Critically reading machine learning literature in neurosurgery: a reader's guide and checklist for appraising prediction models.

OBJECTIVE: Machine learning (ML) has become an increasingly popular tool for use in neurosurgical research. The number of publications and interest in the field have recently seen significant expansion in both quantity and complexity. However, this also places a commensurate burden on the general neurosurgical readership to appraise this literature and decide if these algorithms can be effectively translated into practice. To this end, the authors sought to review the burgeoning neurosurgical ML literature and to develop a checklist to help readers critically review and digest this work. METHODS: The authors performed a literature search of recent ML papers in the PubMed database with the terms "neurosurgery" AND "machine learning," with additional modifiers "trauma," "cancer," "pediatric," and "spine" also used to ensure a diverse selection of relevant papers within the field. Papers were reviewed for their ML methodology, including the formulation of the clinical problem, data acquisition, data preprocessing, model development, model validation, model performance, and model deployment. RESULTS: The resulting checklist consists of 14 key questions for critically appraising ML models and development techniques; these are organized according to their timing along the standard ML workflow. In addition, the authors provide an overview of the ML development process, as well as a review of key terms, models, and concepts referenced in the literature. CONCLUSIONS: ML is poised to become an increasingly important part of neurosurgical research and clinical care. The authors hope that dissemination of education on ML techniques will help neurosurgeons to critically review new research better and more effectively integrate this technology into their practices.

Traumatic Spinal Cord Disorders: Current Topics and Future Directions.

Traumatic spinal cord injury (tSCI) is a life-changing and potentially overwhelming event. The sudden disruption of the spinal cord's integrity necessitates rapid attention at a specialized medical center, and involves a multilateral collaboration between neurologists, spine surgeons, critical care physicians, and trauma specialists. Even with care under ideal conditions, many tSCI patients have significant disability that persists for the rest of their lives. However, recently, we have seen a proliferation in clinical and translational trials that offer the promise that new treatments may be available soon.

Focused ultrasound in neurosurgery: a historical perspective.

Focused ultrasound (FUS) has been under investigation for neurosurgical applications since the 1940s. Early experiments demonstrated ultrasound as an effective tool for the creation of intracranial lesions; however, they were limited by the need for craniotomy to avoid trajectory damage and wave distortion by the skull, and they also lacked effective techniques for monitoring. Since then, the development and hemispheric distribution of phased arrays has resolved the issue of the skull and allowed for a completely transcranial procedure. Similarly, advances in MR technology have allowed for the real-time guidance of FUS procedures using MR thermometry. MR-guided FUS (MRgFUS) has primarily been investigated for its thermal lesioning capabilities and was recently approved for use in essential tremor. In this capacity, the use of MRgFUS is being investigated for other ablative indications in functional neurosurgery and neurooncology. Other applications of MRgFUS that are under active investigation include opening of the blood-brain barrier to facilitate delivery of therapeutic agents, neuromodulation, and thrombolysis. These recent advances suggest a promising future for MRgFUS as a viable and noninvasive neurosurgical tool, with strong potential for yet-unrealized applications.

The Neurocritical and Neurosurgical Care of Subdural Hematomas.

Subdural hematomas (SDHs), though frequently grouped together, can result from a variety of different etiologies, and therefore many different subtypes exist. Moreover, the high incidence of these lesions in the neurocritical care settings behooves practitioners to have a firm grasp on their diagnosis and management. We present here a review of SDHs, with an emphasis on how different subtypes of SDHs differ from one another and with discussion of their medical and surgical management in the neurocritical care setting. In this paper, we discuss considerations for acute, subacute, and chronic SDHs and how presentation and management may change in both the elderly and pediatric populations. We discuss SDHs that arise in the setting of anticoagulation, those that arise in the setting of active cerebrospinal fluid diversion, and those that are recurrent and recalcitrant to initial surgical evacuation. Management steps reviewed include detailed discussion of initial assessment, anticoagulation reversal, seizure prophylaxis, blood pressure management, and indications for intracranial pressure monitoring. Direct surgical management options are reviewed, including open craniotomy, twist-drill, and burr-hole drainage and the usage of subdural drainage systems. SDHs are a common finding in the neurocritical care setting and have a diverse set of presentations. With a better understanding of the fundamental differences between subtypes of SDHs, critical care practitioners can better tailor their management of both the patient's intracranial and multi-systemic pathologies.

