Dendrimer nanotherapy targeting of glial dysfunction improves inflammation and neurobehavioral phenotype in adult female Mecp2-heterozygous mouse model of Rett syndrome.

Rett syndrome is an X-linked neurodevelopmental disorder caused by mutation of Mecp2 gene and primarily affects females. Glial cell dysfunction has been implicated in in Rett syndrome (RTT) both in patients and in mouse models of this disorder and can affect synaptogenesis, glial metabolism and inflammation. Here we assessed whether treatment of adult (5-6 months old) symptomatic Mecp2-heterozygous female mice with N-acetyl cysteine conjugated to dendrimer (D-NAC), which is known to target glia and modulate inflammation and oxidative injury, results in improved behavioral phenotype, sleep and glial inflammatory profile. We show that unbiased global metabolomic analysis of the hippocampus and striatum in adult Mecp2-heterozygous mice demonstrates significant differences in lipid metabolism associated with neuroinflammation, providing the rationale for targeting glial inflammation in this model. Our results demonstrate that treatment with D-NAC (10 mg/kg NAC) once weekly is more efficacious than equivalently dosed free NAC in improving the gross neurobehavioral phenotype in symptomatic Mecp2-heterozygous female mice. We also show that D-NAC therapy is significantly better than saline in ameliorating several aspects of the abnormal phenotype including paw clench, mobility, fear memory, REM sleep and epileptiform activity burden. Systemic D-NAC significantly improves microglial proinflammatory cytokine production and is associated with improvements in several aspects of the phenotype including paw clench, mobility, fear memory, and REM sleep, and epileptiform activity burden in comparison to saline-treated Mecp2-hetereozygous mice. Systemic glial-targeted delivery of D-NAC after symptom onset in an older clinically relevant Rett syndrome model shows promise in improving neurobehavioral impairments along with sleep pattern and epileptiform activity burden. These findings argue for the translational value of this approach for treatment of patients with Rett Syndrome.

Chemogenetics as a neuromodulatory approach to treating neuropsychiatric diseases and disorders.

Chemogenetics enables precise, non-invasive, and reversible modulation of neural activity via the activation of engineered receptors that are pharmacologically selective to endogenous or exogenous ligands. With recent advances in therapeutic gene delivery, chemogenetics is poised to support novel interventions against neuropsychiatric diseases and disorders. To evaluate its translational potential, we performed a scoping review of applications of chemogenetics that led to the reversal of molecular and behavioral deficits in studies relevant to neuropsychiatric diseases and disorders. In this review, we present these findings and discuss the potential and challenges for using chemogenetics as a precision medicine-based neuromodulation strategy.

Strategies to improve surgical technical competency: a systematic review.

BACKGROUND: A cornerstone of surgical residency training is an educational program that produces highly skilled and effective surgeons. Training structures are constantly being revised due to evolving program structures, shifting workforces, and variability in the clinical environment. This has resulted in significant heterogeneity in all surgical resident education, training tools utilized, and measures of training efficacy. METHODS: We systematically reviewed educational interventions for technical skills in neurosurgery published across PubMed, Embase, and Web of Science over four decades. We extracted general characteristics of each surgical training tool while categorizing educational interventions by modality and neurosurgical application. RESULTS: We identified 626 studies which developed surgical training tools across eight different training modalities: textbooks and literature (11), online resources (53), didactic teaching and one-on-one instruction (7), laboratory courses (50), cadaveric models (63), animal models (47), mixed reality (166), and physical models (229). While publication volume has grown exponentially, a majority of studies were cited with relatively low frequency. Most training programs were published in the development and validation phase with only 2.1% of tools implemented long-term. Each training modality expressed unique strengths and limitations, with limited data reported on the educational impact connected to each training tool. CONCLUSIONS: Numerous surgical training tools have been developed and implemented across residency training programs. Though many creative and cutting-edge tools have been devised, evidence supporting educational efficacy and long-term application is lacking. Increased utilization of novel surgical training tools will require validation of metrics used to assess the training outcomes and optimized integration with clinical practice.

Early Mobilization in a PICU: A Qualitative Sustainability Analysis of PICU Up!

