Search

Study Design: Retrospective cohort.Objective: Due to anterior cervical discectomy and fusion (ACDF) popularity, it is important to predict postoperative complications, unfavorable 90-day readmissions, and two-year reoperations to improve surgical decision-making, prognostication, and planning.Summary Of Background Data: Machine learning has been applied to predict postoperative complications for ACDF; however, studies were limited by sample size and model type. These studies achieved ≤0.70 area under the curve (AUC). Further approaches, not limited to ACDF, focused on specific complication types and resulted in AUC between 0.70 and 0.76.Materials and Methods: The IBM MarketScan Commercial Claims and Encounters Database and Medicare Supplement were queried from 2007 to 2016 to identify adult patients who underwent an ACDF procedure (N=176,816). Traditional machine learning algorithms, logistic regression, and support vector machines, were compared with deep neural networks to predict: 90-day postoperative complications, 90-day readmission, and two-year reoperation. We further generated random deep learning model architectures and trained them on the 90-day complication task to approximate an upper bound. Last, using deep learning, we investigated the importance of each input variable for the prediction of 90-day postoperative complications in ACDF.Results: For the prediction of 90-day complication, 90-day readmission, and two-year reoperation, the deep neural network-based models achieved AUC of 0.832, 0.713, and 0.671. Logistic regression achieved AUCs of 0.820, 0.712, and 0.671. Support vector machine approaches were significantly lower. The upper bound of deep learning performance was approximated as 0.832. Myelopathy, age, human immunodeficiency virus, previous myocardial infarctions, obesity, and documentary weakness were found to be the strongest variable to predict 90-day postoperative complications.Conclusions: The deep neural network may be used to predict complications for clinical applications after multicenter validation. The results suggest limited added knowledge exists in interactions between the input variables used for this task. Future work should identify novel variables to increase predictive power. [ABSTRACT FROM AUTHOR]

Study Design: Retrospective cohort studying using a national, administrative database.Objective: The aim of this study was to determine the postoperative complications and quality outcomes of patients with and without obesity undergoing surgical management for lumbar degenerative disease (LDD).Summary Of Background Data: Obesity is a global epidemic that negatively impacts health outcomes. Characterizing the effect of obesity on LDD surgery is important given the growing elderly obese population.Methods: This study identified patients with who underwent surgery for LDD between 2007 and 2016. Patients were stratified based on whether the patient had a concurrent diagnosis of obesity at time of surgery. Propensity score matching (PSM) was then utilized to mitigate intergroup differences between patients with and without obesity. Patients who underwent three or more levels surgical correction, were under the age of 18 years, or those with any previous history of trauma or tumor were excluded from this study. Baseline comorbidities, postoperative complication rates, and reoperation rates were determined.Results: A total of 67,215 patients underwent primary lumbar degenerative surgery, of which 22,405 (33%) were obese. After propensity score matching, baseline covariates of the two cohorts were similar. The complication rate was 8.3% in the nonobese cohort and 10.4% in the obese cohort (P < 0.0001). Patients with obesity also had longer lengths of stay (2.7 days vs. 2.4 days, P < 0.05), and higher rates of reoperation and readmission at all time-points through the study follow-up period to their nonobese counterparts (P < 0.05). Including payments after discharge, lumbar degenerative surgery in patients with obesity was associated with higher payments throughout the 2-year follow-up period ($68,061 vs. $59,068 P < 0.05).Conclusion: Patients with a diagnosis of obesity at time of LDD surgery are at a higher risk for postoperative complications, reoperation, and readmission.Level of Evidence: 4. [ABSTRACT FROM AUTHOR]

Study Design: Retrospective longitudinal cohort.Objective: We investigated opioid prescribing patterns amongst adults in the United States diagnosed with low back or lower extremity pain (LBP/LEP) who underwent spine surgery.Summary Of Background Data: Opioid-based treatment of LBP/LEP and postsurgical pain has separately been associated with chronic opioid use, but a combined and large-scale cohort study is missing.Methods: This study utilizes commercial inpatient, outpatient, and pharmaceutical insurance claims. Between 2008 and 2015, patients without previous prescription opioids with a new diagnosis of LBP/LEP who underwent surgery within 1 year after diagnosis were enrolled. Opioid prescribing patterns after LBP/LEP diagnosis and after surgery were evaluated. All patients had 1-year postoperative follow-up. Low and high frequency (6 or more refills in 12 months) opioid prescription groups were identified.Results: A total of 25,506 patients without previous prescription opioids were diagnosed with LBP/LEP and underwent surgery within 1 year of diagnosis. After LBP/LEP diagnosis, 18,219 (71.4%) were prescribed opioids, whereas 7287 (28.6%) were not. After surgery, 2952 (11.6%) were prescribed opioids with high frequency and 22,554 (88.4%) with low frequency. Among patients prescribed opioids before surgery, those with high-frequency prescriptions were more likely to continue this pattern postoperatively than those with low frequency prescriptions preoperatively (OR 2.15, 95% CI 1.97-2.34). For those prescribed opioids preoperatively, average daily morphine milligram equivalent (MME) decreased after surgery (by 2.62 in decompression alone cohort and 0.25 in arthrodesis cohort, P < 0.001). Postoperative low-frequency patients were more likely than high-frequency patients to discontinue opioids one-year after surgery (OR 3.78, 95% CI 3.59-3.99). Postoperative high-frequency patients incurred higher cost than low-frequency patients. Postoperative high-frequency prescribing varied widely across states (4.3%-20%).Conclusion: A stepwise association exists between opioid use after LEP or LBP diagnosis and frequency and duration of opioid prescriptions after surgery. Simultaneously, the strength of prescriptions as measured by MME decreased following surgery.Level Of Evidence: 3. [ABSTRACT FROM AUTHOR]