Intrasellar abscess following pituitary surgery.

PURPOSE: Intrasellar abscess is an uncommon cause of mass lesions in the sella turcica. Few cases have been reported in the literature, and much remains unknown about the etiology and diagnosis of these lesions. We sought to review a series of patients with intrasellar abscess encountered at our institution and identify defining characteristics of their presentation and management. METHODS: We conducted a retrospective chart review for intrasellar infection cases associated with a mass lesion. Included cases had clear demonstration of a mass lesion on imaging with subsequent positive microbiological cultures. Clinical presentation, management, post-operative course, neuroimaging, microbiology, and any perturbations in serum pituitary biochemical markers were examined. RESULTS: All examined patients had a history of antecedent transsphenoidal pituitary surgery within the preceding 10 months. All presented with headaches, three with progressive visual loss, one with meningismus, one with fever in the setting of an active cerebrospinal fluid leak, and one with fever, meningismus, hypotension, and progressive somnolence. No patient presented with acute endocrine abnormalities. A majority did not initially have any diffusion restriction present on MRI, but in one case we were able to track the evolution of diffusion restriction over sequential MRI scans. Two patients had complete resolution of presenting symptoms, while three experienced improvement or stabilization of their neurologic deficit. There were no mortalities. CONCLUSIONS: Pituitary abscess remains a rare diagnosis that can be difficult to make and to confirm. In our series we found a strong association between culture-positive abscess and recent pituitary surgery. When present, prompt treatment with surgical drainage and aggressive post-operative antibiotics can lead to a favorable outcome.

Complications after transsphenoidal surgery for patients with Cushing's disease and silent corticotroph adenomas.

OBJECT The purpose of this study was to describe complications associated with the endonasal, transsphenoidal approach for the treatment of adrenocorticotropic hormone (ACTH)-positive staining tumors (Cushing's disease [CD] and silent corticotroph adenomas [SCAs]) performed by 1 surgeon at a high-volume academic medical center. METHODS Medical records from Brigham and Women's Hospital were retrospectively reviewed. Selected for study were 82 patients with CD who during April 2008-April 2014 had consecutively undergone transsphenoidal resection or who had subsequent pathological confirmation of ACTH-positive tumor staining. In addition to demographic, patient, tumor, and surgery characteristics, complications were evaluated. Complications of interest included syndrome of inappropriate antidiuretic hormone secretion, diabetes insipidus (DI), CSF leakage, carotid artery injury, epistaxis, meningitis, and vision changes. RESULTS Of the 82 patients, 68 (82.9%) had CD and 14 (17.1%) had SCAs; 55 patients were female and 27 were male. Most common (n = 62 patients, 82.7%) were microadenomas, followed by macroadenomas (n = 13, 14.7%). A total of 31 (37.8%) patients underwent reoperation. Median follow-up time was 12.0 months (range 3-69 months). The most common diagnosis was ACTH-secreting (n = 68, 82.9%), followed by silent tumors/adenomas (n = 14, 17.1%). ACTH hyperplasia was found in 8 patients (9.8%). Of the 74 patients who had verified tumors, 12 (16.2%) had tumors with atypical features. The overall (CD and SCA) rate of minor complications was 35.4%; the rate of major complications was 8.5% (n = 7). All permanent morbidity was associated with DI (n = 5, 6.1%). In 16 CD patients (23.5%), transient DI developed. Transient DI was more likely to develop in CD patients who had undergone a second operation (37.9%) than in those who had undergone a first operation only (12.8%, p < 0.05). Permanent DI developed in 4 CD patients (5.9%) and 1 SCA patient (7.1%). For 1 CD patient, intraoperative carotid artery injury required endovascular sacrifice of the injured artery, but the patient remained neurologically intact. For another CD patient, aseptic meningitis developed and was treated effectively with corticosteroids. One CD patient experienced major postoperative epistaxis requiring another operative procedure to achieve hemostasis. For 2 CD patients, development of sinus mucoceles was managed conservatively. For 1 SCA patient, an abdominal wound dehisced at the fat graft site. No patients experienced postoperative CSF leakage, visual impairment, or deep vein thrombosis. CONCLUSIONS Transsphenoidal surgery is the treatment of choice for patients with CD and other ACTH-positive staining tumors. Recent advances in endoscopic technology and increasing surgeon comfort with this technology are making transsphenoidal procedures safer, faster, and more effective. Serious complications are uncommon and can be managed successfully.

