Journal of Clinical Neuroscience最新文献

{"title":"Diagnostic accuracy of MRI without gadolinium for follow-up of pilocytic astrocytoma in the paediatric population","authors":"Macfarlane Adam Ian ,&nbsp;Soares Jewel Hannah ,&nbsp;Maharaj Monish","doi":"10.1016/j.jocn.2025.111173","DOIUrl":"10.1016/j.jocn.2025.111173","url":null,"abstract":"<div><h3>Purpose</h3><div>Pilocytic astrocytoma is the most common glial tumour in the paediatric population with a long-term life expectancy after surgery. Long-term radiological follow-up with magnetic resonance imaging (MRI) is necessary to detect recurrence of tumour or growth of residual tumour. Established MRI protocols typically dictate post-gadolinium sequences despite concerns around the side-effect and safety concerns of gadolinium-based contrast agents. This study aims to investigate whether omission of gadolinium-enhanced sequences for the long term follow-up MRI for paediatric patients with pilocytic astrocytoma, maintains diagnostic accuracy assessing potential recurrence or growth of residual tumour.</div></div><div><h3>Methods</h3><div>A retrospective review of follow-up MRI for 47 patients with histopathologically proven pilocytic astrocytoma was performed. Patients with optic pathway or suprasellar glioma were excluded from this study. All patients underwent surgery and had a minimum of 2 years of postoperative imaging for review. MRIs were chosen from most recent report of stability or at a time when growth/progression had been diagnosed. Two neuroradiologists and two paediatric neurosurgeons were randomly allocated a series of MRIs with gadolinium enhanced sequences removed, reviewers were blinded to the original report and subsequent treatment decisions. In addition, 30 paired MRI studies were randomly allocated to second review to test interobserver reliability. The reviewer responses were recorded and compared with the original report and analysed with respect to preserved diagnostic accuracy.</div></div><div><h3>Results</h3><div>170 MRI scans were subject to review across 66 episodes of care for 47 patients. 22.7 % of patients experienced growth of residual tumour during the period of follow-up. The sensitivity of non-enhanced MRI for detection of growth was 82 % (95 %CI 64.40–92.12) with a specificity of 97.10 % (95 % CI 90.03–99.20). Accuracy was similar for both neuroradiologists and neurosurgeons (91.49 % vs. 94 %). Interobserver reliability was calculated using Cohen’s Kappa co-efficient with a result of 0.792 showing substantial agreement. We also confirmed a statistically significant difference between gross total resection and sub-total resection and correlation with future growth (41 % vs. 0 %, n = 64, p = 0.001).</div></div><div><h3>Conclusion</h3><div>In paediatric patients who have undergone surgery for pilocytic astrocytoma, long term MRI follow-up without gadolinium-enhanced sequences maintains diagnostic accuracy compared with enhanced sequences. Omission of gadolinium-enhanced sequences may lead to decreased costs, duration of scans and anxiety around follow-up procedures.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111173"},"PeriodicalIF":1.9,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Anatomy of the sellar barrier: From magnetic resonance imaging to the operating room","authors":"Mauro Suárez ,&nbsp;Mario Gomar-Alba ,&nbsp;Juan F. Villalonga ,&nbsp;Paula Alonso ,&nbsp;Matías Baldoncini ,&nbsp;Alvaro Campero","doi":"10.1016/j.jocn.2025.111170","DOIUrl":"10.1016/j.jocn.2025.111170","url":null,"abstract":"<div><h3>Background</h3><div>The sellar barrier concept concerns the correlation between the components of the pituitary fossa roof and the risk of intraoperative cerebrospinal fluid (CSF) leak during pituitary tumor surgery. Our team previously classified the sellar barrier according to its thickness on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) sections into three subtypes: strong, mixed or weak.</div><div>The purpose of this study is to complement the preoperative analysis of the sellar barrier with T2-weighted MRI sections to enhance our knowledge of the anatomical configuration of the sellar barrier and its correlation with the intraoperative findings.