Objective Seizure frequency and seizure freedom are among the most important outcome measures for patients with epilepsy. In this study, we aimed to automatically extract this clinical information from unstructured text in clinical notes. If successful, this could improve clinical decision-making in epilepsy patients and allow for rapid, large-scale retrospective research. Materials and Methods We developed a finetuning pipeline for pretrained neural models to classify patients as being seizure-free and to extract text containing their seizure frequency and date of last seizure from clinical notes. We annotated 1000 notes for use as training and testing data and determined how well 3 pretrained neural models, BERT, RoBERTa, and Bio_ClinicalBERT, could identify and extract the desired information after finetuning. Results The finetuned models (BERTFT, Bio_ClinicalBERTFT, and RoBERTaFT) achieved near-human performance when classifying patients as seizure free, with BERTFT and Bio_ClinicalBERTFT achieving accuracy scores over 80%. All 3 models also achieved human performance when extracting seizure frequency and date of last seizure, with overall F1 scores over 0.80. The best combination of models was Bio_ClinicalBERTFT for classification, and RoBERTaFT for text extraction. Most of the gains in performance due to finetuning required roughly 70 annotated notes. Discussion and Conclusion Our novel machine reading approach to extracting important clinical outcomes performed at or near human performance on several tasks. This approach opens new possibilities to support clinical practice and conduct large-scale retrospective clinical research. Future studies can use our finetuning pipeline with minimal training annotations to answer new clinical questions.
Three decades of studies have shown that inhibition of thesubstantia nigra pars reticulata(SNpr) attenuates seizures, yet the circuits mediating this effect remain obscure. SNpr projects to the deep and intermediate layers of the superior colliculus (DLSC) and the pedunculopontine nucleus (PPN), but the contributions of these projections are unknown. To address this gap, we optogenetically silenced cell bodies within SNpr, nigrotectal terminals within DLSC, and nigrotegmental terminals within PPN. Inhibition of cell bodies in SNpr suppressed generalized seizures evoked by pentylenetetrazole (PTZ), partial seizures evoked from the forebrain, absence seizures evoked by gamma-butyrolactone (GBL), and audiogenic seizures in genetically epilepsy-prone rats. Strikingly, these effects were fully recapitulated by silencing nigrotectal projections. By contrast, silencing nigrotegmental terminals reduced only absence seizures and exacerbated seizures evoked by PTZ. These data underscore the broad-spectrum anticonvulsant efficacy of this circuit, and demonstrate that specific efferent projection pathways differentially control different seizure types.
Neurologic complications are occurring in coronavirus disease 2019 (COVID-19), and these patients should be monitored for neurologic symptoms. c When evaluating abnormal imaging findings in patients with COVID-19, the presence and specific pattern of deep gray structure involvement can be an important clue to etiology.
BackgroundThe ictal examination is crucial for neuroanatomic localization of seizure onset, which informs medical and neurosurgical treatment of epilepsy. Substantial variation exists in ictal examination performance in epilepsy monitoring units (EMUs). We developed and implemented a standardized examination to facilitate rapid, reliable execution of all testing domains and adherence to patient safety maneuvers.MethodsFollowing observation of examination performance, root cause analysis of barriers, and review of consensus guidelines, an ictal examination was developed and disseminated. In accordance with quality improvement methodology, revisions were enacted following the initial intervention, including differentiation between pathways for convulsive and nonconvulsive seizures. We evaluated ictal examination fidelity, efficiency, and EMU staff satisfaction before and after the intervention.ResultsWe identified barriers to ictal examination performance as confusion regarding ictal examination protocol, inadequate education of the rationale for the examination and its components, and lack of awareness of patient-specific goals. Over an 18-month period, 100 ictal examinations were reviewed, 50 convulsive and 50 nonconvulsive. Ictal examination performance varied during the study period without sustained improvement for convulsive or nonconvulsive seizure examination. The new examination was faster to perform (0.8 vs 1.5 minutes). Postintervention, EMU staff expressed satisfaction with the examination, but many still did not understand why certain components were performed.ConclusionWe identified key barriers to EMU ictal assessment and completed real-world testing of a standardized, streamlined ictal examination. We found it challenging to reliably change ictal examination performance in our EMU; further study of implementation is warranted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.