Development of a natural language processing algorithm to extract seizure types and frequencies from the electronic health record.

OBJECTIVE: To develop a natural language processing (NLP) algorithm to abstract seizure types and frequencies from electronic health records (EHR). BACKGROUND: Seizure frequency measurement is an epilepsy quality metric. Yet, abstraction of seizure frequency from the EHR is laborious. We present an NLP algorithm to extract seizure data from unstructured text of clinic notes. Algorithm performance was assessed at two epilepsy centers. METHODS: We developed a rules-based NLP algorithm to recognize terms related to seizures and frequency within the text of an outpatient encounter. Algorithm output (e.g. number of seizures of a particular type within a time interval) was compared to seizure data manually annotated by two expert reviewers ("gold standard"). The algorithm was developed from 150 clinic notes from institution #1 (development set), then tested on a separate set of 219 notes from institution #1 (internal test set) with 248 unique seizure frequency elements. The algorithm was separately applied to 100 notes from institution #2 (external test set) with 124 unique seizure frequency elements. Algorithm performance was measured by recall (sensitivity), precision (positive predictive value), and F1 score (geometric mean of precision and recall). RESULTS: In the internal test set, the algorithm demonstrated 70% recall (173/248), 95% precision (173/182), and 0.82 F1 score compared to manual review. Algorithm performance in the external test set was lower with 22% recall (27/124), 73% precision (27/37), and 0.40 F1 score. CONCLUSIONS: These results suggest NLP extraction of seizure types and frequencies is feasible, though not without challenges in generalizability for large-scale implementation.

Right Ventricular Global Longitudinal Strain as a Predictor of Acute and Early Right Heart Failure Post Left Ventricular Assist Device Implantation.

Early right heart failure (RHF) occurs in up to 40% of patients following left ventricular assist device (LVAD) implantation and is associated with increased morbidity and mortality. The most recent report from the Mechanical Circulatory Support-Academic Research Consortium (MCS-ARC) working group subdivides early RHF into early acute RHF and early postimplant RHF. We sought to determine the effectiveness of right ventricular (RV) longitudinal strain (LS) in predicting RHF according to the new MCS-ARC definition. We retrospectively analyzed clinical and echocardiographic data of patients who underwent LVAD implantation between 2015 and 2018. RVLS in the 4-chamber (4ch), RV outflow tract, and subcostal views were measured on pre-LVAD echocardiograms. Fifty-five patients were included in this study. Six patients (11%) suffered early acute RHF, requiring concomitant RVAD implantation intraoperatively. Twenty-two patients (40%) had postimplant RHF. RVLS was significantly reduced in patients who developed early acute and postimplant RHF. At a cutoff of -9.7%, 4ch RVLS had a sensitivity of 88.9% and a specificity of 77.8% for predicting RHF and area under the receiver operating characteristic curve of 0.86 (95% confidence interval 0.76-0.97). Echocardiographic RV strain outperformed more invasive hemodynamic measures and clinical parameters in predicting RHF.

Efficacy and Tolerability of Clobazam in Adults With Drug-Refractory Epilepsy.

OBJECTIVES: To evaluate the effectiveness and tolerability of clobazam as an adjunctive treatment for adults with drug-resistant epilepsy. METHODS: We performed a single-center, retrospective chart review of patients aged ≥18 years with drug-resistant epilepsy who started clobazam between 2010 and 2018. Included patients had outpatient visits both before and ≥1 month after clobazam initiation. Epilepsy classification, seizure frequency before and after clobazam, duration of clobazam treatment, and adverse effects were analyzed. RESULTS: A total of 417 patients met the inclusion criteria. Mean age was 37.5 years, and 54% of patients were female. Patients were on a mean of 2.4 antiepileptic drugs at the time of initiation of clobazam. Epilepsy types were focal (56.8%), Lennox-Gastaut syndrome (LGS) (21.1%), generalized (15.1%), and unclassified (7.0%). At the first follow-up visit ≥1 month after clobazam initiation, 50.3% of patients had >50% reduction in seizure frequency, and 20.5% were seizure free. Of the initial cohort, 17.1% were followed >1 year and were seizure free at last follow-up. Response rates did not differ between different epilepsy classifications. Fifty-one percent of patients experienced ≥1 side effect, most commonly lethargy/fatigue (30.7%) or mood changes (10.8%). A total of 178 (42.6%) patients discontinued clobazam, most commonly due to adverse effects (55%). CONCLUSIONS: Clobazam is effective and safe as a long-term adjunctive therapy for adults with drug-resistant epilepsy; efficacy in off-label use is similar to that in LGS. CLASSIFICATION OF EVIDENCE: This study provides Class IV evidence that clobazam is an effective treatment for adults with drug-resistant epilepsy, independent of epilepsy classification.

