Machine learning and radiomics for ventricular tachyarrhythmia prediction in hypertrophic cardiomyopathy: insights from an MRI-based analysis.

BACKGROUND: Myocardial fibrosis is often detected in patients with hypertrophic cardiomyopathy (HCM), which causes left ventricular (LV) dysfunction and tachyarrhythmias. PURPOSE: To evaluate the potential value of a machine learning (ML) approach that uses radiomic features from late gadolinium enhancement (LGE) and cine images for the prediction of ventricular tachyarrhythmia (VT) in patients with HCM. MATERIAL AND METHODS: Hyperenhancing areas of LV myocardium on LGE images were manually segmented, and the segmentation was propagated to corresponding areas on cine images. Radiomic features were extracted using the PyRadiomics library. The least absolute shrinkage and selection operator (LASSO) method was employed for radiomic feature selection. Our model development employed the TabPFN algorithm, an adapted Prior-Data Fitted Network design. Model performance was evaluated graphically and numerically over five-repeat fivefold cross-validation. SHapley Additive exPlanations (SHAP) were employed to determine the relative importance of selected radiomic features. RESULTS: Our cohort consisted of 60 patients with HCM (73.3% male; median age = 51.5 years), among whom 17 had documented VT during the follow-up. A total of 1612 radiomic features were extracted for each patient. The LASSO algorithm led to a final selection of 18 radiomic features. The model achieved a mean area under the receiver operating characteristic curve of 0.877, demonstrating good discrimination, and a mean Brier score of 0.119, demonstrating good calibration. CONCLUSION: Radiomics-based ML models are promising for predicting VT in patients with HCM during the follow-up period. Developing predictive models as clinically useful decision-making tools may significantly improve risk assessment and prognosis.

Middle meningeal artery embolization versus conventional management for patients with chronic subdural hematoma: An umbrella review.

BACKGROUND AND OBJECTIVES: Conventional surgical modalities, including twist drill craniotomy, burr hole evacuation, and craniotomy, are the standard surgical interventions for chronic subdural hematomas (cSDH). More recently, treatment of cSDH with middle meningeal artery embolization (MMAE) is being explored. The comparative effectiveness of MMAE versus conventional surgical modalities remains controversial. The objective of this study is to analyze various postoperative outcomes in an umbrella review of existing meta-analysis comparing MMAE and conventional management in patients with cSDH. METHODS: A systematic literature search was executed with defined criteria across PubMed, Scopus, and Web of Science databases. Data was analyzed utilizing the metaumbrella R package, employing equivalent Hedges' g values. The quality assessment of each meta-analysis was carried out using AMSTAR2, assigning scores within the range of 0-11. The credibility of the evidence was determined by applying the Ioannidis criteria. RESULTS: This umbrella review study included five meta-analyses. Upon pooling the meta-analyses, MMAE was associated with fewer reoperations and recurrence, supported by a weak level of evidence (class IV). Conversely, findings related to other postoperative outcomes did not reach statistical significance. CONCLUSION: Our umbrella review offers a comprehensive summary investigating MMAE and conventional management for the treatment of cSDH. MMAE had fewer reoperations and recurrence, but they were classified as being of weak significance. These findings underscore insufficient evidence within the existing literature, emphasizing the imperative need for additional research in this area.

Intracranial ependymomas in pediatric patients: patterns of care, disparities, and survival outcomes from the National Cancer Database.