A national survey of spinal cord stimulation trial-to-permanent conversion rates.

OBJECTIVES: Conversion rates from trial leads to permanent spinal cord stimulation (SCS) systems have recently come under scrutiny. Our goal was to examine the rate of conversion from trial lead to permanent system placement as well as identify factors associated with successful SCS conversion. MATERIALS AND METHODS: We designed a large retrospective analysis using the Thomson Reuters MarketScan database. We included all patients who underwent a percutaneous trial of neurostimulatory electrodes from the years 2000 to 2009 who were aged 18 and older. Patients were then tracked to see if they went on to receive a permanent SCS system. Patients were also analyzed in univariate and multivariate models to identify factors associated with successful conversion. RESULTS: A total of 21,672 unique instances of percutaneous trials were identified. Overall, 41.4% of those receiving trials went on to have a permanent SCS system installed within the subsequent three months. Factors associated with increased likelihood of successful conversion included having commercial insurance (43% vs. 37%, p < 0.0001), younger age (43% for those aged 35-44 vs. 39% for those aged 65 and older, p < 0.0001), and never having had a previous percutaneous trial attempt (44% for first-time trials vs. 27% for those on their second trial vs. 14% for those on their third or later trial, p < 0.0001). In multivariate analysis, we found significant variation in conversion rate by geographic area (patients in the North Central region vs. Northeast region: odds ratio 1.48, 95% confidence interval [1.31, 1.66]; p < 0.0001). CONCLUSIONS: In this study of a national cohort of patients, we identified specific factors associated with higher conversion rates, along with significant geographical variation. In general, there is a need for better patient selection by physicians who practice neuromodulation.

Evaluation of the safety, accuracy, and helpfulness of the GPT-4.0 Large Language Model in neurosurgery.

BACKGROUND: Although prior work demonstrated the surprising accuracy of Large Language Models (LLMs) on neurosurgery board-style questions, their use in day-to-day clinical situations warrants further investigation. This study assessed GPT-4.0's responses to common clinical questions across various subspecialties of neurosurgery. METHODS: A panel of attending neurosurgeons formulated 35 general neurosurgical questions spanning neuro-oncology, spine, vascular, functional, pediatrics, and trauma. All questions were input into GPT-4.0 with a prespecified, standard prompt. Responses were evaluated by two attending neurosurgeons, each on a standardized scale for accuracy, safety, and helpfulness. Citations were indexed and evaluated against identifiable database references. RESULTS: GPT-4.0 responses were consistent with current medical guidelines and accounted for recent advances in the field 92.8 % and 78.6 % of the time respectively. Neurosurgeons reported GPT-4.0 responses providing unrealistic information or potentially risky information 14.3 % and 7.1 % of the time respectively. Assessed on 5-point scales, responses suggested that GPT-4.0 was clinically useful (4.0 ± 0.6), relevant (4.7 ± 0.3), and coherent (4.9 ± 0.2). The depth of clinical responses varied (3.7 ± 0.6), and "red flag" symptoms were missed 7.1 % of the time. Moreover, GPT-4.0 cited 86 references (2.46 citations per answer), of which only 50 % were deemed valid, and 77.1 % of responses contained at least one inappropriate citation. CONCLUSION: Current general LLM technology can offer generally accurate, safe, and helpful neurosurgical information, but may not fully evaluate medical literature or recent field advances. Citation generation and usage remains unreliable. As this technology becomes more ubiquitous, clinicians will need to exercise caution when dealing with it in practice.

Automated ventricular segmentation and shunt failure detection using convolutional neural networks.

