Artificial intelligence innovations in neurosurgical oncology: a narrative review.

PURPOSE: Artificial Intelligence (AI) has become increasingly integrated clinically within neurosurgical oncology. This report reviews the cutting-edge technologies impacting tumor treatment and outcomes. METHODS: A rigorous literature search was performed with the aid of a research librarian to identify key articles referencing AI and related topics (machine learning (ML), computer vision (CV), augmented reality (AR), virtual reality (VR), etc.) for neurosurgical care of brain or spinal tumors. RESULTS: Treatment of central nervous system (CNS) tumors is being improved through advances across AI-such as AL, CV, and AR/VR. AI aided diagnostic and prognostication tools can influence pre-operative patient experience, while automated tumor segmentation and total resection predictions aid surgical planning. Novel intra-operative tools can rapidly provide histopathologic tumor classification to streamline treatment strategies. Post-operative video analysis, paired with rich surgical simulations, can enhance training feedback and regimens. CONCLUSION: While limited generalizability, bias, and patient data security are current concerns, the advent of federated learning, along with growing data consortiums, provides an avenue for increasingly safe, powerful, and effective AI platforms in the future.

Risk Factors and Incidence of Epilepsy after Severe Traumatic Brain Injury.

We determined the incidence of post-traumatic epilepsy after severe traumatic brain injury. Of 392 patients surviving to discharge, cumulative incidence of post-traumatic epilepsy was 25% at 5 years and 32% at 15 years, an increase compared with historical reports. Among patients with one late seizure (>7 days post-trauma), the risk of seizure recurrence was 62% after 1 year and 82% at 10 years. Competing hazards regression identified age, decompressive hemicraniectomy, and intracranial infection as independent predictors of post-traumatic epilepsy. Patients with severe traumatic brain injury and a single late post-traumatic seizure will likely require long-term antiseizure medicines. ANN NEUROL 2022;92:663-669.

Predicting posttraumatic epilepsy using admission electroencephalography after severe traumatic brain injury.

OBJECTIVE: Posttraumatic epilepsy (PTE) develops in as many as one third of severe traumatic brain injury (TBI) patients, often years after injury. Analysis of early electroencephalographic (EEG) features, by both standardized visual interpretation (viEEG) and quantitative EEG (qEEG) analysis, may aid early identification of patients at high risk for PTE. METHODS: We performed a case-control study using a prospective database of severe TBI patients treated at a single center from 2011 to 2018. We identified patients who survived 2 years postinjury and matched patients with PTE to those without using age and admission Glasgow Coma Scale score. A neuropsychologist recorded outcomes at 1 year using the Expanded Glasgow Outcomes Scale (GOSE). All patients underwent continuous EEG for 3-5 days. A board-certified epileptologist, blinded to outcomes, described viEEG features using standardized descriptions. We extracted 14 qEEG features from an early 5-min epoch, described them using qualitative statistics, then developed two multivariable models to predict long-term risk of PTE (random forest and logistic regression). RESULTS: We identified 27 patients with and 35 without PTE. GOSE scores were similar at 1 year (p = .93). The median time to onset of PTE was 7.2 months posttrauma (interquartile range = 2.2-22.2 months). None of the viEEG features was different between the groups. On qEEG, the PTE cohort had higher spectral power in the delta frequencies, more power variance in the delta and theta frequencies, and higher peak envelope (all p < .01). Using random forest, combining qEEG and clinical features produced an area under the curve of .76. Using logistic regression, increases in the delta:theta power ratio (odds ratio [OR] = 1.3, p < .01) and peak envelope (OR = 1.1, p < .01) predicted risk for PTE. SIGNIFICANCE: In a cohort of severe TBI patients, acute phase EEG features may predict PTE. Predictive models, as applied to this study, may help identify patients at high risk for PTE, assist early clinical management, and guide patient selection for clinical trials.

Radiosurgery outcomes in infratentorial juvenile pilocytic astrocytomas.