Current interventional therapies in acute pulmonary embolism.

Pulmonary embolism (PE) is the third leading cause of cardiovascular mortality. The management of PE is currently evolving given the development of new technologies and team-based approaches. This document will focus on risk stratification of PEs, review of the current interventional therapies, the role of clinical endpoints to assess the effectiveness of different interventional therapies, and the role for mechanical circulatory support in the complex management of this disease.

Endogenous T1ρ cardiovascular magnetic resonance in hypertrophic cardiomyopathy.

BACKGROUND: Hypertrophic cardiomyopathy (HCM) is characterized by increased left ventricular wall thickness, cardiomyocyte hypertrophy, and fibrosis. Adverse cardiac risk characterization has been performed using late gadolinium enhancement (LGE), native T1, and extracellular volume (ECV). Relaxation time constants are affected by background field inhomogeneity. T1ρ utilizes a spin-lock pulse to decrease the effect of unwanted relaxation. The objective of this study was to study T1ρ as compared to T1, ECV, and LGE in HCM patients. METHODS: HCM patients were recruited as part of the Novel Markers of Prognosis in Hypertrophic Cardiomyopathy study, and healthy controls were matched for comparison. In addition to cardiac functional imaging, subjects underwent T1 and T1ρ cardiovascular magnetic resonance imaging at short-axis positions at 1.5T. Subjects received gadolinium and underwent LGE imaging 15-20 min after injection covering the entire heart. Corresponding basal and mid short axis LGE slices were selected for comparison with T1 and T1ρ. Full-width half-maximum thresholding was used to determine the percent enhancement area in each LGE-positive slice by LGE, T1, and T1ρ. Two clinicians independently reviewed LGE images for presence or absence of enhancement. If in agreement, the image was labeled positive (LGE + +) or negative (LGE --); otherwise, the image was labeled equivocal (LGE + -). RESULTS: In 40 HCM patients and 10 controls, T1 percent enhancement area (Spearman's rho = 0.61, p < 1e-5) and T1ρ percent enhancement area (Spearman's rho = 0.48, p < 0.001e-3) correlated with LGE percent enhancement area. T1 and T1ρ percent enhancement areas were also correlated (Spearman's rho = 0.28, p = 0.047). For both T1 and T1ρ, HCM patients demonstrated significantly longer relaxation times compared to controls in each LGE category (p < 0.001 for all). HCM patients also showed significantly higher ECV compared to controls in each LGE category (p < 0.01 for all), and LGE -- slices had lower ECV than LGE + + (p = 0.01). CONCLUSIONS: Hyperenhancement areas as measured by T1ρ and LGE are moderately correlated. T1, T1ρ, and ECV were elevated in HCM patients compared to controls, irrespective of the presence of LGE. These findings warrant additional studies to investigate the prognostic utility of T1ρ imaging in the evaluation of HCM patients.

Down syndrome mouse models have an abnormal enteric nervous system.

Children with trisomy 21 (Down syndrome [DS]) have a 130-fold increased incidence of Hirschsprung Disease (HSCR), a developmental defect where the enteric nervous system (ENS) is missing from distal bowel (i.e., distal bowel is aganglionic). Treatment for HSCR is surgical resection of aganglionic bowel, but many children have bowel problems after surgery. Post-surgical problems like enterocolitis and soiling are especially common in children with DS. To determine how trisomy 21 affects ENS development, we evaluated the ENS in two DS mouse models, Ts65Dn and Tc1. These mice are trisomic for many chromosome 21 homologous genes, including Dscam and Dyrk1a, which are hypothesized to contribute to HSCR risk. Ts65Dn and Tc1 mice have normal ENS precursor migration at E12.5 and almost normal myenteric plexus structure as adults. However, Ts65Dn and Tc1 mice have markedly reduced submucosal plexus neuron density throughout the bowel. Surprisingly, the submucosal neuron defect in Ts65Dn mice is not due to excess Dscam or Dyrk1a, since normalizing copy number for these genes does not rescue the defect. These findings suggest the possibility that the high frequency of bowel problems in children with DS and HSCR may occur because of additional unrecognized problems with ENS structure.