Reducing the percentage of surviving infants with acute symptomatic seizures discharged on anti-seizure medication.

OBJECTIVE: To evaluate the impact of inclusion of an anti-seizure medication (ASM) weaning protocol in a neonatal seizure pathway on the percent of infants discharged on ASMs. STUDY DESIGN: This cohort study included surviving infants with acute symptomatic seizures treated with ASMs across three institutions. We evaluated infants in 2 epochs, pre- and post-implementation of the ASM weaning protocol. The primary outcome was discharge on ASM. RESULTS: Of 116 included infants, the percent of infants discharged on ASMs was 69% in epoch 1 versus 34% in epoch 2 (p < 0.001). There was no significant difference between epochs in recurrence of seizures after discharge by 1 year of age (p = 0.125). There was an annual decrease in the percent of infants discharged on ASM across all institutions. CONCLUSION: Inclusion of a formal ASM weaning protocol as part of an institutional seizure pathway reduced percent of infants with acute symptomatic seizures discharged on ASM.

A model for teaching radiology to clinical specialty trainees: A pilot study in pediatric neuroradiology and neonatology.

This article describes the development and assessment of a neuroimaging curriculum for neonatology fellows. The curriculum is focused on topics that are relevant to the practice of neonatology and employs contemporary teaching methods, such as flipped classroom, learner engagement, and spaced repetition. Since its implementation 2018 the curriculum has been appreciated by our trainees and demonstrated improvements in trainee knowledge.

Current Evidence: Seizures in Extremely Low Gestational Age Newborns (ELGANs).

Extremely low gestational age newborns (ELGANs) are born at or below 28 weeks of gestational age. Despite improved obstetric care, the incidence of preterm birth continues to rise in advanced countries. Preterm birth remains a major cause of infant mortality, and for infants who survive, neonatal seizures are a significant predictor of later neurologic morbidity. However, little is known about risk factors for neonatal seizures in ELGANs. Understanding the association between neonatal seizures and the development of other neurologic disorders is important given the increasing prevalence of ELGANs. Identifying risk factors that contribute to the development of neonatal seizures in ELGANs may offer insights into novel mechanisms of epileptogenesis in the developing brain and improvements in the prevention or treatment of seizures in preterm infants, including ELGANs. In this literature review, we outline the limitations of epidemiologic studies of neonatal seizures in ELGANs and discuss risk factors for neonatal seizures.

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.