PURPOSE: To assess survival and neurological outcomes for patients who underwent primary or salvage stereotactic radiosurgery (SRS) for infratentorial juvenile pilocytic astrocytomas (JPA). METHODS: Between 1987 and 2022, 44 patients underwent SRS for infratentorial JPA. Twelve patients underwent primary SRS and 32 patients underwent salvage SRS. The median patient age at SRS was 11.6 years (range, 2-84 years). Prior to SRS, 32 patients had symptomatic neurological deficits, with ataxia as the most common symptom in 16 patients. The median tumor volume was 3.22 cc (range, 0.16-26.6 cc) and the median margin dose was 14 Gy (range, 9.6-20 Gy). RESULTS: The median follow-up was 10.9 years (range, 0.42-26.58 years). Overall survival (OS) after SRS was 97.7% at 1-year, and 92.5% at 5- and 10-years. Progression free survival (PFS) after SRS was 95.4% at 1-year, 79.0% at 5-years, and 61.4% at 10-years. There is not a significant difference in PFS between primary and salvage SRS patients (p = 0.79). Younger age correlated with improved PFS (HR 0.28, 95% CI 0.063-1.29, p = 0.021). Sixteen patients (50%) had symptomatic improvements while 4 patients (15.6%) had delayed onset of new symptoms related to tumor progression (n = 2) or treatment related complications (n = 2). Tumor volumetric regression or disappearance after radiosurgery was found in 24 patients (54.4%). Twelve patients (27.3%) had delayed tumor progression after SRS. Additional management of tumor progression included repeat surgery, repeat SRS, and chemotherapy. CONCLUSIONS: SRS was a valuable alternative to initial or repeat resection for deep seated infratentorial JPA patients. We found no survival differences between patients who had primary and salvage SRS.

Advances in surgical approaches for refractory pituitary adenomas.

Refractory pituitary adenomas are difficult to control tumors that progress through optimal surgical, medical, and radiation management. Repeat surgery is a valuable tool to reduce tumor volume for more effective radiation and/or medical therapy, and to decompress critical neurovascular structures. Advances in surgical techniques and technologies, including minimally invasive cranial approaches, intraoperative MRI suites, and cranial nerve monitoring, have improved surgical outcomes and expanded indications. Today, repeat transsphenoidal surgery has similar complications rates to upfront surgery in historical cohorts. The decision to operate on refractory adenomas should be made with multidisciplinary teams, balancing the benefit of tumor reduction with the potential for complications, including cranial nerve injury, carotid injury, and cerebrospinal fluid leak.

Deconstructing bias in social preferences reveals groupy and not-groupy behavior.

Group divisions are a continual feature of human history, with biases toward people's own groups shown in both experimental and natural settings. Using a within-subject design, this paper deconstructs group biases to find significant and robust individual differences; some individuals consistently respond to group divisions, while others do not. We examined individual behavior in two treatments in which subjects make pairwise decisions that determine own and others' incomes. In a political treatment, which divided subjects into groups based on their political leanings, political party members showed more in-group bias than Independents who professed the same political opinions. However, this greater bias was also present in a minimal group treatment, showing that stronger group identification was not the driver of higher favoritism in the political setting. Analyzing individual choices across the experiment, we categorize participants as "groupy" or "not groupy," such that groupy participants have social preferences that change for in-group and out-group recipients, while not-groupy participants' preferences do not change across group context. Demonstrating further that the group identity of the recipient mattered less to their choices, strongly not-groupy subjects made allocation decisions faster. We conclude that observed in-group biases build on a foundation of heterogeneity in individual groupiness.

Comparison of machine learning models to predict long-term outcomes after severe traumatic brain injury.