</div></div><div><h3>Method</h3><div>A retrospective descriptive study was performed in which medical records, neuroimaging and surgical videos of patients undergoing endoscopic endonasal surgery for pituitary tumors from January 2021 to January 2024 were reviewed. In all cases, the anatomy of the sellar barrier was evaluated by an expert neuroradiologist using pre-surgical T1-weighted MRI with gadolinium and T2-weighted images with sagittal and coronal cuts. Subsequently, the anatomical structures of the sellar barrier were compared with the direct endoscopic view observed in the operating room.</div></div><div><h3>Results</h3><div>A total of 108 patients were included in this study. According to the preoperative neuroimaging findings, an experienced neuroradiologist classified the type of sellar barrier as strong, mixed or weak. Additionally, the T2-weighted imaging study was systematically implemented to identify the anatomical components of the sellar barrier. We found a high correlation between the preoperative neuroimaging description and the intraoperative endoscopic view of the sellar barrier. We present eight illustrative cases herein.</div></div><div><h3>Conclusions</h3><div>The use of T2-weighted sequences in conjunction with gadolinium-enhanced T1-weighted images enhances the preoperative knowledge of the sellar barrier by discriminating its anatomical components with high precision. As in any neurosurgical procedure, a detailed preoperative neuroimaging study and evaluation is highly recommended in order to offer the best possible treatment to our patients affected by pituitary tumors.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111170"},"PeriodicalIF":1.9,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Human-written vs. ChatGPT-generated manuscripts: Suggestions for further consideration.","authors":"Shigeki Matsubara","doi":"10.1016/j.jocn.2025.111172","DOIUrl":"https://doi.org/10.1016/j.jocn.2025.111172","url":null,"abstract":"","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":" ","pages":"111172"},"PeriodicalIF":1.9,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143615741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unplanned extubation prevention in the neuroscience ICU at a High Reliability Organization","authors":"Meagan Aladin ,&nbsp;Lauren Buckley ,&nbsp;Meghan Maloney ,&nbsp;Pimsiri Rojanaporn ,&nbsp;Theresa Gombar ,&nbsp;Ariane Lewis","doi":"10.1016/j.jocn.2025.111124","DOIUrl":"10.1016/j.jocn.2025.111124","url":null,"abstract":"<div><h3>Background</h3><div>Intubated neuroscience ICU patients are at risk for unplanned extubation (premature removal of the endotracheal tube by the patient or during patient care). The incidence of unplanned extubation is an indicator of the quality of ICU care. Unplanned extubation is a risk factor for pneumonia, increased ventilator days, the need for tracheostomy and increased ICU and hospital length-of-stay. After serial unplanned extubations, we introduced a multidisciplinary unit-based practice standard to reduce unplanned extubations as part of a quality improvement initiative in the neuroscience ICU in a large academic medical center at a High Reliability Organization in May 2021. The unit-based practice standard to guide care of intubated neuroscience ICU patients focused on communication, timely escalation of concerns, use of sedation/analgesia targeting RASS ≤ -1, soft wrist restraints (unless specified exclusion criteria met) and continuous observation for patients at high risk of agitation/restlessness. We sought to determine the impact of this initiative on the incidence of unplanned extubations.</div></div><div><h3>Method</h3><div>Unplanned extubations were identified via retrospective audit of prospective incident reports from our Patient Safety Incident registry pre-initiative (June 2020-May 2021) and prospective audit of incident reports post-initiative (July 2021-March 2024). Chart review facilitated collection of data on patient age, sex, diagnosis, intubation day, RASS goal, sedation/analgesia, restraints, constant observation, shift, and reintubation. The total number of intubated patients and ventilator days during these timeframes was identified retrospectively via an electronic medical record report of all patients on ventilators in the neuroscience ICU.</div></div><div><h3>Results</h3><div>During the pre-initiative audit period, there were 214 intubated patients (968 ventilator days). The audit identified 9 unplanned extubations (0.93/100 ventilator days; 8 males, median age 63-years-old (IQR 47–67)). There were 4 patients who were not ordered for sedation/analgesia or had a RASS goal of 0 and no patients were in nonviolent soft wrist restraints.