While ventricular shunts are the main treatment for adult hydrocephalus, shunt malfunction remains a common problem that can be challenging to diagnose. Computer vision-derived algorithms present a potential solution. We designed a feasibility study to see if such an algorithm could automatically predict ventriculomegaly indicative of shunt failure in a real-life adult hydrocephalus population. We retrospectively identified a consecutive series of adult shunted hydrocephalus patients over an eight-year period. Associated computed tomography scans were extracted and each scan was reviewed by two investigators. A machine learning algorithm was trained to identify the lateral and third ventricles, and then applied to test scans. Results were compared to human performance using Sørensen-Dice coefficients, calculated total ventricular volumes, and ventriculomegaly as documented in the electronic medical record. 5610 axial images from 191 patients were included for final analysis, with 52 segments (13.6% of total data) reserved for testing. Algorithmic performance on the test group averaged a Dice score of 0.809 ± 0.094. Calculated total ventricular volumes did not differ significantly between computer-derived volumes and volumes marked by either the first reviewer or second reviewer (p > 0.05). Algorithm detection of ventriculomegaly was correct in all test cases and this correlated with correct prediction of need for shunt revision in 92.3% of test cases. Though development challenges remain, it is feasible to create automated algorithms that detect ventriculomegaly in adult hydrocephalus shunt malfunction with high reliability and accuracy.

Using Resource Utilization in Spine Healthcare to Complement Patient-Reported Outcome Measurements in Assessing Surgical Success.

OBJECTIVE: Patient-reported outcome measures (PROMs) are utilized to assess surgical success but are limited by data collection, response bias, and subjectivity. The large volume of digital healthcare data offers a new method to utilize healthcare utilization as a longitudinal, individualized, and objective proxy for health needs among surgical patients. This study aimed to design and evaluate a novel resource utilization in spine healthcare (RUSH) clustering method that complements PROMs in evaluating post-operative patient outcomes. METHODS: This retrospective cross-sectional study conducted at a large, tertiary healthcare system included all adult patients undergoing cervical or lumbar surgery between 2014 to 2020 with at least 3 months follow-up. Post-operative healthcare utilization was analyzed using clinic visits, inpatient encounters, telephone encounters, MyChart messages, opioid use, physical therapy, injections, and imaging. Latent profile analysis determined RUSH clusters and changes in PROM Information System Physical Health (PROMIS-PH) scores pre- and 12-months post-operation. RESULTS: This study included 5,602 surgeries (mean age 61.3 ± 13.1, 49.9% female). Four RUSH groups were identified: low utilizers (21.5%), moderate utilizers without advanced imaging (34.7%), moderate utilizers with advanced imaging (10.7%), and high utilizers (33.1%,). Utilization patterns varied by surgery type, with lower-utilization patterns among non-fusion procedures and a consistent sub-population of high utilizers across all surgery types. High RUSH utilizers had the lowest pre-operative PROMIS-PH scores and the worst average postoperative change. CONCLUSIONS: RUSH clustering provides a novel, data-driven approach to measure surgical success, complementing traditional PROMs, and leveraging big data to monitor and respond to surgical outcomes.

Outcomes of percutaneous and paddle lead implantation for spinal cord stimulation: a comparative analysis of complications, reoperation rates, and health-care costs.

OBJECTIVES: Spinal cord stimulation (SCS) is a well-established modality for the treatment of chronic pain, and can utilize percutaneous or paddle leads. While percutaneous leads are less invasive, they have been shown to have higher lead migration rates. In this study, we compared the long-term outcomes and health-care costs associated with paddle and percutaneous lead implantation. MATERIALS AND METHODS: We utilized the MarketScan data base to examine patients who underwent percutaneous or paddle lead SCS system implantation from 2000 to 2009. Outcomes including complications, reoperation rates, and health-care costs were evaluated in propensity score matched cohorts using univariate and multivariate analyses. RESULTS: The study cohort was comprised of 13,774 patients. At 90 days following the initial procedure, patients in the SCS paddle group were more likely to develop a postoperative complication than patients receiving percutaneous systems (3.4% vs. 2.2%, p = 0.0005). Two-year (6.3% vs. 3.5%, p = 0.0056) and long-term (five+ years) (22.9% vs. 8.5%, p < 0.0008) reoperation rates were significantly higher in those with percutaneous lead systems. However, long-term health-care costs were similar for those receiving paddle and percutaneous leads ($169,768 vs. $186,139, p = 0.30). CONCLUSIONS: While the implantation of paddle leads is associated with slightly higher initial postoperative complications, these leads are associated with significantly lower long-term reoperation rates. Nonetheless, long-term health-care costs are similar between paddle and percutaneous leads. Additional improvements in SCS technologies that address the shortcomings of current systems are needed to reduce the risk of reoperation due to hardware failure. Further study is required to evaluate the efficacy of newer percutaneous and paddle SCS systems and examine their comparative outcomes.