OBJECTIVE: An estimated 1.5 million people die every year worldwide from traumatic brain injury (TBI). Physicians are relatively poor at predicting long-term outcomes early in patients with severe TBI. Machine learning (ML) has shown promise at improving prediction models across a variety of neurological diseases. The authors sought to explore the following: 1) how various ML models performed compared to standard logistic regression techniques, and 2) if properly calibrated ML models could accurately predict outcomes up to 2 years posttrauma. METHODS: A secondary analysis of a prospectively collected database of patients with severe TBI treated at a single level 1 trauma center between November 2002 and December 2018 was performed. Neurological outcomes were assessed at 3, 6, 12, and 24 months postinjury with the Glasgow Outcome Scale. The authors used ML models including support vector machine, neural network, decision tree, and naïve Bayes models to predict outcome across all 4 time points by using clinical information available on admission, and they compared performance to a logistic regression model. The authors attempted to predict unfavorable versus favorable outcomes (Glasgow Outcome Scale scores of 1-3 vs 4-5), as well as mortality. Models' performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) with 95% confidence interval and balanced accuracy. RESULTS: Of the 599 patients in the database, the authors included 501, 537, 469, and 395 at 3, 6, 12, and 24 months posttrauma. Across all time points, the AUCs ranged from 0.71 to 0.85 for mortality and from 0.62 to 0.82 for unfavorable outcomes with various modeling strategies. Decision tree models performed worse than all other modeling approaches for multiple time points regarding both unfavorable outcomes and mortality. There were no statistically significant differences between any other models. After proper calibration, the models had little variation (0.02-0.05) across various time points. CONCLUSIONS: The ML models tested herein performed with equivalent success compared with logistic regression techniques for prognostication in TBI. The TBI prognostication models could predict outcomes beyond 6 months, out to 2 years postinjury.

Interaction of admission platelet count with current medications and the risk for chronic subdural recurrence.

OBJECTIVE: Chronic subdural hematoma (cSDH) has a reported 10%-24% rate of recurrence after surgery, and prognostic models for recurrence have produced equivocal results. The objective of this study was to leverage a data mining algorithm, chi-square automatic interaction detection (CHAID), which can incorporate continuous, nominal, and binary data into a decision tree, to identify the most robust predictors of repeat surgery for cSDH patients. METHODS: This was a retrospective cohort study of all patients with SDH from two level 1 trauma centers at a single institution. All patients underwent cSDH evacuation performed by 15 neurosurgeons between 2011 and 2020. The primary outcome was the rate of repeat surgery for recurrent cSDH following the initial evacuation. The authors used CHAID to identify relevant predictors of repeat surgery, including age, sex, comorbidities, postsurgical complications, platelet count prior to the first procedure, midline shift prior to the first procedure, hematoma volume, and preoperative use of anticoagulants, antiplatelets, or statins. RESULTS: Sixty (13.8%) of 435 study-eligible patients (average age 74.0 years) had a cSDH recurrence. These patients had 2.0 times greater odds of having used anticoagulants. The final CHAID model had an overall accuracy of 87.4% and an area under the curve of 0.76. According to the model, the predictor with the strongest association with cSDH recurrence was admission platelet count. Approximately 26% of patients (n = 23/87) with an admission platelet count < 157 × 109/L had a cSDH recurrence, whereas none of the 44 patients with admission platelets > 313 × 109/L had a recurrence. Approximately 17% of patients in the 157-313 × 109/L platelet group who had used preoperative statins required a second procedure, which was associated with a 2.3 times increased risk for repeat surgery compared to those who had not used statins preoperatively. Among those who had not used preoperative statins, a platelet count ≤ 179 × 109/L on admission for the first procedure was the strongest differentiator for a second surgery (n = 5/22 [23%]), which increased the risk of recurrence by 4.5 times. Among the patients using preoperative statins, the use of anticoagulants was the strongest differentiator for requiring repeat surgery (n = 11/33 [33%]). CONCLUSIONS: The described model identified platelet count on admission as the most important predictor of repeat cSDH surgery, followed by preoperative statin use and anticoagulant use. Critical cutoffs for platelet count were identified, which future studies should evaluate to determine if they are modifiable or reflective of underlying disease states.

