OBJECTIVE: Glioblastoma (GBM) and primary central nervous system lymphoma (PCNSL) are common intracranial pathologies encountered by neurosurgeons. They often may have similar radiological findings, making diagnosis difficult without surgical biopsy; however, management is quite different between these two entities. Recently, predictive analytics, including machine learning (ML), have garnered attention for their potential to aid in the diagnostic assessment of a variety of pathologies. Several ML algorithms have recently been designed to differentiate GBM from PCNSL radiologically with a high sensitivity and specificity. The objective of this systematic review and meta-analysis was to evaluate the implementation of ML algorithms in differentiating GBM and PCNSL. METHODS: The authors performed a systematic review of the literature using PubMed in accordance with PRISMA guidelines to select and evaluate studies that included themes of ML and brain tumors. These studies were further narrowed down to focus on works published between January 2008 and May 2018 addressing the use of ML in training models to distinguish between GBM and PCNSL on radiological imaging. Outcomes assessed were test characteristics such as accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). RESULTS: Eight studies were identified addressing use of ML in training classifiers to distinguish between GBM and PCNSL on radiological imaging. ML performed well with the lowest reported AUC being 0.878. In studies in which ML was directly compared with radiologists, ML performed better than or as well as the radiologists. However, when ML was applied to an external data set, it performed more poorly. CONCLUSIONS: Few studies have applied ML to solve the problem of differentiating GBM from PCNSL using imaging alone. Of the currently published studies, ML algorithms have demonstrated promising results and certainly have the potential to aid radiologists with difficult cases, which could expedite the neurosurgical decision-making process. It is likely that ML algorithms will help to optimize neurosurgical patient outcomes as well as the cost-effectiveness of neurosurgical care if the problem of overfitting can be overcome.

Background: Few studies have investigated opioid utilization by geriatric patients after spinal surgery, a population in whom degenerative spine disease (DSD) is highly prevalent. We aimed to quantify rates of chronic, continuous opioid utilization by geriatric patients following spine surgery for DSD-related diagnoses. Materials and Methods: Utilizing a national 5% Medicare sample database, we investigated individuals aged above 66 years who underwent spinal surgery for a DSD-related diagnosis between the years of 2008 and 2014. The outcomes of interest were the rate of and risk factors for continuous opioid utilization at 1-year following anterior cervical discectomy and fusion, posterior cervical fusion, 360-degree cervical fusion, lumbar microdiscectomy, lumbar laminectomy, posterior lumbar fusion, anterior lumbar fusion, or 360-degree lumbar fusion for a DSD-related diagnosis. Results: Of the 14,583 Medicare enrollees who met study criteria, 6.0% continuously utilized opioids 1-year after spinal surgery. When stratified by preoperative opioid utilization (with the prior year divided into 4 quarters), the rates of continuous utilization at 1-year postsurgery were 0.3% of opioid-naive patients and 23.6% of patients with opioid use in all 4 quarters before surgery. Anxiety, benzodiazepine use within the year before surgery, and Medicaid dual-eligibility were associated with prolonged opioid utilization. Conclusions: Of opioid-naive geriatric patients who underwent surgery for DSD, 0.3% developed chronic, continuous opioid use. Preoperative opioid use was the strongest predictor of prolonged utilization, which may represent suboptimal use of nonopioid alternatives, pre-existing opioid use disorders, delayed referral for surgical evaluation, or over-prescription of opioids for noncancer pain.