Automated Identification of Fall-related Injuries in Unstructured Clinical Notes.

Fall-related injuries (FRIs) are a major cause of hospitalizations among older patients, but identifying them in unstructured clinical notes poses challenges for large-scale research. In this study, we developed and evaluated Natural Language Processing (NLP) models to address this issue. We utilized all available clinical notes from the Mass General Brigham for 2,100 older adults, identifying 154,949 paragraphs of interest through automatic scanning for FRI-related keywords. Two clinical experts directly labeled 5,000 paragraphs to generate benchmark-standard labels, while 3,689 validated patterns were annotated, indirectly labeling 93,157 paragraphs as validated-standard labels. Five NLP models, including vanilla BERT, RoBERTa, Clinical-BERT, Distil-BERT, and SVM, were trained using 2,000 benchmark paragraphs and all validated paragraphs. BERT-based models were trained in three stages: Masked Language Modeling, General Boolean Question Answering (QA), and QA for FRI. For validation, 500 benchmark paragraphs were used, and the remaining 2,500 for testing. Performance metrics (precision, recall, F1 scores, Area Under ROC [AUROC] or Precision-Recall [AUPR] curves) were employed by comparison, with RoBERTa showing the best performance. Precision was 0.90 [0.88-0.91], recall [0.90-0.93], F1 score 0.90 [0.89-0.92], AUROC and AUPR curves of 0.96 [0.95-0.97]. These NLP models accurately identify FRIs from unstructured clinical notes, potentially enhancing clinical notes-based research efficiency.

Cerebrospinal fluid hypersecretion in pediatric hydrocephalus.

Hydrocephalus, despite its heterogeneous causes, is ultimately a disease of disordered CSF homeostasis that results in pathological expansion of the cerebral ventricles. Our current understanding of the pathophysiology of hydrocephalus is inadequate but evolving. Over this past century, the majority of hydrocephalus cases has been explained by functional or anatomical obstructions to bulk CSF flow. More recently, hydrodynamic models of hydrocephalus have emphasized the role of abnormal intracranial pulsations in disease pathogenesis. Here, the authors review the molecular mechanisms of CSF secretion by the choroid plexus epithelium, the most efficient and actively secreting epithelium in the human body, and provide experimental and clinical evidence for the role of increased CSF production in hydrocephalus. Although the choroid plexus epithelium might have only an indirect influence on the pathogenesis of many types of pediatric hydrocephalus, the ability to modify CSF secretion with drugs newer than acetazolamide or furosemide would be an invaluable component of future therapies to alleviate permanent shunt dependence. Investigation into the human genetics of developmental hydrocephalus and choroid plexus hyperplasia, and the molecular physiology of the ion channels and transporters responsible for CSF secretion, might yield novel targets that could be exploited for pharmacotherapeutic intervention.

Predictors of follow-up care for critically-ill patients with seizures and epileptiform abnormalities on EEG monitoring.

OBJECTIVE: Post-hospitalization follow-up visits are crucial for preventing long-term complications. Patients with electrographic epileptiform abnormalities (EA) including seizures and periodic and rhythmic patterns are especially in need of follow-up for long-term seizure risk stratification and medication management. We sought to identify predictors of follow-up. METHODS: This is a retrospective cohort study of all patients (age ≥ 18 years) admitted to intensive care units that underwent continuous EEG (cEEG) monitoring at a single center between 01/2016-12/2019. Patients with EAs were included. Clinical and demographic variables were recorded. Follow-up status was determined using visit records 6-month post discharge, and visits were stratified as outpatient follow-up, neurology follow-up, and inpatient readmission. Lasso feature selection analysis was performed. RESULTS: 723 patients (53 % female, mean (std) age of 62.3 (16.4) years) were identified from cEEG records with 575 (79 %) surviving to discharge. Of those discharged, 450 (78 %) had outpatient follow-up, 316 (55 %) had a neurology follow-up, and 288 (50 %) were readmitted during the 6-month period. Discharge on antiseizure medications (ASM), younger age, admission to neurosurgery, and proximity to the hospital were predictors of neurology follow-up visits. Discharge on ASMs, along with longer length of stay, younger age, emergency admissions, and higher illness severity were predictors of readmission. SIGNIFICANCE: ASMs at discharge, demographics (age, address), hospital care teams, and illness severity determine probability of follow-up. Parameters identified in this study may help healthcare systems develop interventions to improve care transitions for critically-ill patients with seizures and other EA.

