BACKGROUND AND OBJECTIVES: Chronic subdural hematoma (CSDH) presents significant management challenges in neurosurgical practice, with recurrence being a notable postoperative consideration. This study aimed to evaluate the Relative Cortical Atrophy (RCA) Index as a predictor of recurrence after CSDH surgery. METHODS: A retrospective analysis was conducted on 98 patients who underwent surgical evacuation for unilateral CSDH. The RCA Index was calculated using pre- and postoperative cranial imaging, correlating it with patient demographics, hematoma characteristics, and recurrence. Inter-rater reliability among measurements by 4 independent physicians was assessed using the intraclass correlation coefficient (ICC). Correlation and regression analyses were performed to identify the correlation of the RCA Index with other factors and their potential predicting power of CSDH recurrence, respectively. RESULTS: The study population had a mean age of 74.1 (11.9) years, with a 23.5% (23 patients) recurrence rate of CSDH. The ICC analysis showed excellent inter-rater reliability for RCA Index measurements (ICC: 0.998, 95% CI: 0.997-0.998, P < .001). A higher preoperative RCA Index was significantly associated with recurrence (0.215 [0.031] in the recurrent group vs 0.125 [0.034] in the nonrecurrent group, P < .001). The preoperative RCA Index highly correlated with the postoperative RCA Index (Pearson's correlation: 0.918, P < .001), and there was only a small (average: 0.005) but significant increase in the RCA Index of the unaffected hemisphere after surgery (P = .01).The preoperative RCA Index positively correlated with age, preoperative SDH thickness and volume, and recurrence. A RCA Index cutoff value of 0.165 predicted CSDH recurrence with high sensitivity (95.6%) and specificity (93.3%) (area under the curve = 0.97, 95% CI: 0.93-1). CONCLUSION: The RCA Index is a simple yet robust predictor of CSDH recurrence. Incorporating this measure into the preoperative assessment may enhance surgical planning and postoperative management, potentially reducing recurrence rates.

To evaluate the efficacy of perivascular sympathectomy in managing adventitia layer-related long-segment tubular stenosis of cervical segment (C1) internal carotid arteries (ICAs) in a cohort where conventional medical and endovascular interventions were not viable options, we retrospectively analyzed 20 patients (8 males, 12 females, aged 41–63 years) who underwent perivascular sympathectomy for long-segment (>5 cm) tubular cervical ICA stenosis (non-atherosclerotic, non-intima related, and nondolichoarteriopathic) between 2017 and 2023. The procedure aimed to alleviate symptoms such as hemiparesis, pulsatile tinnitus, and migraines associated with transient ischemic attacks (TIAs). Preoperative and postoperative symptoms were assessed, and patient follow-up was conducted by MR angiography and perfusion studies. Postoperatively, 10 out of 11 migraine sufferers (90.9%) reported complete cessation of symptoms, while one patient (9.09%) experienced reduction in frequency and intensity. In cases of tinnitus, six out of nine patients (66.6%) reported complete resolution, two (22.2%) had reduced symptoms, and one (11.1%) saw no change. Regarding motor function, all 12 patients (100%) with initial hemiparesis (30–40% loss of motor function) showed complete recovery postoperatively. There was no TIA attack among the patients after the procedure in the mean two-year follow-up. Perivascular sympathectomy has shown promising results in alleviating symptoms and preventing recurrent cerebrovascular events in long-segment tubular stenosis of cervical ICAs.

Background/Objective: Subarachnoid hemorrhage (SAH) is associated with high morbidity and mortality rates, necessitating prognostic algorithms to guide decisions. Our study evaluates the use of machine learning (ML) models for predicting 1-month and 1-year mortality among SAH patients using national electronic health records (EHR) system. Methods: Retrospective cohort of 29,274 SAH patients, identified through national EHR system from January 2017 to December 2022, was analyzed, with mortality data obtained from central civil registration system in Türkiye. Variables included (n = 102) pre- (n = 65) and post-admission (n = 37) data, such as patient demographics, clinical presentation, comorbidities, laboratory results, and complications. We employed logistic regression (LR), decision trees (DTs), random forests (RFs), and artificial neural networks (ANN). Model performance was evaluated using area under the curve (AUC), average precision, and accuracy. Feature significance analysis was conducted using LR. Results: The average age was 56.23 ± 16.45 years (47.8% female). The overall mortality rate was 22.8% at 1 month and 33.3% at 1 year. One-month mortality increased from 20.9% to 24.57% (p < 0.001), and 1-year mortality rose from 30.85% to 35.55% (p < 0.001) in the post-COVID period compared to the pre-COVID period. For 1-month mortality prediction, the ANN, LR, RF, and DT models achieved AUCs of 0.946, 0.942, 0.931, and 0.916, with accuracies of 0.905, 0.901, 0.893, and 0.885, respectively. For 1-year mortality, the AUCs were 0.941, 0.927, 0.926, and 0.907, with accuracies of 0.884, 0.875, 0.861, and 0.851, respectively. Key predictors of mortality included age, cardiopulmonary arrest, abnormal laboratory results (such as abnormal glucose and lactate levels) at presentation, and pre-existing comorbidities. Incorporating post-admission features (n = 37) alongside pre-admission features (n = 65) improved model performance for both 1-month and 1-year mortality predictions, with average AUC improvements of 0.093 ± 0.011 and 0.089 ± 0.012, respectively. Conclusions: Our study demonstrates the effectiveness of ML models in predicting mortality in SAH patients using big data. LR models’ robustness, interpretability, and feature significance analysis validate its importance. Including post-admission data significantly improved all models’ performances. Our results demonstrate the utility of big data analytics in population-level health outcomes studies.