OBJECTIVE: This study aimed to extract and analyze comprehensive data from the National Cancer Database (NCDB) to gain insights into the epidemiological prevalence, treatment patterns, and survival outcomes associated with intracranial ependymomas in pediatric patients. METHODS: The authors examined data extracted from the NCDB spanning the years 2010 to 2017, with a specific emphasis on intracranial ependymomas in individuals aged 0-21 years. The study used logistic and Poisson regression, along with Kaplan-Meier survival estimates and Cox proportional hazards models, for analysis. RESULTS: Among 908 included pediatric patients, 495 (54.5%) were male, and 702 (80.6%) were White. Kaplan-Meier analysis determined overall survival (OS) rates of 97.1% (95% CI 96%-98.2%) at 1 year postdiagnosis, 89% (95% CI 86.9%-91.1%) at 3 years, 82.9% (95% CI 80.3%-85.7%) at 5 years, and 74.5% (95% CI 69.8%-79.4%) at 10 years. Grade 3 tumors predicted a more than fourfold higher mortality hazard (p < 0.001; reference = grade 2). Infratentorial localization was also associated with a 1.7-fold increase in mortality hazard (p = 0.002; reference = supratentorial). Larger maximum tumor size (> 5 cm) correlated with a lower mortality hazard (HR 0.64, p = 0.011; reference ≤ 5 cm). The vast majority of patients (85.9%, n = 780) underwent resection. Uninsured patients had over fourfold higher prolonged length of stay (LOS) odds than those privately insured (OR 4.645, p = 0.007). Radiotherapy was received by 76.1% of patients, and the highest rates of radiotherapy occurred among children aged 5-12 years (p < 0.001). Only 25.6% received chemotherapy at any point during their treatment. Peak chemotherapy use emerged within ages 0-4 years, reaching 33.6% in this age group. Kaplan-Meier analysis indicated chemotherapy was associated with significantly worse OS (p = 0.041). CONCLUSIONS: This comprehensive analysis of the NCDB provides valuable insights into the epidemiology, treatment patterns, and survival outcomes of intracranial ependymomas in pediatric patients. Higher tumor grade, infratentorial localization, and chemotherapy use was associated with worse OS, while larger tumor size correlated with lower mortality hazard. Disparities in care were identified, with uninsured patients experiencing prolonged LOS. These findings underscore the need for tailored treatment strategies based on patient and tumor characteristics and highlight the importance of addressing socioeconomic barriers to optimize outcomes for children with ependymomas.

A machine learning-based approach for individualized prediction of short-term outcomes after anterior cervical corpectomy.

STUDY DESIGN: A retrospective machine learning (ML) classification study for prognostic modeling after anterior cervical corpectomy (ACC). PURPOSE: To evaluate the effectiveness of ML in predicting ACC outcomes and develop an accessible, user-friendly tool for this purpose. OVERVIEW OF LITERATURE: Based on our literature review, no study has examined the capability of ML algorithms to predict major shortterm ACC outcomes, such as prolonged length of hospital stay (LOS), non-home discharge, and major complications. METHODS: The American College of Surgeons' National Surgical Quality Improvement Program database was used to identify patients who underwent ACC. Prolonged LOS, non-home discharges, and major complications were assessed as the outcomes of interest. ML models were developed with the TabPFN algorithm and integrated into an open-access website to predict these outcomes. RESULTS: The models for predicting prolonged LOS, non-home discharges, and major complications demonstrated mean areas under the receiver operating characteristic curve (AUROC) of 0.802, 0.816, and 0.702, respectively. These findings highlight the discriminatory capacities of the models: fair (AUROC >0.7) for differentiating patients with major complications from those without, and good (AUROC >0.8) for distinguishing between those with and without prolonged LOS and non-home discharges. According to the SHapley Additive Explanations analysis, single- versus multiple-level surgery, age, body mass index, preoperative hematocrit, and American Society of Anesthesiologists physical status repetitively emerged as the most important variables for each outcome. CONCLUSIONS: This study has considerably enhanced the prediction of postoperative results after ACC surgery by implementing advanced ML techniques. A major contribution is the creation of an accessible web application, highlighting the practical value of the developed models. Our findings imply that ML can serve as an invaluable supplementary tool to stratify patient risk for this procedure and can predict diverse postoperative adverse outcomes.

Exploring Pediatric Vertebral, Sacral, and Pelvic Osteosarcomas through the NCDB: Demographics, Treatment Utilization, and Survival Outcomes.

BACKGROUND AND OBJECTIVES: Retrieve data from the National Cancer Database (NCDB) to examine information on the epidemiological prevalence, treatment strategies, and survival outcomes of pediatric vertebral, sacral and pelvic osteosarcomas. METHODS: We reviewed NCDB data from 2008 to 2018, concentrating on vertebral, sacral, and pelvic osteosarcomas in children 0 to 21 years. Our analysis involved logistic and Poisson regression, Kaplan-Meier survival estimates, and Cox proportional hazards models. RESULTS: The study population included 207 patients. For vertebral osteosarcomas, 62.5% of patients were female, and 78.1% were white. Regional lymph node involvement predicted 80 times higher mortality hazard (p = 0.021). Distant metastasis predicted 25 times higher mortality hazard (p = 0.027). For sacral and pelvic osteosarcomas, 58.3% of patients were male, and 72% were white. Patients with residual tumor were 4 times more likely to have prolonged LOS (p = 0.031). No residual tumor (HR = 0.53, p = 0.03) and radiotherapy receipt (HR = 0.46, p = 0.034) were associated with lower mortality hazards. Distant metastasis predicted 3 times higher mortality hazard (p < 0.001). Hispanic ethnicity was linked to lower resection odds (OR = 0.342, p = 0.043), possibly due to language barriers affecting patient understanding and care decisions. CONCLUSIONS: In conclusion, our examination of NCDB offers a thorough exploration of demographics, treatment patterns, and results, highlighting the importance of personalized approaches to enhance patient outcomes.