OBJECTIVES: To identify staff-reported factors and perceptions that influenced implementation and sustainability of an early mobilization program (PICU Up!) in the PICU. DESIGN: A qualitative study using semistructured phone interviews to characterize interprofessional staff perspectives of the PICU Up! program. Following data saturation, thematic analysis was performed on interview transcripts. SETTING: Tertiary-care PICU in the Johns Hopkins Hospital, Baltimore, MD. SUBJECTS: Interprofessional PICU staff. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Fifty-two staff members involved in PICU mobilization across multiple disciplines were interviewed. Three constructs emerged that reflected the different stages of PICU Up! program execution: 1) factors influencing the implementation process, 2) staff perceptions of PICU Up!, and 3) improvements in program integration. Themes were developed within these constructs, addressing facilitators for PICU Up! implementation, cultural changes for unitwide integration, positive impressions toward early mobility, barriers to program sustainability, and refinements for more robust staff and family engagement. CONCLUSIONS: Three years after implementation, PICU Up! remains well-received by staff, positively influencing role satisfaction and PICU team dynamics. Furthermore, patients and family members are perceived to be enthusiastic about mobility efforts, driving staff support. Through an ongoing focus on stakeholder buy-in, interprofessional engagement, and bundled care to promote mobility, the program has become part of the culture in the Johns Hopkins Hospital PICU. However, several barriers remain that prevent consistent execution of early mobility, including challenges with resource management, sedation decisions, and patient heterogeneity. Characterizing these staff perceptions can facilitate the development of solutions that use institutional strengths to grow and sustain PICU mobility initiatives.

Neurosurgical gene therapy for central nervous system diseases.

Viral vector mediated gene therapies for neurodegenerative and neurodevelopmental conditions that require neurosurgical administration continue to expand. We systematically reviewed the National Institutes of Health (NIH) ClinicalTrials.gov database to identify all clinical trials studying in-vivo viral vector mediated gene therapies targeted to the CNS for neurodegenerative and neurodevelopmental diseases. We isolated studies which delivered therapies using neurosurgical approaches: intracisternal, intraventricular, and/or intraparenchymal. Clinical trials primarily registered in international countries were included if they were referenced by an NIH registered clinical trial. We performed a scoping review to identify the preclinical studies that supported each human clinical trial. Key preclinical and clinical data were aggregated to characterize vector capsid design, delivery methods, gene expression profile, and clinical benefit. A total of 64 clinical trials were identified in active, completed, terminated, and long-term follow-up stages. A range of CNS conditions across pediatric and adult populations are being studied with CNS targeted viral vector gene therapy, including Alzheimer's disease, Parkinson's disease, AADC deficiency, sphingolipidoses, mucopolysaccharidoses, neuronal ceroid lipofuscinoses, spinal muscular atrophy, adrenoleukodystrophy, Canavan disease, frontotemporal dementia, Huntington's disease, Rett syndrome, Dravet syndrome, mesial temporal lobe epilepsy, and glutaric acidemia. Adeno-associated viral vectors (AAVs) were utilized by the majority of tested therapies, with vector serotypes, regulatory elements, delivery methods, and vector monitoring varying based on the disease being studied. Intraparenchymal delivery has evolved significantly, with MRI-guided convection-enhanced delivery established as a gold standard method for pioneering novel gene targets.

Role of Hospital Connectedness in Brain Metastasis Outcomes.

Importance: Although patients with brain metastases receive interdisciplinary and multi-institutional care, the association between neuro-oncologic care networks and patient outcomes remains unknown. As patients often interact with multiple facilities, quantifying this association across a network of hospitals is critical to capture the complexity of the health care journey for patients with brain metastases. Objective: To evaluate how statewide health care network metrics are associated with inpatient mortality and hospital length of stay (LOS) for patients with brain metastases. Design, Setting, and Participants: This multicenter, statewide cohort study used data from the 2018 to 2019 Healthcare Cost and Utilization Project State Inpatient and Emergency Department Databases. Primary analyses were completed by August 2023. Participants included adults with a brain metastases receiving care in Massachusetts. Exposure: All inpatient and emergency department visits mapped for patients following the first diagnosis of brain metastasis. Main Outcomes and Measures: Inpatient mortality and hospital LOS were the main outcomes assessed. Hospital interdependence in brain metastases care was calculated using a connectedness score (weighted degree: weighted sum of ties to other care facilities). The association between hospital connectedness and clinical outcomes was analyzed using mixed-effects logistic and linear regression models, adjusting for hospital-level features. Results: In this cohort study, 4679 patients with brain metastases were identified with inpatient or ED encounters in Massachusetts (from 2018 to 2019). The median (IQR) age was 64 (57-73) years, and 2559 (55%) were female. There was interdependence in brain metastases care, with 993 patients (21%) visiting 2 or more unique hospitals. Highly connected hospitals were heterogeneous, with many being small and one-half lacking subspecialty neuro-oncologic care or teaching status. Increased hospital connectedness was significantly associated with improved inpatient mortality for patients with brain metastases, with the lowest connectedness quartile associated with more than double the risk of mortality compared with the highest quartile (odds ratio, 2.34; 95% CI, 1.33-4.11; P = .003). A stepwise increase in inpatient mortality risk was observed as hospital connectedness decreased, independently of hospital volume. Furthermore, intermediate hospital connectedness was associated with increased hospital LOS (coefficient, 1.08; 95% CI, 0.17-1.95; P = .006). Conclusions and Relevance: This study found that hospital-to-hospital interconnectedness was significantly associated with improved clinical outcomes for patients with brain metastases. The salience of network metrics highlights their potential role alongside other patient-level and hospital-level variables to evaluate and improve oncology care delivery.

