Large language models (LLMs) have transformative potential in neurology, impacting clinical decision-making, medical training, and research. Prompt engineering, the strategic design of inputs to optimize LLM performance, is essential for neurologists and trainees seeking to effectively integrate these powerful tools into practice. Carefully crafted prompts enable LLMs to summarize complex patient narratives, generate differential diagnoses, and support patient education. In training, structured prompts enhance diagnostic reasoning, board preparation, and interactive case-based learning. Neurological research also benefits, with LLMs aiding in data extraction, computed phenotype generation, and literature synthesis. Despite their promise, challenges remain, including hallucinations, data bias, privacy concerns, and regulatory complexities. This review synthesizes current advances and highlights best practices, including two structured prompt engineering frameworks tailored to neurology: Role-Task-Format (RTF) for routine use and our newly developed BRAIN (Background, Role, Aim, Instructions, Next steps) for complex tasks. We offer practical guidance to maximize accuracy, safety, and equity in LLM outputs, ensuring reliable support for neurologists and trainees.

Persistent symptoms after concussion (PSaC) and functional neurological disorder (FND) are frequently encountered in clinical practice and are often challenging to manage due to heterogeneous and polysymptomatic presentations, as well as fragmented care pathways. This review outlines key points of intersection between PSaC and FND across pathophysiology, illness beliefs, rehabilitation models, and emerging treatments. We describe when FND should be considered in the differential diagnosis of patients with PSaC, and provide guidance on history-taking, examination, diagnostic communication, and rehabilitation planning that can be applied to both conditions. We also examine the influence of expectations, clinical messaging, and interactions with the healthcare system on recovery. Integrating principles from FND into concussion care may help clinicians more accurately formulate cases and support individualized rehabilitation pathways.

Artificial intelligence (AI) in multiple sclerosis (MS) is an area of growing importance of growing importance. We review the historical context, current applications, and future prospects of AI and machine learning (ML) in MS. The review highlights AI's potential to address critical challenges in MS management, including early and accurate diagnosis, individualized treatment strategies, prognostication, and efficient patient monitoring. By leveraging large datasets and high-dimensional data, AI promises profound insights and augments clinical decision-making processes. Additionally, the manuscript covers potential limitations and challenges facing AI use in MS clinical practice and research.

The skull base and cranial nerves are of high neurological interest. Although the anatomy is complex, a clinicoradiologic approach using modern neuroimaging informed by history taking and physical examination can be employed to elucidate many problems in skull base neurology. This review illustrates diagnostic principles and pearls in skull base medicine with illustrative case vignettes.

Carotid artery atherosclerosis is an important etiology of carotid artery stenosis and subsequent cerebrovascular events. Carotid atherosclerosis follows a pattern that begins with endothelial dysfunction, marked by impaired nitric oxide-mediated vasodilation and increased endothelial permeability, and is followed by intimal low-density lipoprotein (LDL) accumulation. Retained oxidized LDL results in a pro-inflammatory environment that results in inflammatory cell inflammation and foam cell formation, the basis of the fatty streak. Migrating medial vascular smooth muscle cells, which undergo phenotypic switching, lead to plaque growth and fibrous cap formation. The unique geometry of the carotid bifurcation contributes to the complex local hemodynamic environment and predisposes the carotid bifurcation to endothelial dysfunction. In later stages of atherosclerosis, higher wall shear stress erodes the fibrous cap and increases the risk of plaque rupture. Several parameters of carotid bifurcation geometry, including the bifurcation angle and relative diameters of the internal and common carotid arteries, also contribute to disturbed flow and atherosclerotic plaque development.