</div><div>During the post-initiative audit period, there were 576 intubated patients (2,730 ventilator days). The audit identified 6 unplanned extubations (0.22/100 ventilator days; 6 males, median age 53-years-old (IQR 27–78)). All 6 patients had a RASS goal ≤ -1 and were in nonviolent soft wrist restraints.</div></div><div><h3>Conclusion</h3><div>This quality improvement initiative effectively reduced the incidence of unplanned extubations in our neuroscience ICU.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111124"},"PeriodicalIF":1.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579414","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Implementation of Integrated Patient-Reported outcome collection in outpatient cranial neurosurgical Practice: Results of qualitative interviews","authors":"Fatima Gauhar ,&nbsp;Gunther W. Wong ,&nbsp;Robert J. Dambrino ,&nbsp;Chloe D’Agostino ,&nbsp;Ashley Sellers ,&nbsp;Kemberlee R. Bonnet ,&nbsp;David G. Schlundt ,&nbsp;Justin M. Bachmann ,&nbsp;Reid C. Thompson ,&nbsp;Lola B. Chambless ,&nbsp;Peter J. Morone ,&nbsp;Patrick D. Kelly","doi":"10.1016/j.jocn.2025.111171","DOIUrl":"10.1016/j.jocn.2025.111171","url":null,"abstract":"<div><h3>Objective</h3><div>Patient Reported Outcome Measures (PROMs) quantify the patient’s quality of life and symptom burden. This study assesses the implementation of an automated PROM-capture system in an outpatient cranial neurosurgery clinic.</div></div><div><h3>Methods</h3><div>We conducted both quantitative and qualitative analyses of the implementation of a PROM tool in a single-center, dedicated brain tumor neurosurgery clinic. The primary measures were the PROMIS-10 and FACT-Br. The primary outcome of interest was PROM tool completion. For qualitative analysis, patients and providers were queried over a 6-month period to participate in a phone interview on their PROM tool experience.</div></div><div><h3>Results</h3><div>2,211 patients completed the PROM tool. The quantitative analysis found that white race (OR 1.42, 95% CI 1.21 – 1.68), being of non-Hispanic ethnicity (OR 1.20, 95% CI 1.06 – 1.37), or having private insurance (OR 1.28, 95% CI 1.08 – 1.53) were all associated with higher odds of PROM tool completion. Having an inactive patient portal – My Health At Vanderbilt (MHAV [OR 0.62, 95% CI 0.42 – 0.90]), or appointment providers were associated with decreased odds of PROM tool completion. In-person visits for new patients or for follow-up care were less likely to complete PROM tools as compared to telehealth. Fifteen patients and two providers participated in the phone interview, and the demographics of this group matched the overall cohort. Both patients and providers felt the PROM tool was pertinent, beneficial to patient care, and focused communication between the patient and provider.</div></div><div><h3>Conclusions</h3><div>This implementation study identified several barriers to developing an automated PROM-collection system in an outpatient cranial neurosurgery practice. These findings have been used to refine this system at our institution and may inform similar implementations elsewhere.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111171"},"PeriodicalIF":1.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Timely access to neurosurgical public care in Peru: A geospatial analysis","authors":"Jhon E. Bocanegra-Becerra","doi":"10.1016/j.jocn.2025.111143","DOIUrl":"10.1016/j.jocn.2025.111143","url":null,"abstract":"<div><h3>Introduction</h3><div>Understanding geographic access to neurosurgical care is key to ensuring timely treatment, particularly in countries with challenging topography like Peru. This investigation sought to estimate Peru’s population distribution within critical time intervals and proximity to the nearest neurosurgical facility in the Ministry of Health network.</div></div><div><h3>Methods</h3><div>A geospatial analysis was conducted to assess the distribution of Peru’s population across its 25 regions within six travel time areas (1 h, 2 h, 4 h, 6 h, 1 day, and 5 days) to the nearest neurosurgical facility.</div></div><div><h3>Results</h3><div>Twenty-five facilities were identified across Peru, of which 92 % pertained to tertiary or higher-level facilities and were included in the analysis. Peru’s population was estimated at 32,625,937 people. Lima concentrates 52.17 % of neurosurgical facilities. Nearly 13,819,251 people (42.36 %) could lack neurosurgical access within 4 h of travel. About 302,733 people (31.3 %) living in the region of Loreto could access neurosurgical treatment in up to 5 days of travel.