Frederik R. Teunissen, Bianca M. Verbeek, Thomas D. Cha and Joseph H. Schwab
Spinal cord injury (SCI) is a major complication of spinal fractures in patients with ankylosing spondylitis (AS) and diffuse idiopathic skeletal hyperostosis (DISH). Due to the uncommon nature of these conditions, existing literature consists of relatively small case series without detailed neurological data. This study aims to investigate the incidence, predictors, and sequelae of SCI in patients with a traumatic fracture of the ankylosed spine.
The study included all patients older than 18 years of age with AS or DISH who presented to two affiliated tertiary care centers between January 1, 1990, and January 1, 2016, and had a traumatic fracture of the spine. Factors associated with SCI after traumatic fracture were compared using Fisher’s exact tests. Logistic regression was used for the analysis of predictive factors for SCI. For the comparison of probability of survival between patients with and without SCI, Kaplan-Meier methodology was used.
One hundred seventy-two patients with a traumatic fracture of an ankylosed spine were included. Fifty-seven patients (34.1%) had an SCI associated with the fracture. The cervical spine was the most fractured region for patients both with (77.2%) and without (51.4%) SCI. A cervical fracture (odds ratio [OR] 2.70, p = 0.024) and a spinal epidural hematoma (SEH) after fracture (OR 2.69, p = 0.013) were predictive of SCI. Eleven patients (19.3%) with SCI had delayed SCI (range 8–230 days). Of 44 patients with SCI and sufficient follow-up, 20 (45.5%) had neurological improvement after treatment. Early and late complication rates were significantly higher (p = 0.001 and p = 0.004) and hospital stay was significantly longer (p = 0.001) in patients with SCI. The probability of survival was significantly lower in the SCI group compared with the non-SCI group (p = 0.006).
The incidence of SCI was high after fracture of the spine in patients with AS and DISH. Predictive factors for SCI after fracture were a fracture in the cervical spine and an SEH following fracture. One-fifth of the patients with SCI had delayed SCI. Patients with SCI had more complications, a longer hospital stay, and a lower probability of survival. Less than half of the patients with SCI showed neurological improvement.
Aditya V. Karhade, Paul Ogink, Quirina Thio, Marike Broekman, Thomas Cha, William B. Gormley, Stuart Hershman, Wilco C. Peul, Christopher M. Bono and Joseph H. Schwab
If not anticipated and prearranged, hospital stay can be prolonged while the patient awaits placement in a rehabilitation unit or skilled nursing facility following elective spine surgery. Preoperative prediction of the likelihood of postoperative discharge to any setting other than home (i.e., nonroutine discharge) after elective inpatient spine surgery would be helpful in terms of decreasing hospital length of stay. The purpose of this study was to use machine learning algorithms to develop an open-access web application for preoperative prediction of nonroutine discharges in surgery for elective inpatient lumbar degenerative disc disorders.
The American College of Surgeons National Surgical Quality Improvement Program was queried to identify patients who underwent elective inpatient spine surgery for lumbar disc herniation or lumbar disc degeneration between 2011 and 2016. Four machine learning algorithms were developed to predict nonroutine discharge and the best algorithm was incorporated into an open-access web application.
The rate of nonroutine discharge for 26,364 patients who underwent elective inpatient surgery for lumbar degenerative disc disorders was 9.28%. Predictive factors selected by random forest algorithms were age, sex, body mass index, fusion, level, functional status, extent and severity of comorbid disease (American Society of Anesthesiologists classification), diabetes, and preoperative hematocrit level. On evaluation in the testing set (n = 5273), the neural network had a c-statistic of 0.823, calibration slope of 0.935, calibration intercept of 0.026, and Brier score of 0.0713. On decision curve analysis, the algorithm showed greater net benefit for changing management over all threshold probabilities than changing management on the basis of the American Society of Anesthesiologists classification alone or for all patients or for no patients. The model can be found here: https://sorg-apps.shinyapps.io/discdisposition/.
Machine learning algorithms show promising results on internal validation for preoperative prediction of nonroutine discharges. If found to be externally valid, widespread use of these algorithms via the open-access web application by healthcare professionals may help preoperative risk stratification of patients undergoing elective surgery for lumbar degenerative disc disorders.