{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T02:28:30Z","timestamp":1789698510056,"version":"4.0.1"},"reference-count":76,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>Large language models have the potential to transform neurology by augmenting diagnostic reasoning, streamlining documentation, and improving workflow efficiency. This Mini Review surveys emerging applications of large language models in Alzheimer\u2019s disease, Parkinson\u2019s disease, multiple sclerosis, and epilepsy, with emphasis on ambient documentation, multimodal data integration, and clinical decision support. Key barriers to adoption include bias, privacy, reliability, and regulatory alignment. Looking ahead, neurology-focused language models may develop greater fluency in biomedical ontologies and FHIR standards, improving data interoperability and supporting more seamless collaboration between clinicians and AI systems. Two future developments have the potential to be particularly impactful: (1) the integration of multi-omic and neuroimaging data with digital-twin simulations to advance precision neurology, and (2) broader adoption of ambient documentation and other language-model\u2013based efficiencies that could reduce administrative and cognitive burden. Ultimately, the clinical success of large language models will depend on continued progress in model robustness, ethical governance, and careful implementation.<\/jats:p>","DOI":"10.3389\/fdgth.2025.1732759","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T06:42:59Z","timestamp":1767681779000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Large language models for neurology: a mini review"],"prefix":"10.3389","volume":"7","author":[{"given":"Donald C.","family":"Wunsch III","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel B.","family":"Hier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e209497","DOI":"10.1212\/WNL.0000000000209497","article-title":"Implications of large language models for quality and efficiency of neurologic care: emerging issues in neurology","volume":"102","author":"Moura","year":"2024","journal-title":"Neurology"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2978","DOI":"10.1212\/WNL.0000000000210712","article-title":"Validating patient symptoms in the electronic health record with large language models for scalable tracking of symptoms in neuro-oncology (p3-11.004)","volume":"104","author":"Rhee","year":"2025","journal-title":"Neurology"},{"key":"B3","article-title":"Emergent abilities in large language models: a survey","author":"Berti","year":""},{"key":"B4","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1212\/WNL.0000000000207853","article-title":"Improving neurology clinical care with natural language processing tools","volume":"101","author":"Ge","year":"2023","journal-title":"Neurology"},{"key":"B5","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1212\/WNL.0000000000013200","article-title":"Artificial intelligence and the practice of neurology in 2035: the neurology future forecasting series","volume":"98","author":"Jones","year":"2022","journal-title":"Neurology"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e2346721","DOI":"10.1001\/jamanetworkopen.2023.46721","article-title":"Performance of large language models on a neurology board\u2013style examination","volume":"6","author":"Schubert","year":"2023","journal-title":"JAMA Netw Open"},{"key":"B7","doi-asserted-by":"publisher","first-page":"10785","DOI":"10.1038\/s41598-024-60405-y","article-title":"Evaluating the strengths and weaknesses of large language models in answering neurophysiology questions","volume":"14","author":"Shojaee-Mend","year":"2024","journal-title":"Sci Rep"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e56762","DOI":"10.2196\/56762","article-title":"Evaluating AI competence in specialized medicine: comparative analysis of chatgpt and neurologists in a neurology specialist examination in spain","volume":"10","author":"Ros-Arlanz\u00f3n","year":"2024","journal-title":"JMIR Med Educ"},{"key":"B9","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1152\/advan.00093.2024","article-title":"Claude, ChatGPT, Copilot, and gemini performance versus students in different topics of neuroscience","volume":"49","author":"Mavrych","year":"2025","journal-title":"Adv Physiol Educ"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2826","DOI":"10.1212\/WNL.0000000000204763","article-title":"Large language model performance in neurology board questions (s33. 