</div></div><div><h3>Conclusion</h3><div>Geographic access to neurosurgical care in Peru is heterogeneous. Major hospital settings remain centralized in the regions of Lima and Callao. Virtually 42.36 % of the Peruvian population could not access timely neurosurgical care within 4 h of travel. Notably, roughly one-third of the population in the Amazon area of Loreto could access a neurosurgical setting in up to 5 days of travel. These findings can incentivize further assessment of underserved regions, prioritization of infrastructure development, and synergistic policy interventions from governmental and non-governmental organizations.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111143"},"PeriodicalIF":1.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Safety of Focused Ultrasound Ablation in Parkinson’s Disease: A Meta-Analysis of Randomized Controlled Trials","authors":"Abner Lucas Balduino de Souza ,&nbsp;Thaís Pereira Mendes ,&nbsp;Marco Antonnio Rocha dos Santos ,&nbsp;Pierludovico Moro ,&nbsp;Lauren Nirta ,&nbsp;Laura de Lima Xavier","doi":"10.1016/j.jocn.2025.111159","DOIUrl":"10.1016/j.jocn.2025.111159","url":null,"abstract":"<div><h3>Introduction</h3><div>Magnetic resonance-guided focused ultrasound (MRgFUS) is well-established for the treatment of essential tremor and is emerging as a promising non-incisional treatment for Parkinson’s disease (PD). However, its safety in this context is not well established.</div></div><div><h3>Methods</h3><div>We performed a systematic review and <em>meta</em>-analysis to evaluate the incidence of adverse events among patients with medication-refractory PD treated with MRgFUS. PubMed, Embase, Scopus, and Cochrane databases were searched from inception until December 2023. Included studies were peer-reviewed randomized controlled trials (RCTs) comparing MRgFUS to sham-procedures among patients with medication-refractory PD.</div></div><div><h3>Results</h3><div>Three RCTs comprising 161 patients (MRgFUS n = 115) were included. Dizziness was the most reported adverse event associated with MRgFUS (odds ratio [OR] 4.25; 95 % confidence interval [CI] 1.23–14.64; p = 0.02; I² = 0 %). Pin-site complications (OR 0.52; 95 % CI 0.23–1.20; I² = 0 %) and headache (OR 0.88; 95 % CI 0.19–4.16; I² = 48 %) were also notable. Ablation-related adverse events included gait disturbances (OR 4.53; 95 % CI 0.79–26.07; p = 0.09; I² = 0 %) and facial disturbances (OR 2.93; 95 % CI 0.49–17.51). No significant between-group differences were observed for life-threatening events (OR 1.76, 95 % CI 0.55–5.65; p = 0.35; I² = 0 %).</div></div><div><h3>Conclusion</h3><div>MRgFUS demonstrated a reasonable safety profile for the treatment of patients with medication-refractory PD. This promising safety profile, combined with its non-incisional nature, supports its potential as a valuable tool for managing refractory PD.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111159"},"PeriodicalIF":1.9,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143579401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of post-craniotomy headache management: A single-center retrospective study","authors":"Morgan E. Michas ,&nbsp;Eric G. Johnson ,&nbsp;Kathryn Ruf ,&nbsp;Amy Sheldrake ,&nbsp;Farhan A. Mirza ,&nbsp;Aric Schadler ,&nbsp;Aaron M. Cook","doi":"10.1016/j.jocn.2025.111160","DOIUrl":"10.1016/j.jocn.2025.111160","url":null,"abstract":"<div><h3>Background</h3><div>Post-craniotomy headache (PCH) pain is common among patients undergoing craniotomy and is associated with increased perioperative morbidity and mortality. It is often undertreated due to the various flaws in the agents used for PCH. The aim of this study was to describe the efficacy of current pain management practices for patients undergoing elective craniotomy.</div></div><div><h3>Methods</h3><div>This was a single center, retrospective study in adults undergoing elective craniotomy for neoplasm and epilepsy who had a post-operative length of stay of 48 h or greater. The primary objective of this study was to describe the efficacy of current pain management practices. Secondary objectives were to evaluate the relationship between pain control and hospital length of stay (LOS), to identify factors associated with uncontrolled pain, and to assess where in the post-operative course uncontrolled pain occurred.