Outcome Prediction in Patients with Severe Traumatic Brain Injury Using Deep Learning from Head CT Scans.

Background After severe traumatic brain injury (sTBI), physicians use long-term prognostication to guide acute clinical care yet struggle to predict outcomes in comatose patients. Purpose To develop and evaluate a prognostic model combining deep learning of head CT scans and clinical information to predict long-term outcomes after sTBI. Materials and Methods This was a retrospective analysis of two prospectively collected databases. The model-building set included 537 patients (mean age, 40 years ± 17 [SD]; 422 men) from one institution from November 2002 to December 2018. Transfer learning and curriculum learning were applied to a convolutional neural network using admission head CT to predict mortality and unfavorable outcomes (Glasgow Outcomes Scale scores 1-3) at 6 months. This was combined with clinical input for a holistic fusion model. The models were evaluated using an independent internal test set and an external cohort of 220 patients with sTBI (mean age, 39 years ± 17; 166 men) from 18 institutions in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury (TRACK-TBI) study from February 2014 to April 2018. The models were compared with the International Mission on Prognosis and Analysis of Clinical Trials in TBI (IMPACT) model and the predictions of three neurosurgeons. Area under the receiver operating characteristic curve (AUC) was used as the main model performance metric. Results The fusion model had higher AUCs than did the IMPACT model in the prediction of mortality (AUC, 0.92 [95% CI: 0.86, 0.97] vs 0.80 [95% CI: 0.71, 0.88]; P < .001) and unfavorable outcomes (AUC, 0.88 [95% CI: 0.82, 0.94] vs 0.82 [95% CI: 0.75, 0.90]; P = .04) on the internal data set. For external TRACK-TBI testing, there was no evidence of a significant difference in the performance of any models compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.90) in the prediction of mortality. The Imaging model (AUC, 0.73; 95% CI: 0.66-0.81; P = .02) and the fusion model (AUC, 0.68; 95% CI: 0.60, 0.76; P = .02) underperformed as compared with the IMPACT model (AUC, 0.83; 95% CI: 0.77, 0.89) in the prediction of unfavorable outcomes. The fusion model outperformed the predictions of the neurosurgeons. Conclusion A deep learning model of head CT and clinical information can be used to predict 6-month outcomes after severe traumatic brain injury. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Haller in this issue.

Gonococcal Infection and Ventriculoperitoneal Shunts.

ABSTRACT: Neisseria gonorrhoea e and Chlamydia trachomatis are pathogens commonly isolated in pelvic inflammatory disease. Neisseria gonorrhoea e may uncommonly spread outside the urogenital tract to cause complications. We present 2 cases of adolescents with ventriculoperitoneal shunt infection due to N. gonorrhoea e, requiring shunt externalization.

A contemporary update on glioblastoma: molecular biology, current management, and a vision towards bio-adaptable personalized care.

INTRODUCTION: Glioblastoma (GBM) is the most fatal brain tumor in adults. Current survival rates of GBM remain below 2 years due to GBM's aggressive cellular migration and genetically driven treatment escape pathways. Despite our rapidly increasing understanding of GBM biology, earlier diagnoses, and refined surgical techniques, only moderate survival benefits have been achieved. Nonetheless, the pressing need for better survival rates has brought forward a multitude of newer therapeutic approaches and opened the door for potential personalization of these modalities in the near future. METHODS: We reviewed the published literature discussing the current state of knowledge regarding GBM biology and therapy and summarized the information that may point toward future personalized therapeutic strategies. RESULTS: Several novel modalities such as oncolytic viruses, targeted immune, and molecular therapies, and tumor treating fields have been introduced. To date, there is no single treatment modality for GBM, but rather a wide spectrum of combined modalities that address intratumoral cellular and genetic variabilities. While the current state of GBM research and clinical trial landscape may hold promise, current literature lacks any fruitful progress towards personalized GBM therapy. CONCLUSION: In this review, we are discussing our recent knowledge of the GBM genetic biologic landscape and the current advances in therapy, as well as providing a blueprint for an envisioned GBM management paradigm that should be personalized and adaptable to accommodate each patient's diverse genetic variations and therapy response/escape patterns.