Insurance disparities in the outcomes of spinal cord stimulation surgery.

OBJECTIVES: The Affordable Care Act aims to expand health insurance and to help narrow existing health care disparities. Medicaid patients have previously been noted to be at an increased risk for impaired access to health care, delayed medical treatment, and the receipt of substandard care. Conversely, those with commercial insurance may be subject to overtreatment. The goal of this study was to evaluate how Medicaid versus commercial insurance status affects outcomes following spinal cord stimulation (SCS) surgery. MATERIALS AND METHODS: A retrospective cohort study of 13,774 patients underwent either percutaneous or paddle permanent SCS implantation, selected from the Thomson Reuter's MarketScan database between 2000 and 2009. Patients were characterized by age at initial procedure, gender, baseline comorbidity burden, procedure-associated diagnosis code, follow-up, and type of insurance (Medicaid vs. commercial insurance). Outcome measures included probability of reoperation, timing and type of reoperation, presence of postoperative complications (immediate, 30 days, and 90 days), and overall utilization of health resources postoperatively. Multivariate analysis was performed comparing the relative effect of insurance status on outcomes following initial surgery. RESULTS: Medicaid patients had greater healthcare resource utilization as measured by medications prescribed, emergency department visits, and length of stay; however, commercially insured patients had significantly higher overall costs ($110,908 vs. $64,644, p < 0.0001). Commercial and Medicaid patients did not significantly differ in their complication rates during the index hospitalization or at 30 days or 90 days postoperatively. The group were also not significantly different in their two-year reoperation rates (7.32% vs. 5.06%, p = 0.0513). CONCLUSIONS: There are substantial insurance disparities that affect healthcare utilization and overall cost following SCS. Efforts for national healthcare reform should examine system factors that will reduce socioeconomic disparities in outcomes following SCS.

Fractal analysis of healthy and diseased vasculature in pediatric Moyamoya disease.

BACKGROUND AND PURPOSE: Fractal dimension is an objective metric for the notion of structural complexity. We sought to investigate differences in structural complexity between healthy and affected territories of cerebral vasculature in moyamoya, as well as associated scalp vasculature and native transdural collaterals in patients with moyamoya by comparing their respective fractal dimensions. METHODS: Our cohort consisted of 15 transdural collaterals from 12 patients with unilateral anterior circulation moyamoya. Frames of distal arterial vasculature from internal and external carotid angiograms were selected then automatically segmented and also manually annotated by a cerebrovascular surgeon. In the affected hemisphere, the region with transdural collateral supply was compared to the contralateral region. The resulting skeletonized angiograms were analyzed for their fractal dimensions. RESULTS: We found the average fractal dimension (Df) of the moyamoya-side ICA was 1.82 with slightly different means for the anteroposterial (AP) and lateral views (mean = 1.82; mean = 1.81). The overall mean for healthy cerebral vasculature was also found to be 1.82 (AP: mean = 1.83; lateral: mean = 1.81). Mean Df of native transdural collaterals was found to be 1.82 (AP: mean = 1.83; lateral: mean = 1.81). The mean Df difference between autosegmented and manually segmented images was 0.013. CONCLUSION: In accordance with the clinical understanding of moyamoya disease, the distal arterial structural complexity is not affected in moyamoya, and is maintained by transdural collaterals formed by vasculogenesis. Autosegmentation of cerebral vasculature is also shown to be accurate when compared to manual segmentation.

One Year Outcomes From a Prospective Multicenter Investigation Device Trial of a Novel Conformal Mesh Interbody Fusion Device.