Carotid webs are increasingly recognized as an underdiagnosed etiology of ischemic stroke, especially in young, otherwise healthy patients. These fibrous intimal protrusions create regions of flow stasis within the internal carotid artery, predisposing to thromboembolism. Diagnosis remains challenging due to their subtle radiographic appearance and underappreciation in clinical practice. While antiplatelet therapy or anticoagulation used to be the cornerstone of management, medical therapy alone has been found to be insufficient for stroke prevention in symptomatic patients. Definitive intervention includes carotid artery stenting or carotid endarterectomy; both have demonstrated excellent safety and efficacy. Risk stratification for symptomatic and asymptomatic carotid webs remains an area of active research, with emerging evidence suggesting that specific anatomic features, termed the carotid web angioarchitecture, may help predict stroke risk. Further studies are needed to determine the role of preventative intervention. A deeper understanding of carotid web pathogenesis, natural history, and hemodynamic impact is critical for guiding clinical decision-making.

As the U.S. population ages, Alzheimer's disease and related dementias (ADRD) cases are increasing, resulting in long wait times for specialist care. We review state-of-the-art artificial intelligence (AI) applications in ADRD care, from streamlining clinical diagnosis to pioneering novel digital biomarkers. Near-term AI applications include neuroimaging interpretation, conversational agents for patient interviews, and digital cognitive assessments. Large language models show promise as collaborative partners, helping clinicians interpret complex data while supporting patients and caregivers. Emerging digital biomarkers-speech analysis, passive monitoring through wearable devices, electronic health record analysis, and multiomics-offer potential for continuous monitoring to detect cognitive decline years before traditional assessments. Despite the acceleration of AI innovation, most of these systems are inaccessible in clinical practice. Implementation bottlenecks include limited external validation, technical challenges, model biases, infrastructure, and regulatory requirements. This review aims to help neurologists navigate this rapidly evolving AI landscape and prepare for implementation in ADRD care.

Cervical artery dissection is one of the leading causes of ischemic stroke in young adults, and poses unique diagnostic and therapeutic challenges due to an often nonspecific clinical presentation. Prompt recognition is essential, as early ischemic events are common within the first 2 to 4 weeks. This review summarizes current evidence on the epidemiology, pathophysiology, clinical features, diagnostic strategies, and management of cervical carotid artery dissections. While antithrombotic therapy is the mainstay of secondary stroke prevention, the optimal choice between antiplatelet and anticoagulation remains uncertain. Randomized trials and large cohort studies suggest similar efficacy between antiplatelet and anticoagulant therapies, though anticoagulation may confer benefit in patients with vessel occlusion. Recurrent dissection and ischemic events are rare, and dissecting aneurysms generally have a benign course. Endovascular intervention is reserved for select cases. A tailored, risk-based approach to therapy-guided by clinical and radiographic features-is essential to improve outcomes in this complex and heterogeneous population.

This review provides an overview of the emergence and application of transformer-based language models in electronic health records in neurology. Transformer architectures are well-suited for neurological data due to their ability to model complex spatiotemporal patterns and capture long-range dependencies, both characteristic of neurological conditions and their documentation. We introduce the foundational principles of transformer models and outline the model training and evaluation frameworks commonly used in clinical text processing. We then examine current applications of transformers in neurology, spanning disease detection and diagnosis, phenotyping and symptom extraction, and outcome and prognosis prediction, and synthesize emerging patterns in model adaptation and evaluation strategies. Additionally, we discuss the limitations of current models, including generalizability, model bias, and data privacy, and propose future directions for research and implementation. By synthesizing recent advances, this review aims to guide future efforts in leveraging transformer-based language models to improve neurological care and research.

Artificial intelligence (AI) is transforming neurology and stroke education through applications like automated feedback, adaptive simulations, and enhanced exposure to critical events. This narrative review explores foundational AI concepts, current educational uses in professional and patient training, virtual patients, tutoring tools, and personalized assessment. We evaluate the growing evidence for AI's effectiveness in improving knowledge, skills, and learner engagement, alongside implementation strategies. Key challenges include accuracy, bias, ethics, resource gaps, and potential skill decay. Conclusions emphasize that while AI shows promise for personalized learning and objective assessment, realizing its potential requires addressing barriers like cost-effectiveness, faculty readiness, and an evolving curriculum. Thoughtful integration requires rigorous validation, ethical standards, and further research into long-term outcomes. Ultimately, AI can complement traditional mentorship, preparing neurologists for data-driven practice.