Long term results of primary radiosurgery for vestibular schwannomas.

BACKGROUND: Stereotactic radiosurgery (SRS) has become a primary option for management for both newly diagnosed vestibular schwannomas (VS), as well as VS that enlarge after initial observation. METHODS: A retrospective review of our prospectively maintained data base found 871 patients who underwent Gamma knife® SRS as their initial (primary) management between 1987 and 2008. Follow-up ranged from 1-25 years (median = 5.2 years) Median tumor volume was 0.9 cc (0.02-36) and median margin dose was 13 Gy (12-25). RESULTS: Progression free survival (PFS) after SRS was 97% at 3 years, 95% at 5 years, and 94% at 10 years. Freedom from delayed surgical resection was found in 98.7% of patients. Smaller tumor volume was significantly associated with improved PFS. There were 326 patients with serviceable hearing (Gardner-Robertson 1 or 2) at the time of SRS with audiological follow-up of ≥ 1 year. Serviceable hearing preservation rates after SRS were 89.8% at 1 year, 76.9% at 3 years, 68.4% at 5 years, 62.5% at 7 years, and 51.4% at 10 years. Factors associated with improved serviceable hearing preservation included younger age, Gardner-Robertson grade 1 at SRS, and absence of subjective complaints of dysequilibrium or vertigo (vestibulopathy). Fifty-one patients (5.8%) developed trigeminal neuropathy. Fourteen (1.6%) developed a transient House-Brackmann grade 2 or 3 facial neuropathy. CONCLUSIONS: In this report with extended follow-up, primary SRS achieved tumor growth control in 94% of patients. Optimization of long- term cranial nerve outcomes remains an important achievement of this management strategy for VS.

Gamma Knife Radiosurgery for Trigeminal Neuralgia Caused by a Cavernous Malformation: Case Report and Literature Review.

OBJECTIVE: Trigeminal neuralgia (TN) related to a brainstem cavernous malformation (CM) is a rare entity. We present the first radiosurgical management of a patient with TN secondary to a CM. CLINICAL PRESENTATION: An 80-year-old female presented with a 33-year history of progressively severe TN refractory to medications. Imaging confirmed a solitary CM located at the pontine dorsal root entry zone of cranial nerve 5. TREATMENT: Stereotactic radiosurgery of the trigeminal nerve was performed using the Leksell gamma knife. A single 4-mm isocenter of radiation was focused on the trigeminal nerve and a maximum dose of 80 Gy (40 Gy at the 50% isodose line) was delivered to the nerve. RESULTS: At 1 year, the patient noted that the severe pain attacks had been reduced by 75%, although a background lingering discomfort persisted. Pain suppression medications had been significantly reduced to lamotrigine 100 mg twice daily. Her preoperative distribution of sensory dysfunction mildly increased. CONCLUSION: For medically refractory TN related to a CM, radiosurgery of the afferent nerve may ameliorate pain without a major decrease in sensation. The more than 30-year history of pain in our patient may have reduced the chance of more significant pain relief.

Case Series: Pediatric Shunt Tunnel Catheter Infection.

Shunt infections are common pediatric neurosurgical cases with high morbidity that almost always requires surgical removal of the shunt, external ventricular drain placement, and delayed shunt replacement. Tunnel infections are well-described clinical entities occurring with indwelling catheters, whereby the indwelling tunnel portion of a line becomes externally infected with a sterile central lumen. These infections are typically treated with line replacement or antibiotics depending on clinical circumstances. We describe 2 cases of shunt tunnel infection. Both cases presented as erythema over the thoracic portion of the shunt without signs of CNS infection, with only a remote history of shunt surgery and no recent systemic illness. One case was treated with a course of antibiotics, and the other with surgical removal and eventual replacement. Both children made full recoveries. Our case series juxtaposes 2 alternative successful strategies for treating the rare entity of shunt tunnel infection.

