Decision tree-based machine learning analysis of intraoperative vasopressor use to optimize neurological improvement in acute spinal cord injury.

OBJECTIVE: Previous work has shown that maintaining mean arterial pressures (MAPs) between 76 and 104 mm Hg intraoperatively is associated with improved neurological function at discharge in patients with acute spinal cord injury (SCI). However, whether temporary fluctuations in MAPs outside of this range can be tolerated without impairment of recovery is unknown. This retrospective study builds on previous work by implementing machine learning to derive clinically actionable thresholds for intraoperative MAP management guided by neurological outcomes. METHODS: Seventy-four surgically treated patients were retrospectively analyzed as part of a longitudinal study assessing outcomes following SCI. Each patient underwent intraoperative hemodynamic monitoring with recordings at 5-minute intervals for a cumulative 28,594 minutes, resulting in 5718 unique data points for each parameter. The type of vasopressor used, dose, drug-related complications, average intraoperative MAP, and time spent in an extreme MAP range (< 76 mm Hg or > 104 mm Hg) were collected. Outcomes were evaluated by measuring the change in American Spinal Injury Association Impairment Scale (AIS) grade over the course of acute hospitalization. Features most predictive of an improvement in AIS grade were determined statistically by generating random forests with 10,000 iterations. Recursive partitioning was used to establish clinically intuitive thresholds for the top features. RESULTS: At discharge, a significant improvement in AIS grade was noted by an average of 0.71 levels (p = 0.002). The hemodynamic parameters most important in predicting improvement were the amount of time intraoperative MAPs were in extreme ranges and the average intraoperative MAP. Patients with average intraoperative MAPs between 80 and 96 mm Hg throughout surgery had improved AIS grades at discharge. All patients with average intraoperative MAP > 96.3 mm Hg had no improvement. A threshold of 93 minutes spent in an extreme MAP range was identified after which the chance of neurological improvement significantly declined. Finally, the use of dopamine as compared to norepinephrine was associated with higher rates of significant cardiovascular complications (50% vs 25%, p < 0.001). CONCLUSIONS: An average intraoperative MAP value between 80 and 96 mm Hg was associated with improved outcome, corroborating previous results and supporting the clinical verifiability of the model. Additionally, an accumulated time of 93 minutes or longer outside of the MAP range of 76-104 mm Hg is associated with worse neurological function at discharge among patients undergoing emergency surgical intervention for acute SCI.

Surgical site infection in spinal surgery: description of surgical and patient-based risk factors for postoperative infection using administrative claims data.

STUDY DESIGN: Retrospective analysis. OBJECTIVE: The objective of this study was to investigate the accuracy of using an automated approach to administrative claims data to assess the rate and risk factors for surgical site infection (SSI) in spinal procedures. SUMMARY OF BACKGROUND DATA: SSI is a major indicator of health care quality. A wide range of SSI rates have been proposed in the literature depending on clinical setting and procedure type. METHODS: All spinal surgeries performed at a university-affiliated tertiary-care center from July 2005 to December 2010 were identified using diagnosis-related group, current procedural terminology, and International Classification of Diseases, Ninth Revision (ICD-9) codes and were validated through chart review. Rates of SSI and associated risk factors were calculated using univariate regression analysis. Odds ratios were calculated through multivariate logistic regression. RESULTS: A total of 6628 hospital visits were identified. The cumulative incidence of SSI was 2.9%. Procedural risk factors associated with a statistically significant increase in rates of infection were the following: sacral involvement (9.6%), fusions greater than 7 levels (7.8%), fusions greater than 12 levels (10.4%), cases with an osteotomy (6.5%), operative time longer than 5 hours (5.1%), transfusions of red blood cells (5.0%), serum (7.4%), and autologous blood (4.1%). Patient-based risk factors included anemia (4.3%), diabetes mellitus (4.2%), coronary artery disease (4.7%), diagnosis of coagulopathy (7.8%), and bone or connective tissue neoplasm (5.0%). CONCLUSION: Used individually, diagnosis-related group, current procedural terminology, and ICD-9 codes cannot completely capture a patient population. Using an algorithm combining all 3 coding systems to generate both inclusion and exclusion criteria, we were able to analyze a specific population of spinal surgery patients within a high-volume medical center. Within that group, risk factors found to increase infection rates were isolated and can serve to focus hospital-wide efforts to decrease surgery-related morbidity and improve patient outcomes.