STUDY DESIGN: A prospective multicenter investigational device exempt trial is underway evaluating a novel conformable mesh interbody fusion device in subjects undergoing single-level fusion for degenerative disc disease. Patients meeting inclusion and exclusion criteria were offered enrollment. There is no comparative group in this study. OBJECTIVE: Establish the short and long-term safety and effectiveness of a novel conformable mesh interbody fusion device in subjects undergoing single-level fusion for degenerative disc disease unresponsive to conservative care. SUMMARY OF BACKGROUND DATA: Transforaminal lumbar interbody fusion remains a critical procedure for patients with degenerative lumbar disc disease. Increasingly minimally invasive techniques have been proposed to minimize muscle dissection and tissue damage with the goal of minimizing pain and length of stay. METHODS: One hundred two subjects were enrolled across 10 sites. Ninety nine subjects remained available for follow-up at 12-months. Physical evaluations/imaging were performed serially through 12-months. Validated assessment tools included 100 mm visual analogue scale (VAS) for pain, Oswestry Disability Index (ODI) for function, and computerized tomography scan for fusion. Independent committees were used to identify adverse events and for assessment of radiographic fusion. RESULTS: Reductions in low back pain (LBP)/leg pain and improvements in functional status occur early and are maintained through 12-month follow-up. Mean VAS-LBP change from baseline to 6-weeks post-op (-46 mm) continued to improve through 12 months (-51 mm). Similar trends were observed for leg pain. Mean ODI change from baseline to 6 weeks post-op (-17) was almost doubled by 12 months (-32). Fusion rates at 12-months are high (98%). No device-related serious adverse events have occurred. CONCLUSION: 12-month outcomes demonstrated excellent patient compliance and positive outcomes for pain, function, fusion, and device safety. Clinical improvements were observed by 6-weeks post-op and appear durable up to 1 year later. A novel mesh interbody device may provide an alternative means of interbody fusion that reduces connective tissue disruption.Level of Evidence: 3.

Two-Year Outcomes From a Prospective Multicenter Investigation Device Trial of a Novel Conformal Mesh Interbody Fusion Device.

BACKGROUND: Interbody fusion is a widely utilized and accepted procedure to treat advanced debilitating lumbar degenerative disc disease (DDD). Increasingly, surgeons are seeking interbody devices that are large for stability and grafting purposes but can be inserted with less invasive techniques. To achieve these contrary objectives a novel, conformable mesh interbody fusion device was designed to be placed in the disc space through a small portal and filled with bone graft in situ to a large size. This design can reduce the risk of trauma to surrounding structures while creating a large graft footprint that intimately contours to the patient's own anatomy. The purpose of this Investigational Device Exempt (IDE) trial was to evaluate the perioperative and long-term results of this novel conformable mesh interbody fusion device. METHODS: This investigation is a prospective, multicenter, single-arm, Food and Drug Administration and Institutional Review Board-approved IDE, performance goal trial. A total of 102 adults presenting with DDD at a single level between L2 and S1 and unresponsive to 6 months conservative care had instrumented lumbar interbody fusion. Validated assessment tools include 100 mm visual analog scale for pain, Oswestry Disability Index (ODI) for function, single question survey for patient satisfaction, and computed tomography (CT) scan for fusion. Patients were enrolled across 10 geographically distributed sites. Pain/ODI surveys, physical evaluations, and imaging were performed serially through 24 months. Specifically, CT was performed at 12 and, if not fused, 24 months. Independent radiologists assessed CTs for fusion. An independent committee adjudicated adverse events. Patients with complete data at 24 months were included in the analysis. RESULTS: Ninety-six (96, 94% follow-up rate) patients (57.0 ± 12.0 years, 50.0% female, Body Mass Index 30.6 ± 4.9) reported average decreased low back pain from baseline of 45.0 ± 26.6 at 6 weeks and 51.4 ± 26.2 at 24 months. Right/left leg pain reduced by 28.9 ± 36.7/37.8±32.4 at 6 weeks and 30.5±33.0/40.3 34.6 at 24 months. Mean ODI improved 17.1 ± 18.7 from baseline to 6 weeks and 32.0 ± 18.5 by 24 months. At 24 months, 91.7% of patients rated their procedure as excellent/good. Fusion rates were 97.9% (94/96) at 12 months, and 99% (95/96) at 24 months. Mean operative time, estimated blood loss, and length of stay were 2.6 ± 0.9 hours, 137 ± 217 mL, and 2.3 ± 1.2 days, respectively. No device-related serious adverse events have occurred. CONCLUSIONS: Clinically significant outcomes for pain, function, fusion, and device safety were demonstrated in this population. Substantial clinical improvements occur by 6 weeks postoperative and continue to improve to 24 months. The successful outcomes observed in this trial support use of this novel device in an instrumented lumbar interbody fusion. LEVEL OF EVIDENCE: 3. CLINICAL RELEVANCE: This reports substantiates that the preliminary 1-year findings published earlier for this investigation are confirmed and the fusion rates and that patient improvements reported are sustained through 2 years.