</div></div><div><h3>Results</h3><div>One hundred patients were included in the study, with 75 patients undergoing craniotomy for neoplasm excision and 25 for epilepsy procedures. Median pain scores were significantly higher on postoperative day (POD) 0 compared to POD 1 through 3 (P = 0.043), however there was no significant difference in maximum pain scores among post-operative days (P = 0.629). No correlation existed between LOS and maximum pain score (R = 0.065, P = 0.520). Thirty-three patients (33 %) experienced uncontrolled pain, most frequently occurring on POD 0 and 1. Female sex (P = 0.011), prior history of migraines (P = 0.014), younger age (P &lt; 0.001), and craniotomy for epilepsy procedures (P &lt; 0.001) were associated with uncontrolled pain.</div></div><div><h3>Conclusion</h3><div>PCH pain was well-controlled with current pain management practices, with the highest frequency of uncontrolled pain occurring on POD 0 and 1. Optimization of PCH pain management in patients with identified risk factors is warranted, and future studies evaluating PCH pain in larger, multicenter studies are needed.</div></div><div><h3>Previous presentations</h3><div>Great Lakes Pharmacy Conference, West Lafayette, Indiana – 4/29/2022 – preliminary results presented as a poster presentation.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111160"},"PeriodicalIF":1.9,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143562224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Hybrid radiomic Machine learning models for preoperative prediction of meningioma grade on multiparametric MRI","authors":"Steven Zhang ,&nbsp;Jesse Richter ,&nbsp;Jonathon Veale ,&nbsp;Vu Minh Hieu Phan ,&nbsp;Nick Candy ,&nbsp;Santosh Poonnoose ,&nbsp;Marc Agzarian ,&nbsp;Minh-Son To","doi":"10.1016/j.jocn.2025.111118","DOIUrl":"10.1016/j.jocn.2025.111118","url":null,"abstract":"<div><h3>Purpose</h3><div>To develop and compare machine learning models for distinguishing low and high grade meningiomas on multiparametric MRI. Methods: Pre-operative T1-weighted(T1), contrast-enhanced T1-weighted(T1CE), T2-weighted, T2 FLAIR, and DWI/ADC MRI sequences of meningiomas performed between 2000 and 2020 were retrospectively collected from a single tertiary hospital dedicated neurosurgical department. Tumours were manually segmented and handcrafted radiomic features were extracted. Deep learning features were extracted using a fine-tuned foundation model. Various oversampling techniques, feature selection algorithms and classifiers were trialled to build Handcrafted radiomics only (HRO) and handcrafted with deep learning radiomics (HDLR) models. Bootstrap was used for internal validation of model performance and calculating confidence intervals of metrices. Discrimination, calibration, feature importance and clinical utility of models were assessed via ROC AUC, calibration curve, Shapley values and decision curve analysis, respectively. Results: The analysis included 97 low grade and 18 high grade meningiomas. HRO and HDLR models had comparable diagnostic performance, using Random Forest and XGBoost respectively. They achieved mean (95 %CI): ROC AUC 0.825[0.662,0.952] and 0.794[0.662,0.948], specificity 0.913[0.793,0.952] and 0.892[0.796,0.983], sensitivity 0.499[0.204,1] and 0.509[0.225,0.851], NPV 0.909[0.851,0.971] and 0.909[0.851,0.972], and PPV 0.529[0.238,0.924] and 0.465[0.263,0.846], respectively for HRO and HDLR models. HRO and HDLR models selected 11–12 features, with T1 and T1CE having consistent importance. Conclusion: HRO and HDLR can effectively predict meningioma grades preoperatively. Challenges remain in achieving consistent sensitivity and PPV. Larger, multi-centre studies are warranted to confirm our findings, but it holds promise for improving personalized treatment strategies and patient outcomes in meningioma management. Code is available on Github <span><span>https://github.com/stephano41/radiomics_ai</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"135 ","pages":"Article 111118"},"PeriodicalIF":1.9,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI in neurosurgical education: Can machines learn to see like surgeons?","authors":"Ari Metalin Ika Puspita ,&nbsp;Mimin Ninawati ,&nbsp;Farida Istianah ,&nbsp;Agus Budi Santosa ,&nbsp;Bahrul Sri Rukmini ,&nbsp;Erfan Ramadhani","doi":"10.1016/j.jocn.2025.111153","DOIUrl":"10.1016/j.jocn.2025.111153","url":null,"abstract":"","PeriodicalId":15487,"journal":{"name":"Journal of Clinical Neuroscience","volume":"134 ","pages":"Article 111153"},"PeriodicalIF":1.9,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143556986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}