Spatial Distribution of Meningiomas: A Magnetic Resonance Image Atlas.

BACKGROUND AND OBJECTIVES: The size and anatomic location of meningiomas have been shown to correlate with distinct clinical manifestations, histopathological subtypes, and surgical risk. However, meningioma anatomic origin sites can be obscured in large tumors and those crossing compartments. We therefore sought to apply unbiased lesion mapping to localize intracranial meningioma distributions and their association with biology and grade. METHODS: MRI scans, World Health Organization (WHO) grade, and a molecularly Integrated Grade (IG) derived from cytogenetics were analyzed from adult patients with intracranial meningiomas. Semi-automated tumor segmentation was performed on T1-weighted contrast-enhanced MRI. We used the voxel-based lesion mapping technique to generate a meningioma atlas, mapping spatial frequency and correlating with tumor grades. RESULTS: Of 881 patients with meningioma (median age: 57 years, 68.8% female), 589 were WHO grade 1 (66.8%), 265 WHO grade 2 (30.1%), and 27 WHO grade 3 (3.1%) with a median tumor volume of 14.6 cm3. After molecular reclassification, 585 were IG-1 (66.4%), 160 IG-2 (18.2%), and 136 IG-3 (15.4%). Benign tumors were concentrated in and around the midline anterior skull base while malignant meningiomas were enriched in the falcine/parasagittal region and the sphenoid wing, similar to the distribution when stratified by chromosome 1p loss. Meningiomas exhibited sharper spatial clustering when stratified by the molecular IG than by WHO grade. WHO grade 2 meningiomas divided equally across IG 1-3, with corresponding partition of spatial distribution in the midline anterior skull base (in WHO grade 2, IG-1) and falcine/parasagittal and sphenoid regions (WHO grade 2, IG-3). Meningioma volumes significantly varied across age, sex, and WHO/IG grades. CONCLUSION: We demonstrate the utility of voxel-based lesion mapping for intracranial tumors, characterizing distinct meningioma distribution patterns across histopathological and molecularly defined grades. Molecular grading associated with sharper tumor spatial clusters, supporting a phenotype-genotype association in meningiomas.

Sustainability of a PICU Situation Awareness Intervention: A Qualitative Study.

Introduction: We aimed to investigate facilitators and barriers that impact the sustainability of an interprofessional situation awareness bundle. Methods: This is a single-center qualitative study at a tertiary care pediatric center examining the sustainability of an interprofessional situation awareness bundle to reduce in-hospital cardiac arrests. The bundle includes an automated clinical decision support tool, twice-daily safety huddles, and a bedside mitigation plan. A trained research staff member interviewed participants in October 2022. Interviews were audio recorded and transcribed verbatim, and recruitment continued until data saturation. Inductive and deductive analyses were used here. Results: The authors interviewed twelve staff members via individual semistructured interviews: registered nurses (RN, n = 2) and clinicians [(advanced practice providers, n = 2), pediatric critical care fellows, n = 4 and attendings, n = 4)]. Five main themes were identified: (1) the situation awareness bundle is ingrained into daily practice and culture, (2) the bundle has strengthened communication, decision-making, and improved outcomes, (3) standardized processes, stakeholder buy-in, and support of team members are key to adoption and sustainability, (4) variation in processes and fast-changing clinical context remains a challenge for reliable use, and (5) the situation awareness bundle excluded families. Conclusions: The situation awareness bundle has become ingrained, strengthened, and sustained over the last 5 years through integration into daily practice and culture and leveraging standardized processes, tools and technology. It is associated with improved communication and shared decision-making. Understanding the key components for implementation and sustainability is necessary for ongoing spread and improvement in the future.