Subdural Pneumocephalus Aspiration Reduces Recurrence of Chronic Subdural Hematoma.

BACKGROUND: Chronic subdural hematoma (cSDH) is a common neurosurgical condition, with symptoms ranging from headaches to coma. Operative evacuation is the treatment of choice. Subdural reaccumulation leading to reoperation is a vexing postoperative complication. OBJECTIVE: To present a novel technique for intraoperative aspiration of pneumocephalus via a subdural drain following SDH evacuation as a method of reducing potential subdural space and promoting cerebral expansion, thereby decreasing SDH recurrence. METHODS: In this retrospective study, 15 patients who underwent operative evacuation of cSDH between 2008 and 2015 were assessed. Six patients underwent a small craniotomy with intraoperative pneumocephalus aspiration. These patients were matched by age, gender, and anticoagulation status to 9 patients who underwent evacuation of SDH without pneumocephalus aspiration. Quantitative volumetric analysis was performed on the preoperative, postoperative, and 1-mo follow-up computed tomography scan to assess the subdural volume. RESULTS: In the immediate postoperative period, there was no difference in the percentage of residual subdural fluid between the aspiration and control groups (0.291 vs 0.251; P = 1.00). There was a decrease in amount of pneumocephalus present when the aspiration technique was applied (0.182 vs 0.386; P = .041). At 1-mo follow-up, there was a decrease in the residual cSDH volume between the aspiration and the control groups (28.7 mL vs 60.8 mL; P = .011). The long-term evacuation rate was greater in the aspiration group (75.4% vs 51.6%; P = .015). CONCLUSION: Intraoperative aspiration of cSDH cavity is a safe technique that may enhance cerebral expansion and reduce likelihood of cSDH recurrence.

MRI-guided cryoablation for metastatic spine disease: intermediate-term clinical outcomes in 14 consecutive patients.

OBJECTIVE: Minimal access ablative techniques have emerged as a less invasive option for spinal metastatic disease reduction and separation from neural tissue. Compared with heat-based ablation modalities, percutaneous image-guided cryoablation allows for more distinct visualization of treatment margins. The authors report on a series of patients undergoing MRI-guided cryoablation as a feasible method for treating spinal metastatic disease. METHODS: A total of 14 patients with metastatic spine disease undergoing MR-monitored cryoablation were prospectively enrolled. Procedures were performed in an advanced imaging operating suite with the use of both CT and MRI to gain access to the spinal canal and monitor real-time cryoablation. RESULTS: The average age was 54.5 years (range 35-81 years). The mean preoperative Karnofsky Performance Status score was 79.3 (range 35-90). The average radiographic follow-up was 7.1 months (range 25-772 days), and the average clinical follow-up was 9.8 months (range 7-943 days). In 10 patients with epidural disease, 7 patients underwent postprocedural imaging, and of these 71% (5/7) had stable or reduced radiographic disease burden. Bone regrowth was observed in 63% (5/8) of patients with bone ablation during the treatment who had postoperative imaging. Pre- and postoperative visual analog scale scores were obtained, and a significant reduction in these scores was found following ablation. There were no complications. CONCLUSIONS: MR-guided cryoablation is a minimally invasive treatment option for metastatic spine disease. In patients with epidural disease, the majority experienced tumor reduction or arrest at follow-up. In addition, pain was significantly improved following ablation. The average hospital stay was short, and the procedure was safe in a range of patients who are otherwise not ideal candidates for standard treatment.

