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.

Background and Objectives: Idiopathic normal pressure hydrocephalus (iNPH) primarily affects older patients. Ventriculoperitoneal (VP) shunt surgery is a standard treatment. Many iNPH patients have high cardiovascular risks and require aspirin (ASA) therapy to prevent thromboembolic events. Discontinuing ASA increases the risk of these events. This study evaluates the impact of perioperative ASA use on hemorrhagic complications in iNPH patients undergoing VP shunt surgery. Methods: This retrospective cohort study included patients who underwent VP shunt surgery for iNPH from January 2020 to September 2024. Patients were divided into two groups based on perioperative ASA use: no ASA ( n = 50) and ASA continued ( n = 51). Data collected included demographics, surgery details, ASA dosage, and indications for ASA use. Primary outcomes were early and late postoperative hemorrhage incidences. Postoperative follow-up included MRI or CT scans at regular intervals (mean ≈ one year). Statistical analyses were performed using SPSS version 23.0, with Chi-square tests and independent samples t-tests or Mann–Whitney U tests used to analyze differences between groups. Results: The study cohort had 101 patients with a mean age of 69.5 ± 7.6 years, 41.6% female and 58.4% male. Early postoperative hemorrhage occurred in 5% of patients, including epidural (1), intraparenchymal(3), and intraventricular hematoma(1). Late postoperative hemorrhages occurred in 4% of patients ( 4 patients in the no-ASA group), with two cases each of unilateral and bilateral subdural hematoma. No significant differences in hemorrhagic outcomes were observed between the ASA continuation and non-use groups ( p = 0.092). The mean follow-up period was 300 days. One patient died in non-ASA group due to neurodegenerative disease. Conclusion: Perioperative ASA use does not significantly impact the incidence of postoperative hemorrhages in iNPH patients undergoing VP shunt surgery. These findings suggest that ASA can be safely continued without increasing hemorrhagic risks. This is a particularly significant issue for patients with high cardiovascular risk.

Background and Objectives: Chronic neck pain is a prevalent condition linked to functional disability and maladaptive pain-related behaviors. Although the physical and psychosocial impairments have been extensively studied in the literature, the factors related to cognitive impairments are not fully understood. This study aimed to examine the physical, psychosocial, and cognitive impairments associated with chronic neck pain and examine the variables associated with cognitive performance in this population. Materials and Methods: This cross-sectional study included 87 individuals with chronic neck pain. Pain sensitivity, neck disability, physical capacity, cervical muscle strength, pain catastrophizing, kinesiophobia, and self-reported central sensitization were assessed in all participants. Within the scope of the neuropsychological assessment, global cognition, processing speed, attention, and executive functioning were evaluated. The relationship between physical, psychosocial, and cognitive impairments was assessed using Spearman correlation. Additionally, a multiple linear regression analysis was performed to assess the extent to which the independent variables were associated with cognitive performance. Results: Global cognition was moderately correlated with pain intensity (r = −0.427, p < 0.001) and pain catastrophizing (r = −0.414, p < 0.001). Difficulties in response inhibition were moderately related to age (r = 0.440, p < 0.001). Cervical muscle strength (r = 0.384–0.233) and physical capacity (r = 0.332) were also weakly correlated with global cognition (p < 0.05). Age exhibited the strongest relationship with global cognition (β = −0.332, p < 0.001), followed by pain intensity (β = −0.291, p = 0.004) and pain sensitivity (β = 0.253, p = 0.011), with an explained variance of 30.8%. Additionally, age showed the strongest association with difficulties in processing speed (β = 0.448, p < 0.001), followed by kinesiophobia (β = 0.325, p = 0.001) and neck disability (β = 0.262, p = 0.030), with an explained variance of 34.2%. Conclusions: These findings suggest that increased nociceptive sensitization and deficits in physical health may be associated with maladaptive pain-related coping strategies in individuals with chronic neck pain. Furthermore, cognitive impairments in these individuals may reflect a multidimensional association of demographic, physical, psychosocial, and sensorial mechanisms.

Background: Hemifacial spasm (HFS) is most commonly caused by arterial compression at the root exit zone (REZ) of the facial nerve. In contrast, isolated venous compression in the absence of arterial involvement is uncommon, accounting for 0.4–5.5% of cases in surgical series, and poses diagnostic challenges due to the subtle appearance of venous structures on conventional neuroimaging. This rarity highlights the importance of recognizing pure venous neurovascular conflict as a distinct, albeit underdiagnosed, and etiology of HFS. Case Description: We report a 69-year-old woman with a 5-year history of refractory right-sided HFS. Although preoperative magnetic resonance imaging suggested possible arterial contact, retrosigmoid exploration revealed compression of the facial nerve REZ by a transverse pontine vein coursing along the middle cerebellar peduncle, with no arterial offender identified. Microvascular decompression was performed through careful mobilization and transposition of the offending vein using Teflon interposition. Intraoperative quantitative lateral spread response (LSR) monitoring showed marked attenuation of response amplitudes following decompression. The patient experienced immediate and complete resolution of symptoms postoperatively. Conclusion: This case illustrates that pure venous compression by a transverse pontine vein is a rare but surgically treatable cause of HFS that can be misinterpreted as arterial conflict on imaging. A successful outcome was achieved through meticulous intraoperative identification and vein-preserving decompression, combined with quantitative LSR monitoring, which proved valuable even without complete response disappearance. Thorough exposure of the REZ, including endoscopic inspection when indicated, remains important to identify such atypical neurovascular conflicts.