Prophylactic Antiepileptics and Seizure Incidence Following Subarachnoid Hemorrhage: A Propensity Score-Matched Analysis.

BACKGROUND AND PURPOSE: The utility of prophylactic antiepileptic drug (AED) administration after spontaneous subarachnoid hemorrhage remains controversial. AEDs have not clearly been associated with a reduction in seizure incidence and have been associated with both neurological worsening and delayed functional recovery in this setting. METHODS: We retrospectively analyzed a prospectively collected database of subarachnoid hemorrhage patients admitted to our institution between 2005 and 2010. Between 2005 and 2007, all patients received prophylactic AEDs upon admission. After 2007, no patients received prophylactic AEDs or had AEDs immediately discontinued if initiated at an outside hospital. A propensity score-matched analysis was then performed to compare the development of clinical and electrographic seizures in these 2 populations. RESULTS: Three hundred and fifty three patients with spontaneous subarachnoid hemorrhage were analyzed, 43% of whom were treated with prophylactic AEDs upon admission. Overall, 10% of patients suffered clinical and electrographic seizures, most frequently occurring within 24 hours of ictus (47%). The incidence of seizures did not vary significantly based on the use of prophylactic AEDs (11 versus 8%; P=0.33). Propensity score-matched analyses suggest that patients receiving prophylactic AEDs had a similar likelihood of suffering seizures as those who did not (P=0.49). CONCLUSIONS: Propensity score-matched analysis suggests that prophylactic AEDs do not significantly reduce the risk of seizure occurrence in patients with spontaneous subarachnoid hemorrhage.

Development and prospective validation of an artificial intelligence-based smartphone app for rapid intraoperative pituitary adenoma identification.

BACKGROUND: Intraoperative pathology consultation plays a crucial role in tumor surgery. The ability to accurately and rapidly distinguish tumor from normal tissue can greatly impact intraoperative surgical oncology management. However, this is dependent on the availability of a specialized pathologist for a reliable diagnosis. We developed and prospectively validated an artificial intelligence-based smartphone app capable of differentiating between pituitary adenoma and normal pituitary gland using stimulated Raman histology, almost instantly. METHODS: The study consisted of three parts. After data collection (part 1) and development of a deep learning-based smartphone app (part 2), we conducted a prospective study that included 40 consecutive patients with 194 samples to evaluate the app in real-time in a surgical setting (part 3). The smartphone app's sensitivity, specificity, positive predictive value, and negative predictive value were evaluated by comparing the diagnosis rendered by the app to the ground-truth diagnosis set by a neuropathologist. RESULTS: The app exhibits a sensitivity of 96.1% (95% CI: 89.9-99.0%), specificity of 92.7% (95% CI: 74-99.3%), positive predictive value of 98% (95% CI: 92.2-99.8%), and negative predictive value of 86.4% (95% CI: 66.2-96.8%). An external validation of the smartphone app on 40 different adenoma tumors and a total of 191 scanned SRH specimens from a public database shows a sensitivity of 93.7% (95% CI: 89.3-96.7%). CONCLUSIONS: The app can be readily expanded and repurposed to work on different types of tumors and optical images. Rapid recognition of normal versus tumor tissue during surgery may contribute to improved intraoperative surgical management and oncologic outcomes. In addition to the accelerated pathological assessments during surgery, this platform can be of great benefit in community hospitals and developing countries, where immediate access to a specialized pathologist during surgery is limited.

