of prediction models in degenerative spinal surgery.

METHODS

Review of PubMed/Medline and Embase databases was conducted to identify articles between January 1, 2000 and March 1, 2020 that reported prediction model performance for outcomes following elective degenerative spine surgery.

RESULTS

Thirty-one articles were included. Twenty studies were of thoracolumbar, 5 were of cervical, and 6 included all spine patients. Five studies were externally validated. Prediction models were developed using machine learning (42%) and logistic regression (42%) as well as other techniques. Web-based calculators were included in 45% of published articles. Various outcomes were investigated, including complications, infection, length of stay, discharge disposition, reoperation, readmission, disability score, back pain, leg pain, return to work, and opioid dependence.

CONCLUSIONS

Significant heterogeneity exists in methods used to develop prediction models of postoperative outcomes after degenerative spine surgery. Most internally validate their scores, but a few have been externally validated. Areas under the curve for most models range from 0.6 to 0.9. Techniques for development are becoming increasingly sophisticated with different machine learning tools. With further external validation, these models can be deployed online for patient, physician, and administrative use, and have the potential to optimize outcomes and maximize value in spine surgery.

Utility of the 5-Item Modified Frailty Index for Predicting Adverse Outcomes Following Elective Anterior Cervical Discectomy and Fusion

BACKGROUND

Frailty is an increasingly studied tool for preoperative risk stratification, but its prognostic value for anterior cervical discectomy and fusion (ACDF) patients is unclear. We sought to evaluate the association of the 5-item modified Frailty Index (5i-mFI) with 30-day adverse outcomes following ACDF and its predictive performance compared with other common metrics.

METHODS

The National Surgical Quality Improvement Program was queried from 2016-2018 for patients undergoing elective ACDF for degenerative diseases. Outcomes of interest included 30-day complications, extended length of stay (LOS), non-home discharge, and unplanned readmissions. Unadjusted/adjusted odds ratios were calculated. The discriminatory performance of the 5i-mFI compared with age, American Society of Anesthesiologists (ASA) classification, and body mass index was computed using the area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 23,754 patients were identified. On adjusted analysis, an index of 1 was significantly associated with extended LOS, non-home discharge, and unplanned readmissions (P < 0.001, P = 0.023, P = 0.003, respectively), but not complications (all P > 0.05). An index ≥2 was significantly associated with each outcome (all P < 0.001). The 5i-mFI was found to have a significantly higher AUC than body mass index for each outcome, a similar AUC compared with ASA classification and age for complications and unplanned readmissions, and a significantly lower AUC than ASA classification and age for extended LOS and non-home discharge.

CONCLUSIONS

The 5i-mFI was found to be significantly associated with 30-day adverse outcomes following ACDF but had similar or lesser predictive performance compared with more universally available and easily implemented metrics, such as ASA classification and age.