Study Design: An epidemiological study using national administrative data from the MarketScan database.Objective: The aim of this study was to identify the impact of bone morphogenetic protein (BMP) on postoperative outcomes in patients undergoing adult cervical deformity (ACD) surgery.Summary Of Background Data: BMP has been shown to stimulate bone growth and improve fusion rates in spine surgery. However, the impact of BMP on reoperation rates and postoperative complication rate is controversial.Methods: We queried the MarketScan database to identify patients who underwent ACD surgery from 2007 to 2015. Patients were stratified by BMP use in the index operation. Patients <18 years and those with any history of tumor or trauma were excluded. Baseline demographics and comorbidities, postoperative complication rates, and reoperation rates were analyzed.Results: A total of 13,549 patients underwent primary ACD surgery, of which 1155 (8.5%) had intraoperative BMP use. The overall 90-day complication rate was 27.6% in the non-BMP cohort and 31.1% in the BMP cohort (P < 0.05). Patients in the BMP cohort had longer average length of stay (4.0 days vs. 3.7 days, P < 0.05) but lower revision surgery rates at 90 days (14.5% vs. 28.3%, P < 0.05), 6 months (14.9% vs. 28.6%, P < 0.05), 1 year (15.7% vs. 29.2%, P < 0.05), and 2 years (16.5% vs. 29.9%, P < 0.05) postoperatively. BMP use was associated with higher payments throughout the 2-year follow-up period ($107,975 vs. $97,620, P < 0.05). When controlling for baseline group differences, BMP use independently increased the odds of postoperative complication (odds ratio [OR] 1.22, 95% confidence interval [CI] 1.1-1.4) and reduced the odds of reoperation throughout 2 years of follow-up (OR 0.49, 95% CI 0.4-0.6).Conclusion: Intraoperative BMP use has benefits for fusion integrity in ACD surgery but is associated with increased postoperative complication rate. Spine surgeons should weigh these benefits and drawbacks to identify optimal candidates for BMP use in ACD surgery.Level Of Evidence: 3. [ABSTRACT FROM AUTHOR]

Study Design: This was a retrospective study using national administrative data from the MarketScan database.Objective: To investigate the complication rates, quality outcomes, and costs in a nationwide cohort of patients with movement disorders (MD) who undergo spinal deformity surgery.Summary Of Background Data: Patients with MD often present with spinal deformities, but their tolerance for surgical intervention is unknown.Methods: The MarketScan administrative claims database was queried to identify adult patients with MD who underwent spinal deformity surgery. A propensity-score match was conducted to create two uniform cohorts and mitigate interpopulation confounders. Perioperative complication rates, 90-day postoperative outcomes, and total costs were compared between patients with MD and controls.Results: A total of 316 patients with MD (1.7%) were identified from the 18,970 undergoing spinal deformity surgery. The complication rate for MD patients was 44.6% and for the controls 35.6% (P = 0.009). The two most common perioperative complications were more likely to occur in MD patients, acute-posthemorrhagic anemia (26.9% vs. 20.8%, P < 0.05) and deficiency anemia (15.5% vs. 8.5%, P < 0.05). At 90 days, MD patients were more likely to be readmitted (17.4% vs. 13.2%, P < 0.05) and have a higher total cost ($94,672 vs. $85,190, P < 0.05). After propensity-score match, the overall complication rate remained higher in the MD group (44.6% vs. 37.6%, P < 0.05). 90-day readmissions and costs also remained significantly higher in the MD cohort. Multivariate modeling revealed MD was an independent predictor of postoperative complication and inpatient readmission. Subgroup analysis revealed that Parkinson disease was an independent predictor of inpatient readmission, reoperation, and increased length of stay.Conclusion: Patients with MD who undergo spinal deformity surgery may be at risk of higher rate of perioperative complications and 90-day readmissions compared with patients without these disorders.Level Of Evidence: 3. [ABSTRACT FROM AUTHOR]