Implications of Large Language Models for Quality and Efficiency of Neurologic Care: Emerging Issues in Neurology.

Large language models (LLMs) are advanced artificial intelligence (AI) systems that excel in recognizing and generating human-like language, possibly serving as valuable tools for neurology-related information tasks. Although LLMs have shown remarkable potential in various areas, their performance in the dynamic environment of daily clinical practice remains uncertain. This article outlines multiple limitations and challenges of using LLMs in clinical settings that need to be addressed, including limited clinical reasoning, variable reliability and accuracy, reproducibility bias, self-serving bias, sponsorship bias, and potential for exacerbating health care disparities. These challenges are further compounded by practical business considerations and infrastructure requirements, including associated costs. To overcome these hurdles and harness the potential of LLMs effectively, this article includes considerations for health care organizations, researchers, and neurologists contemplating the use of LLMs in clinical practice. It is essential for health care organizations to cultivate a culture that welcomes AI solutions and aligns them seamlessly with health care operations. Clear objectives and business plans should guide the selection of AI solutions, ensuring they meet organizational needs and budget considerations. Engaging both clinical and nonclinical stakeholders can help secure necessary resources, foster trust, and ensure the long-term sustainability of AI implementations. Testing, validation, training, and ongoing monitoring are pivotal for successful integration. For neurologists, safeguarding patient data privacy is paramount. Seeking guidance from institutional information technology resources for informed, compliant decisions, and remaining vigilant against biases in LLM outputs are essential practices in responsible and unbiased utilization of AI tools. In research, obtaining institutional review board approval is crucial when dealing with patient data, even if deidentified, to ensure ethical use. Compliance with established guidelines like SPIRIT-AI, MI-CLAIM, and CONSORT-AI is necessary to maintain consistency and mitigate biases in AI research. In summary, the integration of LLMs into clinical neurology offers immense promise while presenting formidable challenges. Awareness of these considerations is vital for harnessing the potential of AI in neurologic care effectively and enhancing patient care quality and safety. The article serves as a guide for health care organizations, researchers, and neurologists navigating this transformative landscape.

Teratogenesis, Perinatal, and Neurodevelopmental Outcomes After In Utero Exposure to Antiseizure Medication: Practice Guideline From the AAN, AES, and SMFM.

This practice guideline provides updated evidence-based conclusions and recommendations regarding the effects of antiseizure medications (ASMs) and folic acid supplementation on the prevalence of major congenital malformations (MCMs), adverse perinatal outcomes, and neurodevelopmental outcomes in children born to people with epilepsy of childbearing potential (PWECP). A multidisciplinary panel conducted a systematic review and developed practice recommendations following the process outlined in the 2017 edition of the American Academy of Neurology Clinical Practice Guideline Process Manual. The systematic review includes studies through August 2022. Recommendations are supported by structured rationales that integrate evidence from the systematic review, related evidence, principles of care, and inferences from evidence. The following are some of the major recommendations. When treating PWECP, clinicians should recommend ASMs and doses that optimize both seizure control and fetal outcomes should pregnancy occur, at the earliest possible opportunity preconceptionally. Clinicians must minimize the occurrence of convulsive seizures in PWECP during pregnancy to minimize potential risks to the birth parent and to the fetus. Once a PWECP is already pregnant, clinicians should exercise caution in attempting to remove or replace an ASM that is effective in controlling generalized tonic-clonic or focal-to-bilateral tonic-clonic seizures. Clinicians must consider using lamotrigine, levetiracetam, or oxcarbazepine in PWECP when appropriate based on the patient's epilepsy syndrome, likelihood of achieving seizure control, and comorbidities, to minimize the risk of MCMs. Clinicians must avoid the use of valproic acid in PWECP to minimize the risk of MCMs or neural tube defects (NTDs), if clinically feasible. Clinicians should avoid the use of valproic acid or topiramate in PWECP to minimize the risk of offspring being born small for gestational age, if clinically feasible. To reduce the risk of poor neurodevelopmental outcomes, including autism spectrum disorder and lower IQ, in children born to PWECP, clinicians must avoid the use of valproic acid in PWECP, if clinically feasible. Clinicians should prescribe at least 0.4 mg of folic acid supplementation daily preconceptionally and during pregnancy to any PWECP treated with an ASM to decrease the risk of NTDs and possibly improve neurodevelopmental outcomes in the offspring.