Interhospital transfer dynamics for patients with intracranial hemorrhage in Massachusetts.

Introduction: Intracranial hemorrhages present across a spectrum of clinical phenotypes, with many patients transferred across hospitals to access higher levels of neurocritical care. We sought to characterize patient dispositions following intracranial hemorrhage and examine disparities associated with interhospital transfers. Methods: Using the Healthcare Cost and Utilization Project database, we mapped and identified factors influencing the likelihood of patient transfers and receipt of specialist interventional procedures following intracranial hemorrhage. Results: Of 11,660 patients with intracranial hemorrhage, 59.4% had non-traumatic and 87.5% single compartment bleeds. After presentation, about a quarter of patients were transferred to another facility either directly from the ED (23.0%) or after inpatient admission (1.8%). On unadjusted analysis, patients who were white, in the upper income quartiles, with private insurance, or resided in suburban areas were more frequently transferred. After adjusting for patient-and hospital-level variables, younger and non-white patients had higher odds of transfer. Hospital capabilities, residence location, insurance status, and prior therapeutic relationship remained as transfer predictors. Transferred patients had a similar hospital length of stay compared to admitted patients, with 43.1% having no recorded surgical or specialist interventional procedure after transfer. Discussion: Our analysis reveals opportunities for improvement in risk stratification guiding transfers, as well as structural challenges likely impacting transfer decisions.

Generation and applications of synthetic computed tomography images for neurosurgical planning.

OBJECTIVE: CT and MRI are synergistic in the information provided for neurosurgical planning. While obtaining both types of images lends unique data from each, doing so adds to cost and exposes patients to additional ionizing radiation after MRI has been performed. Cross-modal synthesis of high-resolution CT images from MRI sequences offers an appealing solution. The authors therefore sought to develop a deep learning conditional generative adversarial network (cGAN) which performs this synthesis. METHODS: Preoperative paired CT and contrast-enhanced MR images were collected for patients with meningioma, pituitary tumor, vestibular schwannoma, and cerebrovascular disease. CT and MR images were denoised, field corrected, and coregistered. MR images were fed to a cGAN that exported a "synthetic" CT scan. The accuracy of synthetic CT images was assessed objectively using the quantitative similarity metrics as well as by clinical features such as sella and internal auditory canal (IAC) dimensions and mastoid/clinoid/sphenoid aeration. RESULTS: A total of 92,981 paired CT/MR images obtained in 80 patients were used for training/testing, and 10,068 paired images from 10 patients were used for external validation. Synthetic CT images reconstructed the bony skull base and convexity with relatively high accuracy. Measurements of the sella and IAC showed a median relative error between synthetic CT scans and ground truth images of 6%, with greater variability in IAC reconstruction compared with the sella. Aerations in the mastoid, clinoid, and sphenoid regions were generally captured, although there was heterogeneity in finer air cell septations. Performance varied based on pathology studied, with the highest limitation observed in evaluating meningiomas with intratumoral calcifications or calvarial invasion. CONCLUSIONS: The generation of high-resolution CT scans from MR images through cGAN offers promise for a wide range of applications in cranial and spinal neurosurgery, especially as an adjunct for preoperative evaluation. Optimizing cGAN performance on specific anatomical regions may increase its clinical viability.

Contemporary Prognostic Signatures and Refined Risk Stratification of Gliomas: An Analysis of 4,400 Tumors.

