Effects of explainable artificial intelligence in neurology decision support.

OBJECTIVE: Artificial intelligence (AI)-based decision support systems (DSS) are utilized in medicine but underlying decision-making processes are usually unknown. Explainable AI (xAI) techniques provide insight into DSS, but little is known on how to design xAI for clinicians. Here we investigate the impact of various xAI techniques on a clinician's interaction with an AI-based DSS in decision-making tasks as compared to a general population. METHODS: We conducted a randomized, blinded study in which members of the Child Neurology Society and American Academy of Neurology were compared to a general population. Participants received recommendations from a DSS via a random assignment of an xAI intervention (decision tree, crowd sourced agreement, case-based reasoning, probability scores, counterfactual reasoning, feature importance, templated language, and no explanations). Primary outcomes included test performance and perceived explainability, trust, and social competence of the DSS. Secondary outcomes included compliance, understandability, and agreement per question. RESULTS: We had 81 neurology participants with 284 in the general population. Decision trees were perceived as the more explainable by the medical versus general population (P < 0.01) and as more explainable than probability scores within the medical population (P < 0.001). Increasing neurology experience and perceived explainability degraded performance (P = 0.0214). Performance was not predicted by xAI method but by perceived explainability. INTERPRETATION: xAI methods have different impacts on a medical versus general population; thus, xAI is not uniformly beneficial, and there is no one-size-fits-all approach. Further user-centered xAI research targeting clinicians and to develop personalized DSS for clinicians is needed.

COVID-19 and the Pandemic-Related Aspects in Pediatric Demyelinating Disorders.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), also known as Coronavirus-19 (COVID-19) infection, has been associated with several neurological symptoms, including acute demyelinating syndromes (ADS). There is a growing body of literature discussing COVID-19 and demyelinating conditions in adults; however, there is less published about COVID-19 demyelinating conditions in the pediatric population. This review aims to discuss the impact of COVID-19 in pediatric patients with central nervous system ADS (cADS) and chronic demyelinating conditions. We reviewed PubMed, Google Scholar, and Medline for articles published between December 1, 2019 and October 25, 2022 related to COVID-19 and pediatric demyelinating conditions. Of 56 articles reviewed, 20 cases of initial presentation of ADS associated with COVID-19 were described. The most commonly described cADS associated with COVID-19 infection in children was Acute Disseminated Encephalomyelitis followed by Transverse Myelitis. Cases of Myelin Oligodendrocyte Glycoprotein Antibody Disease, Neuromyelitis Optica Spectrum Disorder, and Multiple Sclerosis are also described. The risk of severe COVID-19 in pediatric patients with demyelinating conditions appears low, including in patients on disease modifying therapies, but studies are limited. The pandemic did affect disease modifying therapies in ADS, whether related to changes in prescriber practice or access to medications. COVID-19 is associated with ADS in children and the COVID-19 pandemic has impacted pediatric patients with demyelinating conditions in various ways.

Review of Machine Learning and Artificial Intelligence (ML/AI) for the Pediatric Neurologist.

Artificial intelligence (AI) and a popular branch of AI known as machine learning (ML) are increasingly being utilized in medicine and to inform medical research. This review provides an overview of AI and ML (AI/ML), including definitions of common terms. We discuss the history of AI and provide instances of how AI/ML can be applied to pediatric neurology. Examples include imaging in neuro-oncology, autism diagnosis, diagnosis from charts, epilepsy, cerebral palsy, and neonatal neurology. Topics such as supervised learning, unsupervised learning, and reinforcement learning are discussed.