In tumor surgery, precise identification of abnormal tissue during surgical removal of the tumor is paramount. Traditional methods rely on the availability of specialized pathologists for a reliable diagnosis, which could be a limitation in many hospitals. Our study introduces a user-friendly smartphone app that quickly and precisely diagnoses pituitary tumors, powered by artificial intelligence (AI), which is the simulation of human intelligence in machines for tasks like learning, reasoning, problem-solving, and decision-making. Through data collection, app development, and validation, our findings demonstrate that the app can rapidly and accurately identify tumors in real-time. External validation further confirmed its effectiveness in detecting tumor tissue collected from a different source. This AI-driven app could contribute to elevating surgical precision, particularly in settings lacking immediate access to specialized pathologists.

Subarachnoid Hemorrhage Outcomes in an Endovascular Right of First Refusal Neurosurgical Environment.

BACKGROUND: Randomized controlled trials demonstrate that endovascular techniques yield improved outcomes compared with microsurgical approaches. However, not all patients are suitable candidates for endovascular management. This study aimed to determine if healthy patients managed microsurgically could achieve functional outcomes comparable to patients managed endovascularly. METHODS: Patients treated for ruptured aneurysmal subarachnoid hemorrhage at 2 level 1 stroke centers from January 2012 through December 2020 were retrospectively reviewed. All cases were evaluated in an endovascular right of first refusal neurosurgical environment. We collected relevant clinical and follow-up data and created a generalized linear model to identify differences between patients treated endovascularly versus microsurgically. A propensity score model accounting for these differences was used to predict patient outcomes. Functional outcomes were independently assessed using the modified Rankin Scale (mRS) with good functional outcome defined as modified Rankin Scale score <3. RESULTS: The study included 588 patients (211 microsurgical, 377 endovascular); median age was 58 years (interquartile range: 40-86 years); in-hospital mortality was 13%. Age, aneurysm size, and aneurysm location significantly predicted treatment modality (all P < 0.05). After greedy-type matching (210 microsurgical, 210 endovascular), patients managed microsurgically were less likely to be discharged home (odds ratio = 0.6, 95% confidence interval 0.4-0.9, P = 0.01). Functional differences disappeared over time; patients in the 2 treatment arms had similar functional outcomes at 3 months (odds ratio = 1.1, 95% confidence interval 0.7-1.8, P = 0.66) and 1 year after subarachnoid hemorrhage (odds ratio = 1.3, 95% confidence interval 0.8-2.1, P = 0.38). CONCLUSIONS: In an endovascular right of first refusal neurosurgical environment, practitioners can treat patients who are not good endovascular candidates microsurgically and achieve functional outcomes comparable to patients managed endovascularly.

Automated Preoperative and Postoperative Volume Estimates Risk of Retreatment in Chronic Subdural Hematoma: A Retrospective, Multicenter Study.

BACKGROUND AND OBJECTIVES: Several neurosurgical pathologies, ranging from glioblastoma to hemorrhagic stroke, use volume thresholds to guide treatment decisions. For chronic subdural hematoma (cSDH), with a risk of retreatment of 10%-30%, the relationship between preoperative and postoperative cSDH volume and retreatment is not well understood. We investigated the potential link between preoperative and postoperative cSDH volumes and retreatment. METHODS: We performed a retrospective chart review of patients operated for unilateral cSDH from 4 level 1 trauma centers, February 2009-August 2021. We used a 3-dimensional deep learning, automated segmentation pipeline to calculate preoperative and postoperative cSDH volumes. To identify volume thresholds, we constructed a receiver operating curve with preoperative and postoperative volumes to predict cSDH retreatment rates and selected the threshold with the highest Youden index. Then, we developed a light gradient boosting machine to predict the risk of cSDH recurrence. RESULTS: We identified 538 patients with unilateral cSDH, of whom 62 (12%) underwent surgical retreatment within 6 months of the index surgery. cSDH retreatment was associated with higher preoperative (122 vs 103 mL; P < .001) and postoperative (62 vs 35 mL; P < .001) volumes. Patients with >140 mL preoperative volume had nearly triple the risk of cSDH recurrence compared with those below 140 mL, while a postoperative volume >46 mL led to an increased risk for retreatment (22% vs 6%; P < .001). On multivariate modeling, our model had an area under the receiver operating curve of 0.76 (95% CI: 0.60-0.93) for predicting retreatment. The most important features were preoperative and postoperative volume, platelet count, and age. CONCLUSION: Larger preoperative and postoperative cSDH volumes increase the risk of retreatment. Volume thresholds may allow identification of patients at high risk of cSDH retreatment who would benefit from adjunct treatments. Machine learning algorithm can quickly provide accurate estimates of preoperative and postoperative volumes.