BACKGROUND: With the significant shift in the classification, risk stratification, and standards of care for gliomas, we sought to understand how the overall survival of patients with these tumors is impacted by molecular features, clinical metrics, and treatment received. METHODS: We assembled a cohort of patients with a histopathologically diagnosed glioma from The Cancer Genome Atlas, Project Genomics Evidence Neoplasia Information Exchange, and Dana-Farber Cancer Institute/Brigham and Women's Hospital. This incorporated retrospective clinical, histological, and molecular data alongside prospective assessment of patient survival. RESULTS: 4,400 gliomas were identified: 2,195 glioblastoma, 1,198 IDH1/2-mutant astrocytoma, 531 oligodendroglioma, 271 other IDH1/2-wildtype glioma, and 205 pediatric-type glioma. Molecular classification updated 27.2% of gliomas from their original histopathologic diagnosis. Examining the distribution of molecular alterations across glioma subtypes revealed mutually exclusive alterations within tumorigenic pathways. Non-TCGA patients had significantly improved overall survival compared to TCGA patients, with 26.7%, 55.6%, and 127.8% longer survival for glioblastoma, IDH1/2-mutant astrocytoma, and oligodendroglioma respectively (all p<0.01). Several prognostic features were characterized, including NF1 alteration and 21q loss in glioblastoma, and EGFR amplification and 22q loss in IDH1/2-mutant astrocytoma. Leveraging the size of this cohort, nomograms were generated to assess the probability of overall survival based on patient age, the molecular features of a tumor, and the treatment received. CONCLUSIONS: By applying modern molecular criteria, we characterize the genomic diversity across glioma subtypes, identify clinically applicable prognostic features, and provide a contemporary update on patient survival to serve as a reference for ongoing investigations.

Application of radiomics to meningiomas: A systematic review.

BACKGROUND: Quantitative imaging analysis through radiomics is a powerful technology to non-invasively assess molecular correlates and guide clinical decision-making. There has been growing interest in image-based phenotyping for meningiomas given the complexities in management. METHODS: We systematically reviewed meningioma radiomics analyses published in PubMed, Embase, and Web of Science until December 20, 2021. We compiled performance data and assessed publication quality using the radiomics quality score (RQS). RESULTS: A total of 170 publications were grouped into 5 categories of radiomics applications to meningiomas: Tumor detection and segmentation (21%), classification across neurologic diseases (54%), grading (14%), feature correlation (3%), and prognostication (8%). A majority focused on technical model development (73%) versus clinical applications (27%), with increasing adoption of deep learning. Studies utilized either private institutional (50%) or public (49%) datasets, with only 68% using a validation dataset. For detection and segmentation, radiomic models had a mean accuracy of 93.1 ± 8.1% and a dice coefficient of 88.8 ± 7.9%. Meningioma classification had a mean accuracy of 95.2 ± 4.0%. Tumor grading had a mean area-under-the-curve (AUC) of 0.85 ± 0.08. Correlation with meningioma biological features had a mean AUC of 0.89 ± 0.07. Prognostication of the clinical course had a mean AUC of 0.83 ± 0.08. While clinical studies had a higher mean RQS compared to technical studies, quality was low overall with a mean RQS of 6.7 ± 5.9 (possible range -8 to 36). CONCLUSIONS: There has been global growth in meningioma radiomics, driven by data accessibility and novel computational methodology. Translatability toward complex tasks such as prognostication requires studies that improve quality, develop comprehensive patient datasets, and engage in prospective trials.

Impact of H3K27 trimethylation loss in meningiomas: a meta-analysis.

Trimethylation of lysine 27 on histone 3 (H3K27me3) loss has been implicated in worse prognoses for patients with meningiomas. However, there have been challenges in measuring H3K27me3 loss, quantifying its impact, and interpreting its clinical utility. We conducted a systematic review across Pubmed, Embase, and Web of Science to identify studies examining H3K27me3 loss in meningioma. Clinical, histopathological, and immunohistochemistry (IHC) characteristics were aggregated. A meta-analysis was performed using a random-effects model to assess prevalence of H3K27me3 loss and meningioma recurrence risk. Study bias was characterized using the NIH Quality Assessment Tool and funnel plots. Nine publications met inclusion criteria with a total of 2376 meningioma cases. The prevalence of H3K27me3 loss was 16% (95% CI 0.09-0.27), with higher grade tumors associated with a significantly greater proportion of loss. H3K27me3 loss was more common in patients who were male, had recurrent meningiomas, or required adjuvant radiation therapy. Patients were 1.70 times more likely to have tumor recurrence with H3K27me3 loss (95% CI 1.35-2.15). The prevalence of H3K27me3 loss in WHO grade 2 and 3 meningiomas was found to be significantly greater in tissue samples less than five years old versus tissue of all ages and when a broader definition of IHC staining loss was applied. This analysis demonstrates that H3K27me3 loss significantly associates with more aggressive meningiomas. While differences in IHC and tumor tissue age have led to heterogeneity in studying H3K27me3 loss, a robust prognostic signal is present. Our findings suggest an opportunity to improve study design and standardize tissue processing to optimize clinical viability of this epigenetic marker.