Crossing the Cervicothoracic Junction in Posterior Cervical Decompression and Fusion: A Cohort Analysis.

BACKGROUND: The cervicothoracic junction (CTJ) has often been identified as an area of biomechanical vulnerability; however, few studies have examined the relative merits of extending fusions across this area. In this study, we sought to investigate the tradeoffs involved in fusing across the CTJ in cases of elective posterior cervical laminectomy and fusion. METHODS: We conducted a single-institution retrospective cohort study of patients undergoing elective, multilevel, posterior cervical decompression and fusion for degenerative cervical stenosis. Data were collected on baseline clinical and radiographic variables as well any subsequent complications or reoperations. Outcomes measures were compared between those who received fusion stopping at C7 with those who received fusion crossing the CTJ, with multivariate logistic regression used to adjust for any known confounders. RESULTS: Patients whose fusion crossed the CTJ were found to have more levels fused (mean: 5.8 vs. 3.5 levels, P < 0.0001), longer surgical times (mean: 216 vs. 149 minutes, P < 0.0001), and higher estimated blood losses (mean: 475 vs. 116 mL, P < 0.0001) despite no significant differences in number of levels decompressed (mean: 4.2 vs. 4.3 levels, P = 0.63). The groups did not differ in overall reoperation rate (10.8% vs. 9.4%, P = 1.00), but crossing the CTJ was associated with a higher rate of wound dehiscence (7.8% vs. 0%, P = 0.03). This difference persisted in multivariate analysis (P < 0.001). CONCLUSIONS: Crossing the CTJ was associated with increased surgical time, estimated blood loss, and the rates of wound dehiscence. These tradeoffs should be considered in planning posterior cervical decompression and fusion procedures.

A computer vision approach to identifying the manufacturer and model of anterior cervical spinal hardware.

OBJECTIVE: Recent advances in computer vision have revolutionized many aspects of society but have yet to find significant penetrance in neurosurgery. One proposed use for this technology is to aid in the identification of implanted spinal hardware. In revision operations, knowing the manufacturer and model of previously implanted fusion systems upfront can facilitate a faster and safer procedure, but this information is frequently unavailable or incomplete. The authors present one approach for the automated, high-accuracy classification of anterior cervical hardware fusion systems using computer vision. METHODS: Patient records were searched for those who underwent anterior-posterior (AP) cervical radiography following anterior cervical discectomy and fusion (ACDF) at the authors' institution over a 10-year period (2008-2018). These images were then cropped and windowed to include just the cervical plating system. Images were then labeled with the appropriate manufacturer and system according to the operative record. A computer vision classifier was then constructed using the bag-of-visual-words technique and KAZE feature detection. Accuracy and validity were tested using an 80%/20% training/testing pseudorandom split over 100 iterations. RESULTS: A total of 321 total images were isolated containing 9 different ACDF systems from 5 different companies. The correct system was identified as the top choice in 91.5% ± 3.8% of the cases and one of the top 2 or 3 choices in 97.1% ± 2.0% and 98.4 ± 13% of the cases, respectively. Performance persisted despite the inclusion of variable sizes of hardware (i.e., 1-level, 2-level, and 3-level plates). Stratification by the size of hardware did not improve performance. CONCLUSIONS: A computer vision algorithm was trained to classify at least 9 different types of anterior cervical fusion systems using relatively sparse data sets and was demonstrated to perform with high accuracy. This represents one of many potential clinical applications of machine learning and computer vision in neurosurgical practice.

Spinal hemangioma mimicking a dumbbell-shaped schwannoma: Case report and review of the literature.

Spinal hemangiomas are common, benign vascular lesions that involve the bony portion of vertebral bodies and are generally asymptomatic. Rarely, they can become aggressive and present with predominantly epidural extension, mimicking other neoplasms. We present the case of a fifty-one year old woman who presented with myelopathy and was discovered to have a large mass causing epidural spinal cord compression, thought to be due to a peripheral nerve sheath tumor. She underwent surgery for tumor debulking. Intraoperatively, the mass was found to be mostly epidural with minimal bone involvement. Final pathology demonstrated a cavernous hemangioma. The patient did well post-operatively, with resolution of symptoms and stable size of residual tumor on eighteen month follow-up imaging.