Antiseizure Medication Use and Outcomes After Suspected or Confirmed Acute Symptomatic Seizures.

Importance: Antiseizure medications (ASMs) are frequently prescribed for acute symptomatic seizures and epileptiform abnormalities (EAs; eg, periodic or rhythmic patterns). There are limited data on factors associated with ASM use and their association with outcomes. Objectives: To determine factors associated with ASM use in patients with confirmed or suspected acute symptomatic seizures undergoing continuous electroencephalography, and to explore the association of ASMs with outcomes. Design, Setting, and Participants: This multicenter cohort study was performed between July 1 and September 30, 2021, at 5 US centers of the Post Acute Symptomatic Seizure Investigation and Outcomes Network. After screening 1717 patients, the study included 1172 hospitalized adults without epilepsy who underwent continuous electroencephalography after witnessed or suspected acute symptomatic seizures. Data analysis was performed from November 14, 2023, to February 2, 2024. Exposure: ASM treatment (inpatient ASM continuation ≥48 hours). Main Outcomes and Measures: Factors associated with (1) ASM treatment, (2) discharge ASM prescription, and (3) discharge and 3-month Glasgow Outcome Scale score of 4 or 5 were ascertained. Results: A total of 1172 patients (median [IQR] age, 64 [52-75] years; 528 [45%] female) were included. Among them, 285 (24%) had clinical acute symptomatic seizures, 107 (9%) had electrographic seizures, and 364 (31%) had EAs; 532 (45%) received ASM treatment. Among 922 patients alive at discharge, 288 (31%) were prescribed ASMs. The respective frequencies of inpatient ASM treatment and discharge prescription were 82% (233 of 285) and 69% (169 of 246) for patients with clinical acute symptomatic seizures, 96% (103 of 107) and 95% (61 of 64) for electrographic seizures, and 64% (233 of 364) and 48% (128 of 267) for EAs. On multivariable analysis, acute and progressive brain injuries were independently associated with increased odds of inpatient ASM treatment (odds ratio [OR], 3.86 [95% CI, 2.06-7.32] and 8.37 [95% CI, 3.48-20.80], respectively) and discharge prescription (OR, 2.26 [95% CI, 1.04-4.98] and 10.10 [95% CI, 3.94-27.00], respectively). Admission to the neurology or neurosurgery service (OR, 2.56 [95% CI, 1.08-6.18]) or to the neurological intensive care unit (OR, 7.98 [95% CI, 3.49-19.00]) was associated with increased odds of treatment. Acute symptomatic seizures and EAs were significantly associated with increased odds of ASM treatment (OR, 14.30 [95% CI, 8.52-24.90] and 2.30 [95% CI, 1.47-3.61], respectively) and discharge prescription (OR, 12.60 [95% CI, 7.37-22.00] and 1.72 [95% CI, 1.00-2.97], respectively). ASM treatment was not associated with outcomes at discharge (OR, 0.96 [95% CI, 0.61-1.52]) or at 3 months after initial presentation (OR, 1.26 [95% CI, 0.78-2.04]). Among 623 patients alive and with complete data at 3 months after discharge, 30 (5%) had postdischarge seizures, 187 (30%) were receiving ASMs, and 202 (32%) had all-cause readmissions. Conclusions and Relevance: This study suggests that etiology and electrographic findings are associated with ASM treatment for acute symptomatic seizures and EAs; ASM treatment was not associated with functional outcomes. Comparative effectiveness studies are indicated to identify which patients may benefit from ASMs and to determine the optimal treatment duration.

Improving Neurology Clinical Care With Natural Language Processing Tools.

The integration of natural language processing (NLP) tools into neurology workflows has the potential to significantly enhance clinical care. However, it is important to address the limitations and risks associated with integrating this new technology. Recent advances in transformer-based NLP algorithms (e.g., GPT, BERT) could augment neurology clinical care by summarizing patient health information, suggesting care options, and assisting research involving large datasets. However, these NLP platforms have potential risks including fabricated facts and data security and substantial barriers for implementation. Although these risks and barriers need to be considered, the benefits for providers, patients, and communities are substantial. With these systems achieving greater functionality and the pace of medical need increasing, integrating these tools into clinical care may prove not only beneficial but necessary. Further investigation is needed to design implementation strategies, mitigate risks, and overcome barriers.