The convergence of artificial intelligence (AI) and neuroscience represents one of medicine's most profound intellectual partnerships. Neuronal architecture has inspired computational methods, while computational models, evolving from theoretical constructs to transformative clinical tools, are reshaping neurological practice. As AI systems attempt to augment diagnostic accuracy, treatment planning, and patient care, neurologists must develop fluency in these technologies to harness their potential while navigating their limitations and dangers. AI-related publications have exponentially increased in recent years, yet many neurologists lack the foundational computer science background needed to critically evaluate and most safely and effectively implement these tools in clinical practice. This article serves to outline the historical foundations linking neuroscience to computing, examine core concepts of the past and current AI landscape in neurology, and describe methodologies that aim to revolutionize neurological care.

Brain tumors are a diverse group of neoplasms that vary widely in treatment and prognosis. Imaging serves as the cornerstone of diagnosis, monitoring response to treatment and identifying progression of disease in neuro-oncologic care. This review outlines current and emerging imaging modalities with a focus on clinical application in glioma, meningioma, and brain metastasis. We cover standard imaging modalities, advanced magnetic resonance techniques such as perfusion and spectroscopic imaging, and nuclear imaging with positron emission tomography (PET), including amino acid PET. We summarize the standardized Response Assessment in Neuro-Oncology (RANO) criteria, and explore innovations in radiomics, artificial intelligence, and targeted imaging biomarkers. Finally, we address challenges related to equitable access to advanced imaging. This review provides a practical, clinically focused guide to support neurologists in the imaging-based care of patients with primary or metastatic brain tumors.

Traumatic brain injury and traumatic spinal cord injury are major causes of morbidity and mortality, necessitating rapid and accurate diagnostic evaluation. Neuroimaging plays a critical role in the early assessment and management of these conditions, allowing for the timely identification of hemorrhagic lesions, cerebral edema, vascular injuries, and spinal cord pathology that may require urgent intervention. In this review, we use a time-based approach to appraise the role of imaging in the hyperacute (first 24 hours) and acute (up to 1 week) periods postinjury. Although computed tomography imaging guides most decision-making in trauma, we also highlight the role of ultrasound imaging modalities such as transcranial Doppler and optic nerve sheath diameter monitoring for noninvasive ICP monitoring, and magnetic resonance imaging for prognostication. Cases are used to highlight imaging findings that may change management in the hyperacute and acute period.

The administration of a Neurology training program requires dynamic leadership. Training programs will have many internal and external challenges. The ability to prepare for these challenges is variable. This paper reviews three cases: (1) The resident who is failing to meet competency in the program, (2) the impact of the growing Vascular Neurology workload, and (3) the impact of the coronavirus disease 2019 (COVID-19) pandemic on neurology training, and how these were handled within our system. The objective of this paper is to provide a road map for addressing these challenges by learning how to identify the problem, utilize available resources, and maximize communication.

Magnetic resonance imaging (MRI) remains an integral diagnostic tool in multiple sclerosis (MS), for both making the initial diagnosis and monitoring for disease relapse and progression. Despite the applied use of MRI according to the revised McDonald's criteria in 2017, there has been persistent low diagnostic specificity, especially as it pertains to differentiating radiologically isolated syndrome from alternative diagnoses that mimic demyelination. This report will provide an overview of recent paraclinical innovations, with a focus on MRI biomarkers and parameters such as the central vein and paramagnetic rim signs. Utilizing these tools in clinical practice will hopefully improve precision in the diagnosis and monitoring of MS and reduce the risk of false-positive diagnoses.