Factors associated with substance use among preclinical medical students in Turkey: a cross-sectional study.

Introduction: Medical students experience high levels of stress due to their rigorous training, which can negatively affect their mental health. This study aimed to investigate substance use habits of medical students at Istanbul University-Cerrahpasa and the association on their mental health and demographic factors. Methods: This cross-sectional survey study was conducted in March-April 2022 among preclinical medical students (years 1-3 of a 6-year program). A confidential, anonymous online survey consisting of four sections on sociodemographic and educational characteristics, nicotine use and dependence [Fagerström Test for Nicotine Dependence (FTND)], alcohol use [Alcohol Use Disorders Identification Test (AUDIT)], mental health status [12-item General Health Questionnaire (GHQ-12)], was distributed to 1131 students via WhatsApp and Telegram text messages. Mann-Whitney U and Kruskal Wallis tests compared variables' distribution in the questionnaire categories. Spearman's correlation assessed associations between scales. Significance was p < 0.05. Results: The study included 190 medical students. A total of 26.3% of the participants were smokers, with 8.4% showing moderate to high levels of nicotine dependence. An estimated 45.8% and 8.4%reported low-risk consumption and risky usage of alcohol, respectively. There were statistically significant associations between substance use and demographic factors such as sex, GPA, and religious belief. The study found a statistically significant correlation between FTND scores and GHQ-12 scores, and, between FTND scores and AUDIT scores. Conclusion: The findings of this study will inform the development of interventions to improve the mental health and academic performance of medical students at Istanbul University-Cerrahpasa. Furthermore, it will raise awareness about the importance of addressing substance use among medical students in Turkey.

Introduction: Les étudiants en médecine sont assujettis à des niveaux élevés de stress en raison de leur formation rigoureuse, ce qui peut avoir un impact négatif sur leur santé mentale. Cette étude avait pour but d'étudier les habitudes de consommation de substances des étudiants en médecine de l'Université d'Istanbul-Cerrahpasa et l'association avec leur santé mentale et les facteurs démographiques. Méthodes: Cette étude transversale a été menée en mars-avril 2022 parmi les étudiants en médecine au pré-clinique (années 1 à 3 d'un programme de 6 ans). Un questionnaire en ligne confidentiel et anonyme comprenant quatre sections sur les caractéristiques sociodémographiques et éducatives, l'usage et la dépendance à la nicotine [Test de Fagerström pour la dépendance à la nicotine (FTND)], la consommation d'alcool [Test d'identification des troubles liés à la consommation d'alcool (AUDIT)], l'état de santé mentale [Questionnaire général sur la santé en 12 points (GHQ-12)], a été distribué à 1131 étudiants au moyen de messages texte WhatsApp et Telegram. Les tests de Mann-Whitney U et de Kruskal Wallis ont comparé la distribution des variables dans les catégories du questionnaire. La corrélation de Spearman a évalué les associations entre les échelles. Le niveau de signification statistique était p<0,05. Résultats: L'étude a porté sur 190 étudiants en médecine. Au total, 26,3 % des participants étaient des fumeurs, dont 8,4 % présentaient des niveaux modérés à élevés de dépendance à la nicotine. On estime que 45,8 % et 8,4 % des participants ont déclaré une consommation d'alcool à faible risque et une consommation d'alcool à risque, respectivement. Des associations statistiquement significatives ont été observées entre la consommation de substances et des facteurs démographiques tels que le sexe, la moyenne générale et les croyances religieuses. L'étude a mis en évidence une corrélation statistiquement significative entre les scores FTND et les scores GHQ-12, ainsi qu'entre les scores FTND et les scores AUDIT. Conclusion: Les résultats de cette étude permettront d'élaborer des interventions visant à améliorer la santé mentale et les résultats universitaires des étudiants en médecine de l'université d'Istanbul-Cerrahpasa. En outre, elle sensibilisera à l'importance de la prise en charge de l'utilisation de substances chez les étudiants en médecine en Turquie.