001)","volume":"102","author":"Shu","year":"2024","journal-title":"Neurology"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4605","DOI":"10.1007\/s10072-024-07580-y","article-title":"Evaluation of responses of the large language model GPT to the neurology question of the week","volume":"45","author":"Erdogan","year":"2024","journal-title":"Neurol Sci"},{"key":"B12","first-page":"10","article-title":"Chatgpt will take your neurology boards now: large-language models vs. humans on exams","volume":"24","author":"Fitzgerald","year":"2024","journal-title":"Neurol Today"},{"key":"B13","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1002\/ana.410280114","article-title":"The accuracy of bedside neurological diagnoses","volume":"28","author":"Chimowitz","year":"1990","journal-title":"Ann Neurol"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-95951-1","volume-title":"The Neurologic Diagnosis: A Practical Bedside Approach","author":"Alpert","year":"2019"},{"key":"B15","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1001\/jamaneurol.2013.2977","article-title":"Neurologists: the last bedside physician-scientists","volume":"70","author":"Berger","year":"2013","journal-title":"JAMA Neurol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e200293","DOI":"10.1212\/CPJ.0000000000200293","article-title":"GPT-4 performance for neurologic localization","volume":"14","author":"Lee","year":"2024","journal-title":"Neurol Clin Pract"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e73212","DOI":"10.2196\/73212","article-title":"Large language models in neurological practice: real-world study","volume":"27","author":"Maiorana","year":"2025","journal-title":"J Med Internet Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e0332196","DOI":"10.1371\/journal.pone.0332196","article-title":"Evaluating the diagnostic performance of openbioA in neurology: a case-based assessment of a medical large language model","volume":"20","author":"Habibi","year":"2025","journal-title":"PLoS One"},{"key":"B19","doi-asserted-by":"publisher","first-page":"347","DOI":"10.3390\/brainsci15040347","article-title":"Specialized large language model outperforms neurologists at complex diagnosis in blinded case-based evaluation","volume":"15","author":"Barrit","year":"2025","journal-title":"Brain Sci"},{"key":"B20","article-title":"SemioA: evaluating large language models for diagnostic reasoning from unstructured clinical narratives in epilepsy","author":"Dani","year":""},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1101\/2024.09.23.24314229","article-title":"Bridging language gaps in neurology patient education through large language models: a comparative analysis of chatgpt, gemini, and claude","author":"Haq","year":""},{"key":"B22","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1212\/WNL.0000000000208430","article-title":"Neurological history both twinned and queried by generative artificial intelligence (p1-2.006)","volume":"104","author":"Lee","year":"2025","journal-title":"Neurology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1703","DOI":"10.1212\/WNL.0000000000208693","article-title":"Enhancing physician efficiency with ambient artificial intelligence","volume":"104","author":"Chadehumbe","year":"2025","journal-title":"Neurology"},{"key":"B24","doi-asserted-by":"publisher","first-page":"12189880","DOI":"10.3390\/bioengineering12060631","article-title":"Large language models in healthcare and medical applications: a comprehensive review","volume":"3","author":"Johnsen","year":"2025","journal-title":"Front Digit Health"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1212\/WNL.0000000000207967","article-title":"Large language models in neurology research and future practice","volume":"101","author":"Romano","year":"2023","journal-title":"Neurology"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e67010","DOI":"10.2196\/67010","article-title":"Stroke diagnosis and prediction tool using ChatGLM: development and validation study","volume":"27","author":"Song","year":"2025","journal-title":"J Med Internet Res"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.12968\/hmed.2024.0666","article-title":"Large language models: a paradigm shift for dementia diagnosis and care","volume":"86","author":"Harrison","year":"2025","journal-title":"Br J Hosp Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6658","DOI":"10.3390\/s24206658","article-title":"Artificial general intelligence for the detection of neurodegenerative disorders","volume":"24","author":"Qadri","year":"2024","journal-title":"Sensors"},{"key":"B29","article-title":"An explainable diagnostic framework for neurodegenerative dementias via reinforcement-optimized a reasoning","author":"Zamai","year":""},{"key":"B30","doi-asserted-by":"publisher","first-page":"1638340","DOI":"10.3389\/fnagi.2025.1638340","article-title":"AI-driven precision diagnosis and treatment in Parkinson\u2019s disease: a comprehensive review and experimental analysis","volume":"17","author":"Twala","year":"2025","journal-title":"Front Aging Neurosci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1177\/13524585251333228","article-title":"Deconstructing complex diagnostic criteria and leveraging generative artificial intelligence to facilitate multiple sclerosis diagnosis","volume":"31","author":"Venkatesh","year":"2025","journal-title":"Mult Scler J"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e45412","DOI":"10.7759\/cureus.45412","article-title":"Artificial intelligence and multiple sclerosis: up-to-date review","volume":"15","author":"Naji","year":"2023","journal-title":"Cureus"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.1111\/epi.18322","article-title":"Can artificial intelligence diagnose seizures based on patients\u2019 descriptions? a study of GPT-4","volume":"66","author":"Ford","year":"2025","journal-title":"Epilepsia"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1101\/2024.05.26.24307955","article-title":"EpiSemoLLM: a fine-tuned large language model for epileptogenic zone localization based on seizure semiology with a performance comparable to epileptologists","author":"Yang","year":""},{"key":"B35","article-title":"Bias in large language models across clinical applications: a systematic review","author":"Suenghataiphorn","year":""},{"key":"B36","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1038\/s41746-025-01790-0","article-title":"Cognitive bias in clinical large language models","volume":"8","author":"Mahajan","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B37","doi-asserted-by":"publisher","first-page":"94071","DOI":"10.5662\/wjm.v14.i3.94071","article-title":"Ethical framework for artificial intelligence in healthcare research: a path to integrity","volume":"14","author":"Abujaber","year":"2024","journal-title":"World J Methodol"},{"key":"B38","first-page":"1","article-title":"Security and privacy challenges of large language models: a survey","volume":"57","author":"Das","year":"2025","journal-title":"ACM Comput Surv"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e200311","DOI":"10.1212\/CPJ.0000000000200311","article-title":"Exploring the potential of large language models in neurology, using neurologic localization as an example","volume":"14","author":"Chiang","year":"2024","journal-title":"Neurol Clin Pract"},{"key":"B40","doi-asserted-by":"publisher","first-page":"114","DOI":"10.4258\/hir.2025.31.2.114","article-title":"Large language models in medicine: clinical applications, technical challenges, and ethical considerations","volume":"31","author":"Jung","year":"2025","journal-title":"Healthc Inform Res"},{"key":"B41","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1038\/s43856-024-00717-2","article-title":"Current applications and challenges in large language models for patient care: a systematic review","volume":"5","author":"Busch","year":"2025","journal-title":"Commun Med"},{"key":"B42","doi-asserted-by":"publisher","first-page":"AIdbp2500120","DOI":"10.1056\/AIdbp2500120","article-title":"Assessment of large language models in clinical reasoning: a novel benchmarking study","volume":"2","author":"McCoy","year":"2025","journal-title":"NEJM AI"},{"key":"B43","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1038\/s41746-024-01083-y","article-title":"Evaluating large language models as agents in the clinic","volume":"7","author":"Mehandru","year":"2024","journal-title":"NPJ Digit Med"},{"key":"B44","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1001\/archneur.1985.04060060059010","article-title":"Interobserver variability in the assessment of neurologic history and examination in the stroke data bank","volume":"42","author":"Shinar","year":"1985","journal-title":"Arch Neurol"},{"key":"B45","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1038\/s41746-024-01098-5","article-title":"Navigating the us regulatory landscape for neurologic digital health technologies","volume":"7","author":"Busis","year":"2024","journal-title":"NPJ Digit Med"},{"key":"B46","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/s41746-025-01544-y","article-title":"Unregulated large language models produce medical device\u2013like output","volume":"8","author":"Weissman","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B47","article-title":"Artificial intelligence and machine learning in software as a medical device (SaMD)","year":""},{"key":"B48","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104946","article-title":"Scaling up biomedical vision-language models: fine-tuning, instruction tuning, and multi-modal learning","author":"Peng","year":""},{"key":"B49","article-title":"LLMs help alleviate the cross-subject variability in brain signal and language alignment","author":"Liu","year":""},{"key":"B50","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1212\/WNL.0000000000012570","article-title":"Guidelines for conducting ethical artificial intelligence research in neurology: a systematic approach for clinicians and researchers","volume":"97","author":"Chiang","year":"2021","journal-title":"Neurology"},{"key":"B51","doi-asserted-by":"publisher","first-page":"2792","DOI":"10.7150\/ijms.111780","article-title":"Large language models in medicine: applications, challenges, and future directions","volume":"22","author":"Yu","year":"2025","journal-title":"Int J Med Sci"},{"key":"B52","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1002\/ana.27225","article-title":"AI in neurology: everything, everywhere, all at once part 1: principles and practice","volume":"98","author":"Rizzo","year":"2025","journal-title":"Ann Neurol"},{"key":"B53","doi-asserted-by":"publisher","first-page":"e73212","DOI":"10.2196\/73212","article-title":"Large language models in neurological practice: real-world study","volume":"27","author":"Maiorana","year":"2025","journal-title":"J Med Internet Res"},{"key":"B54","doi-asserted-by":"publisher","first-page":"e0000877","DOI":"10.1371\/journal.pdig.0000877","article-title":"Retrieval-augmented generation for large language models in healthcare: a systematic review","volume":"4","author":"Wang","year":"2025","journal-title":"PLoS