Advances and Evolving Challenges in Spinal Deformity Surgery.

BACKGROUND: Surgical intervention is a critical tool to address adult spinal deformity (ASD). Given the evolution of spinal surgical techniques, we sought to characterize developments in ASD correction and barriers impacting clinical outcomes. METHODS: We conducted a literature review utilizing PubMed, Embase, Web of Science, and Google Scholar to examine advances in ASD surgical correction and ongoing challenges from patient and clinician perspectives. ASD procedures were examined across pre-, intra-, and post-operative phases. RESULTS: Several factors influence the effectiveness of ASD correction. Standardized radiographic parameters and three-dimensional modeling have been used to guide operative planning. Complex minimally invasive procedures, targeted corrections, and staged procedures can tailor surgical approaches while minimizing operative time. Further, improvements in osteotomy technique, intraoperative navigation, and enhanced hardware have increased patient safety. However, challenges remain. Variability in patient selection and deformity undercorrection have resulted in heterogenous clinical responses. Surgical complications, including blood loss, infection, hardware failure, proximal junction kyphosis/failure, and pseudarthroses, pose barriers. Although minimally invasive approaches are being utilized more often, clinical validation is needed. CONCLUSIONS: The growing prevalence of ASD requires surgical solutions that can lead to sustained symptom resolution. Leveraging computational and imaging advances will be necessary as we seek to provide comprehensive treatment plans for patients.

Integration of Veterans Affairs Medical Centers Into Neurosurgical Residency Programs.

Veterans Affairs (VA) medical centers serve as a unique training environment for US residency programs. In this study, we aim to explore the scope and details of VA integration into neurosurgery resident training. We used data from the Accreditation Council for Graduate Medical Education database to provide an overview of neurosurgery training programs with an active VA affiliation and developed a multi-institutional survey to gather information related to rotation design, operative volume, expectations, and core training values. Of the 116 neurosurgery residency programs, 40 have an active affiliation with a VA medical center (34%). Residents most frequently rotated at the VA during their third postgraduate year, with an average rotation length of 7.5 months (range 2-21). Nearly all programs reported a weekly mix of clinic and operative days (96%), with residents longitudinally following patients throughout their rotations. Attending neurosurgeons from VA-affiliated programs reported operative experience (100%), independent decision-making (89%), and continuity of care (81%) as core values of VA neurosurgery rotations. Surgical volume varied between programs with an average of 13.4 ± 6.4 (SD) cases per month per rotating resident. A significant portion of neurosurgery residency programs in the United States incorporate VA rotations into resident training. Although rotation details vary from program-to-program, shared values include a strong operative experience, independent decision-making, and continuity of care. This analysis provides a comprehensive assessment of VA rotation structure across the country, which is valuable for programs considering implementing a VA rotation into their training program or modifying an existing rotation.

Machine Learning in the Classification of Pediatric Posterior Fossa Tumors: A Systematic Review.

Background: Posterior fossa tumors (PFTs) are a morbid group of central nervous system tumors that most often present in childhood. While early diagnosis is critical to drive appropriate treatment, definitive diagnosis is currently only achievable through invasive tissue collection and histopathological analyses. Machine learning has been investigated as an alternative means of diagnosis. In this systematic review and meta-analysis, we evaluated the primary literature to identify all machine learning algorithms developed to classify and diagnose pediatric PFTs using imaging or molecular data. Methods: Of the 433 primary papers identified in PubMed, EMBASE, and Web of Science, 25 ultimately met the inclusion criteria. The included papers were extracted for algorithm architecture, study parameters, performance, strengths, and limitations. Results: The algorithms exhibited variable performance based on sample size, classifier(s) used, and individual tumor types being investigated. Ependymoma, medulloblastoma, and pilocytic astrocytoma were the most studied tumors with algorithm accuracies ranging from 37.5% to 94.5%. A minority of studies compared the developed algorithm to a trained neuroradiologist, with three imaging-based algorithms yielding superior performance. Common algorithm and study limitations included small sample sizes, uneven representation of individual tumor types, inconsistent performance reporting, and a lack of application in the clinical environment. Conclusions: Artificial intelligence has the potential to improve the speed and accuracy of diagnosis in this field if the right algorithm is applied to the right scenario. Work is needed to standardize outcome reporting and facilitate additional trials to allow for clinical uptake.