Cannabis Use Disorder Trends and Health Care Utilization After Cervical and Lumbar Spine Fusions.

STUDY DESIGN: A retrospective cohort study. OBJECTIVE: To identify differences in complication rates after cervical and lumbar fusion over the first postoperative year between those with and without cannabis use disorder (CUD) and to assess how CUD affects opioid prescription patterns. SUMMARY OF BACKGROUND DATA: Cannabis is legal for medical purposes in 36 states and for recreational use in 18 states. Cannabis has multisystem effects and may contribute to transient vasoconstrictive, prothrombotic, and inflammatory effects. METHODS: The IBM MarketScan Database (2009-2019) was used to identify patients who underwent cervical or lumbar fusions, with or without CUD. Exact match hospitalization and postdischarge outcomes were analyzed at index, six, and 12 months. RESULTS: Of 72,024 cervical fusion (2.0% with CUD) and 105,612 lumbar fusion patients (1.5% with CUD), individuals with CUD were more likely to be young males with higher Elixhauser index. The cervical CUD group had increased neurological complications (3% vs. 2%) and sepsis (1% vs. 0%) during the index hospitalization and neurological (7% vs. 5%) and wound complications (5% vs. 3%) at 12 months. The lumbar CUD group had increased wound (8% vs. 5%) and myocardial infarction (MI) (2% vs. 1%) complications at six months and at 12 months. For those with cervical myelopathy, increased risk of pulmonary complications was observed with CUD at index hospitalization and 12-month follow-up. For those with lumbar stenosis, cardiac complications and MI were associated with CUD at index hospitalization and 12 months. CUD was associated with opiate use disorder, decreasing postoperatively. CONCLUSIONS: No differences in reoperation rates were observed for CUD groups undergoing cervical or lumbar fusion. CUD was associated with an increased risk of stroke for the cervical fusion cohort and cardiac (including MI) and pulmonary complications for lumbar fusion at index hospitalization and six and 12 months postoperatively. Opiate use disorder and decreased opiate dependence after surgery also correlated with CUD.

Machine learning in clinical diagnosis, prognostication, and management of acute traumatic spinal cord injury (SCI): A systematic review.

Background: Machine learning has been applied to improve diagnosis and prognostication of acute traumatic spinal cord injury. We investigate potential for clinical integration of machine learning in this patient population to navigate variability in injury and recovery. Materials and methods: We performed a systematic review using PRISMA guidelines through PubMed database to identify studies that use machine learning algorithms for clinical application toward improvements in diagnosis, management, and predictive modeling. Results: Of the 132 records identified, a total of 13 articles met inclusion criteria and were included in final analysis. Of the 13 articles, 5 focused on diagnostic accuracy and 8 were related to prognostication or management of traumatic spinal cord injury. Across studies, 1983 patients with spinal cord injury were evaluated with most classifying as ASIA C or D. Retrospective designs were used in 10 of 13 studies and 3 were prospective. Studies focused on MRI evaluation and segmentation for diagnostic accuracy and prognostication, investigation of mean arterial pressure in acute care and intraoperative settings, prediction of ambulatory and functional ability, chronic complication prevention, and psychological quality of life assessments. Decision tree, random forests (RF), support vector machines (SVM), hierarchical cluster tree analysis (HCTA), artificial neural networks (ANN), convolutional neural networks (CNN) machine learning subtypes were used. Conclusions: Machine learning represents a platform technology with clinical application in traumatic spinal cord injury diagnosis, prognostication, management, rehabilitation, and risk prevention of chronic complications and mental illness. SVM models showed improved accuracy when compared to other ML subtypes surveyed. Inherent variability across patients with SCI offers unique opportunity for ML and personalized medicine to drive desired outcomes and assess risks in this patient population.