Atypical and anaplastic meningiomas in the later decades of life: A national cancer database analysis.

PURPOSE: We conducted a National Cancer Database (NCDB) study to investigate the epidemiological characteristics and identify predictors of outcomes associated with geriatric meningiomas. METHODS: The NCDB was queried for adults aged 60-89 years diagnosed between 2010 and 2017 with grade 2 and 3 meningiomas. The patients were classified into three age groups based on their age: 60-69 (hexagenarians), 70-79 (septuagenarians), and 80-89 (octogenarians). The log-rank test was utilized to compare the differences in overall survival (OS). Univariate and multivariate Cox proportional hazards regressions were used to evaluate the mortality risk associated with various patient and disease parameters. RESULTS: A total of 6585 patients were identified. Hexagenerians were the most common age group (49.8%), with the majority of meningiomas being classified as grade 2 (89.5%). The incidence of high-grade meningiomas increased in all age groups during the study period. Advanced age, male sex, black race, lower socioeconomic status, Charlson-Deyo score ≥ 2, and higher tumor grade were independent factors of poor survival. Among the modes of treatment, the extent of surgical resection, adjuvant radiotherapy, and treatment at a noncommunity cancer program were linked with better outcomes. CONCLUSION: In geriatric patients with high-grade meningiomas, the greater extent of surgical resection and radiotherapy are associated with improved survival. However, the management and outcome of geriatric patients with higher-grade meningiomas are also associated with several socioeconomic factors.

Optimal Timing in Cervical Spinal Cord Injury: A Comprehensive Meta-Analysis of Ultra-Early Surgical Intervention Within Five Hours.

The optimal timing of surgery for cervical spinal cord injuries (SCI) and its impact on neurological recovery continue to be subjects of debate. This systematic review and meta-analysis aims to consolidate and assess the existing evidence regarding the efficacy of ultra-early decompression surgery in improving clinical outcomes after cervical SCI. A search was conducted in PubMed, Embase, Cochrane, and CINAHL databases from inception until September 18, 2023, focusing on human studies. The groups were categorized into ultra-early decompression (decompression surgery ≤ 5 hours post-injury) and a control group (decompression surgery between 5-24 hours post-injury). A random effects meta-analysis was performed on all studies using R Studio. Outcomes were reported as effect size (OR, treatment effect, and 95% CI. Of the 140 patients, 63 (45%) underwent decompression ≤ 5 hours, while 77 (55%) underwent decompression > 5 hours post-injury. Analysis using the OR model showed no statistically significant difference in the odds of neurological improvement between the ultra-early group and the early group (OR = 1.33, 95% CI: 0.22-8.18, p = 0.761). This study did not observe significant neurological improvement among cervical SCI patients who underwent decompression within five hours. Due to the scarcity of literature on the ultra-early decompression of cervical SCI, this study underscores the necessity for additional investigation into the potential benefits of earlier interventions for cervical SCI to enhance patient outcomes.

Artificial intelligence/machine learning for neuroimaging to predict hemorrhagic transformation: Systematic review/meta-analysis.

BACKGROUND AND PURPOSE: Early and reliable prediction of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) is crucial for treatment decisions and early intervention. The purpose of this study was to conduct a systematic review and meta-analysis on the performance of artificial intelligence (AI) and machine learning (ML) models that utilize neuroimaging to predict HT. METHODS: A systematic search of PubMed, EMBASE, and Web of Science was conducted until February 19, 2024. Inclusion criteria were as follows: patients with AIS who received reperfusion therapy; AI/ML algorithm using imaging to predict HT; or presence of sufficient data on the predictive performance. Exclusion criteria were as follows: articles with less than 20 patients; articles lacking algorithms that operate solely on images; or articles not detailing the algorithm used. The quality of eligible studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 and Checklist for Artificial Intelligence in Medical Imaging. Pooled sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated using a random-effects model, and a summary receiver operating characteristic curve was constructed using the Reitsma method. RESULTS: We identified six eligible studies, which included 1640 patients. Aside from an unclear risk of bias regarding flow and timing identified in two of the studies, all studies showed low risk of bias and applicability concerns in all categories. Pooled sensitivity, specificity, and DOR were .849, .878, and 45.598, respectively. CONCLUSION: AI/ML models can reliably predict the occurrence of HT in AIS patients. More prospective studies are needed for subgroup analyses and higher clinical certainty and usefulness.