Search Results

You are looking at 1 - 3 of 3 items for

  • Author or Editor: Roxanna Garcia x
Clear All Modify Search
Full access

Aaron J. Clark, Roxanna M. Garcia, Malla K. Keefe, Tyler R. Koski, Michael K. Rosner, Justin S. Smith, Joseph S. Cheng, Christopher I. Shaffrey, Paul C. McCormick and Christopher P. Ames

Object

Adult spinal deformity (ASD) surgery is increasing in the spinal neurosurgeon's practice.

Methods

A survey of neurosurgeon AANS membership assessed the deformity knowledge base and impact of current training, education, and practice experience to identify opportunities for improved education. Eleven questions developed and agreed upon by experienced spinal deformity surgeons tested ASD knowledge and were subgrouped into 5 categories: 1) radiology/spinopelvic alignment, 2) health-related quality of life, 3) surgical indications, 4) operative technique, and 5) clinical evaluation. Chi-square analysis was used to compare differences based on participant demographic characteristics (years of practice, spinal surgery fellowship training, percentage of practice comprising spinal surgery).

Results

Responses were received from 1456 neurosurgeons. Of these respondents, 57% had practiced less than 10 years, 20% had completed a spine fellowship, and 32% devoted more than 75% of their practice to spine. The overall correct answer percentage was 42%. Radiology/spinal pelvic alignment questions had the lowest percentage of correct answers (38%), while clinical evaluation and surgical indications questions had the highest percentage (44%). More than 10 years in practice, completion of a spine fellowship, and more than 75% spine practice were associated with greater overall percentage correct (p < 0.001). More than 10 years in practice was significantly associated with increased percentage of correct answers in 4 of 5 categories. Spine fellowship and more than 75% spine practice were significantly associated with increased percentage correct in all categories. Interestingly, the highest error was seen in risk for postoperative coronal imbalance, with a very low rate of correct responses (15%) and not significantly improved with fellowship (18%, p = 0.08).

Conclusions

The results of this survey suggest that ASD knowledge could be improved in neurosurgery. Knowledge may be augmented with neurosurgical experience, spinal surgery fellowships, and spinal specialization. Neurosurgical education should particularly focus on radiology/spinal pelvic alignment, especially pelvic obliquity and coronal imbalance and operative techniques for ASD.

Restricted access

Benjamin S. Hopkins, Jonathan T. Yamaguchi, Roxanna Garcia, Kartik Kesavabhotla, Hannah Weiss, Wellington K. Hsu, Zachary A. Smith and Nader S. Dahdaleh

OBJECTIVE

Unplanned 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.

METHODS

The 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).

RESULTS

Mean 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.

CONCLUSIONS

Machine 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.