Recent reports of surgical resection of tuberculum sellae meningiomas through an endoscopic endonasal approach (EEA) have provided an alternative to transcranial approaches in selected cases. However, these published reports have been limited by small sample size from single institutions. We performed a systematic review and meta-analysis to gain insight into potential limitations and benefits of EEA for tuberculum sellae meningiomas. We performed a systematic review of the literature and analyzed pooled data for descriptive statistics on short-term morbidity and outcomes. We compared EEA to transcranial approaches reported during the same time-frame. Six studies (49 patients) met inclusion criteria for EEA. A pooled analysis of transcranial results reported during a similar time period yielded 11 studies (412 patients). There were no differences in rate of gross total resection or peri-operative complications between the two groups. Although the EEA group was associated with higher rates of CSF leak (p < 0.05; OR 3.9; 95 % CI 1.15, 15.75), EEA were also associated with significantly higher rates of post-operative visual improvement compared to transcranial approaches (p < 0.05; OR 1.5; 95 % CI 1.18, 1.82). A systematic review of the small series of EEA for tuberculum sellae meningiomas published to date revealed similar extent of resection and morbidity, but increased post-operative visual improvement compared to transcranial approaches during a similar time period. Long-term follow-up will be needed to define recurrence rates of EEA as compared to transcranial approaches. Cautious use of EEA for the removal of smaller tuberculum sellae meningiomas after formal endoscopic training may be warranted.

Rather than developing a grading system for all cerebral cavernous malformations that is weak with BSCMs, we propose a system for the patients who need it most. The BSCM grading system differentiates patients who might expect favorable surgical outcomes and offers guidance to neurosurgeons forced to select these patients.

Over the first 4 years of the program, PRIME-US students and non-PRIME students, faculty, and staff experienced educational benefits consistent with the intended program goals. Long-term evaluation is needed to examine the participants' medical careers and impacts on California's healthcare workforce and patient outcomes. Attention should also be paid to the challenges of implementing new medical education enrichment programs.

OBJECTIVEUnplanned preventable hospital readmissions within 30 days are a great burden to patients and the healthcare system. With an estimated $41.3 billion spent yearly, reducing such readmission rates is of the utmost importance. With the widespread adoption of big data and machine learning, clinicians can use these analytical tools to understand these complex relationships and find predictive factors that can be generalized to future patients. The object of this study was to assess the efficacy of a machine learning algorithm in the prediction of 30-day hospital readmission after posterior spinal fusion surgery.METHODSThe authors analyzed the distribution of National Surgical Quality Improvement Program (NSQIP) posterior lumbar fusions from 2011 to 2016 by using machine learning techniques to create a model predictive of hospital readmissions. A deep neural network was trained using 177 unique input variables. The model was trained and tested using cross-validation, in which the data were randomly partitioned into training (n = 17,448 [75%]) and testing (n = 5816 [25%]) data sets. In training, the 17,448 training cases were fed through a series of 7 layers, each with varying degrees of forward and backward communicating nodes (neurons).RESULTSMean and median positive predictive values were 78.5% and 78.0%, respectively. Mean and median negative predictive values were both 97%, respectively. Mean and median areas under the curve for the model were 0.812 and 0.810, respectively. The five most heavily weighted inputs were (in order of importance) return to the operating room, septic shock, superficial surgical site infection, sepsis, and being on a ventilator for > 48 hours.CONCLUSIONSMachine learning and artificial intelligence are powerful tools with the ability to improve understanding of predictive metrics in clinical spine surgery. The authors’ model was able to predict those patients who would not require readmission. Similarly, the majority of predicted readmissions (up to 60%) were predicted by the model while retaining a 0% false-positive rate. Such findings suggest a possible need for reevaluation of the current Hospital Readmissions Reduction Program penalties in spine surgery.