Digit Health"},{"key":"B55","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.emnlp-main.15","article-title":"Fine-tuning or retrieval? Comparing knowledge injection in LLMs","author":"Ovadia","year":""},{"key":"B56","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1038\/s41746-025-01963-x","article-title":"The evaluation illusion of large language models in medicine","volume":"8","author":"Agrawal","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B57","article-title":"Study suggests 60% of U.S. neurologists experiencing burnout","author":"Busis","year":""},{"key":"B58","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1212\/WNL.0000000000003640","article-title":"Burnout, career satisfaction, and well-being among U.S. neurologists in 2016","volume":"88","author":"Busis","year":"2017","journal-title":"Neurology"},{"key":"B59","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.1212\/WNL.0000000000004526","article-title":"Burnout in neurologists: a survey of us neurologists in 2016","volume":"89","author":"Miyasaki","year":"2017","journal-title":"Neurology"},{"key":"B60","doi-asserted-by":"publisher","first-page":"1063141","DOI":"10.3389\/fdgth.2022.1063141","article-title":"It\u2019s time to change our documentation philosophy: writing better neurology notes without the burnout","volume":"4","author":"Rodr\u00edguez-Fern\u00e1ndez","year":"2022","journal-title":"Front Digit Health"},{"key":"B61","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1016\/j.landig.2025.02.004","article-title":"Medical digital twins: enabling precision medicine and proactive care","volume":"7","author":"Sad\u00e9e","year":"2025","journal-title":"Lancet Digit Health"},{"key":"B62","doi-asserted-by":"publisher","first-page":"e72411","DOI":"10.2196\/72411","article-title":"Digital twins for personalized medicine require epidemiological data and mathematical modeling","volume":"27","author":"Vall\u00e9e","year":"2025","journal-title":"J Med Internet Res"},{"key":"B63","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/s41746-025-01897-4","article-title":"A consensus statement on the use of digital twins in medicine","volume":"8","author":"Iqbal","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B64","article-title":"Digital twin generators for disease modeling","year":""},{"key":"B65","article-title":"Medical digital twins: a new frontier in personalized healthcare","year":"2024"},{"key":"B66","article-title":"Combining large language models with digital twin simulations. (2024)","year":""},{"key":"B67","first-page":"1","article-title":"TWIN-GPT: digital twins for clinical trials via large language model","author":"Wang","year":"2024","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"B68","article-title":"As4ol 2025 overview: the second large language models for ontology learning challenge","author":"Giglou","year":""},{"key":"B69","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1093\/jamia\/ocaf165","article-title":"FHIR-former: enhancing clinical predictions through fast healthcare interoperability resources and large language models","volume":"32","author":"Engelke","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"B70","doi-asserted-by":"publisher","first-page":"446","DOI":"10.3390\/info16060446","article-title":"Preprocessing of physician notes by LLMs improves clinical concept extraction without information loss","volume":"16","author":"Hier","year":"2025","journal-title":"Information"},{"key":"B71","article-title":"Remote: a framework to create fast healthcare interoperability resources (fHIR) from unstructured clinical data","author":"Hier","year":""},{"key":"B72","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1001\/jama.2013.393","article-title":"The inevitable application of big data to health care","volume":"309","author":"Murdoch","year":"2013","journal-title":"JAMA"},{"key":"B73","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","year":"2018","journal-title":"J Biomed Inform"},{"key":"B74","doi-asserted-by":"publisher","first-page":"102900","DOI":"10.1016\/j.artmed.2024.102900","article-title":"Transformers and large language models in healthcare: a review","volume":"154","author":"Nerella","year":"2024","journal-title":"Artif Intell Med"},{"key":"B75","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1001\/jamaneurol.2025.0905","article-title":"General AI may revolutionize neurology\u2014or it might be bad","volume":"82","author":"Westover","year":"2025","journal-title":"JAMA Neurol"},{"key":"B76","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2025.findings-acl.254","article-title":"Re-task: revisiting LLM tasks from capability, skill, and knowledge perspectives","author":"Wang","year":""}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1732759\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T06:43:45Z","timestamp":1767681825000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2025.1732759\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":76,"alternative-id":["10.3389\/fdgth.2025.1732759"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2025.1732759","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]},"article-number":"1732759"}}