Background: Rapid differentiation between ischemic and hemorrhagic stroke is essential because management differs significantly. In settings without immediate neuroimaging, artificial intelligence (AI) may assist early decision-making. To evaluate the performance of AI in distinguishing ischemic from hemorrhagic stroke using history and physical examination alone. Methods: This retrospective, observational, case-control study included 54 adults (27 ischemic, 27 hemorrhagic) with neuroimaging-confirmed stroke in a tertiary hospital from January to June 2025. De-identified clinical data were entered into a structured AI prompt. AI predictions were compared with imaging diagnoses, and accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. Results: Ischemic stroke patients were slightly older than hemorrhagic cases; hypertension was the most frequent comorbidity. One-sided weakness was the most common presenting symptom, while headache occurred only in hemorrhagic stroke. Overall accuracy of Google Gemini 2.5 Pro was 66.7% (p = 0.0099). Sensitivity for ischemic stroke was 85.2%, specificity for hemorrhagic stroke was 48.1%, and PPV and NPV were 62.2% and 76.5%, respectively. Conclusion: AI demonstrated moderate diagnostic performance, with greater accuracy for ischemic than hemorrhagic stroke. AI may serve as an adjunct in resource-limited settings but should not replace neuroimaging. Larger studies and model refinement are recommended.
Perineuronal nets (PNNs) are specialized extracellular matrix structures that enwrap select neuronal populations—particularly, parvalbumin-positive inhibitory interneurons. Under physiological conditions, they stabilize synaptic connectivity, regulate excitatory– inhibitory balance, and contribute to the closure of developmental critical periods. Rather than being static scaffolds, PNNs dynamically regulate neuronal excitability, synaptic plasticity, and circuit maturation across the lifespan. Notably, accumulating evidence indicates that the disruption of these functions represents a cross-diagnostic mechanism underlying shared circuit vulnerabilities across multiple brain disorders. In autism spectrum disorder, schizophrenia, bipolar disorder, epilepsy, Alzheimer’s disease, amyotrophic lateral sclerosis, and substance use disorders, alterations in PNN density, composition, and remodeling are consistently associated with disrupted PV interneuron function, impaired network oscillations, and aberrant circuit stability. A central paradox thus emerges: excessive PNN stabilization may prematurely restrict plasticity during development, whereas pathological degradation or dysregulation in adulthood destabilizes mature circuits and increases vulnerability to excitotoxicity, neuroinflammation, and maladaptive memory persistence. These context-dependent effects highlight the translational potential of targeting PNNs to restore circuit balance. Together, these findings position PNNs as critical regulators of the balance between stability and adaptability in neural circuits and underscore their potential as translational targets for circuit-level therapeutic interventions.
Objective To characterize glymphaticu2010 and cerebrospinal fluid (CSF)u2010related imaging alterations in moderateu2010tou2010advanced, deep brain stimulation (DBS)u2010eligible Parkinsonu2019s disease (PD) using a multidimensional magnetic resonance imaging (MRI) framework. Methods We studied 60 moderateu2010tou2010advanced, DBSu2010eligible patients with PD and 30 frequencyu2010matched healthy controls with 3.0 T MRI. The u201CSourceu2010Dynamicsu2010Functionu2010Structureu201D framework integrated choroid plexus volume fraction, C1u2013C2 phaseu2010contrast MRI, diffusion tensor image analysis along the perivascular space index, and perivascular space volumetry. Multivariable analyses were used to examine associations between imaging biomarkers and motor severity, anxiety, and sleep quality. Results Patients with PD showed reduced diffusion tensor image analysis along the perivascular space index, a nominal increase in choroid plexus volume fraction, and a lowu2010netu2010flow CSF pattern with nominal evidence of increased reflux and marked spatial heterogeneity, despite preserved gross perivascular morphology. Ventral CSF dynamics showed significant partial correlations with motor severity, whereas selected dorsal flow metrics remained significantly associated with anxiety severity in covariateu2010adjusted regression analyses. The combined logistic model showed modest diagnostic performance (area under the curve = 0.686), with the highest area under the curve numerically but no statistically significant advantage over individual imaging metrics in paired DeLong comparisons. Conclusion This framework provides an exploratory neuroimaging reference for moderateu2010tou2010advanced, DBSu2010eligible PD and may support future validation studies and DBSu2010related investigations.
Background: Rathke’s cleft cysts (RCCs) are benign sellar and suprasellar lesions. Most are treated conservatively, while others require surgery, usually via a transsphenoidal intervention. However, long-term outcomes of surgical intervention remain challenged by the risk of cyst recurrence, which can manifest years after initial treatment. We aim to assess the long-term outcomes of RCCs and predictors of recurrence post endoscopic endonasal resection. Methods: We reviewed our database for the last 10 years (2014–2024). We included all the patients with Rathke’s Cleft Cysts who underwent Endoscopic Endonasal Transsphenoidal (EET) surgery. Demographic data, preoperative, intraoperative, postoperative clinical data and patients’ outcomes were retrospectively collected and analyzed. Results: Thirty RCC patients who underwent transsphenoidal surgery were included in this study. The mean age of our cohort was 54.6 years, and 59% were females. Four patients developed cerebrospinal fluid (CSF) leak postoperatively (13.33%), and four patients (13.33%) had permanent diabetes insipidus (DI). During follow-up, recurrence was observed in 16.67% (5 patients) with an average latency of 23 months. Only three patients were symptomatic and required re-operation. Conclusions: Following transsphenoidal surgery for Rathke’s cleft cysts, many patients experienced rapid improvement of symptoms. Moreover, recurrence is influenced by numerous factors requiring long-term follow-up. Future studies with larger sample sizes and longer follow-up durations are recommended.