Early Seizure Prophylaxis in Mild and Moderate Traumatic Brain Injury: A Systematic Review and Meta-Analysis.

Importance: Guidelines recommend seizure prophylaxis for early posttraumatic seizures (PTS) after severe traumatic brain injury (TBI). Use of antiseizure medications for early seizure prophylaxis after mild or moderate TBI remains controversial. Objective: To determine the association between seizure prophylaxis and risk reduction for early PTS in mild and moderate TBI. Data Sources: PubMed, Google Scholar, and Web of Science (January 1, 1991, to April 18, 2023) were systematically searched. Study Selection: Observational studies of adult patients presenting to trauma centers in high-income countries with mild (Glasgow Coma Scale [GCS], 13-15) and moderate (GCS, 9-12) TBI comparing rates of early PTS among patients with seizure prophylaxis with those without seizure prophylaxis. Data Extraction and Synthesis: The Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) reporting guidelines were used. Two authors independently reviewed all titles and abstracts, and 3 authors reviewed final studies for inclusion. A meta-analysis was performed using a random-effects model with absolute risk reduction. Main Outcome Measures: The main outcome was absolute risk reduction of early PTS, defined as seizures within 7 days of initial injury, in patients with mild or moderate TBI receiving seizure prophylaxis in the first week after injury. A secondary analysis was performed in patients with only mild TBI. Results: A total of 64 full articles were reviewed after screening; 8 studies (including 5637 patients) were included for the mild and moderate TBI analysis, and 5 studies (including 3803 patients) were included for the mild TBI analysis. The absolute risk reduction of seizure prophylaxis for early PTS in mild to moderate TBI (GCS, 9-15) was 0.6% (95% CI, 0.1%-1.2%; P = .02). The absolute risk reduction for mild TBI alone was similar 0.6% (95% CI, 0.01%-1.2%; P = .04). The number needed to treat to prevent 1 seizure was 167 patients. Conclusion and Relevance: Seizure prophylaxis after mild and moderate TBI was associated with a small but statistically significant reduced risk of early posttraumatic seizures after mild and moderate TBI. The small absolute risk reduction and low prevalence of early seizures should be weighed against potential acute risks of antiseizure medications as well as the risk of inappropriate continuation beyond 7 days.

Insights into epileptogenesis from post-traumatic epilepsy.

Post-traumatic epilepsy (PTE) accounts for 5% of all epilepsies. The incidence of PTE after traumatic brain injury (TBI) depends on the severity of injury, approaching one in three in groups with the most severe injuries. The repeated seizures that characterize PTE impair neurological recovery and increase the risk of poor outcomes after TBI. Given this high risk of recurrent seizures and the relatively short latency period for their development after injury, PTE serves as a model disease to understand human epileptogenesis and trial novel anti-epileptogenic therapies. Epileptogenesis is the process whereby previously normal brain tissue becomes prone to recurrent abnormal electrical activity, ultimately resulting in seizures. In this Review, we describe the clinical course of PTE and highlight promising research into epileptogenesis and treatment using animal models of PTE. Clinical, imaging, EEG and fluid biomarkers are being developed to aid the identification of patients at high risk of PTE who might benefit from anti-epileptogenic therapies. Studies in preclinical models of PTE have identified tractable pathways and novel therapeutic strategies that can potentially prevent epilepsy, which remain to be validated in humans. In addition to improving outcomes after TBI, advances in PTE research are likely to provide therapeutic insights that are relevant to all epilepsies.