Population-level call properties of endangered Dryophytes suweonensissensu lato (Anura: Amphibia) in South Korea.

Calling is one of the unique amphibian characteristics that facilitates social communication and shows individuality; however, it also makes them vulnerable to predators. Researchers use amphibian call properties to study their population status, ecology, and behavior. This research scope has recently broadened to species identification and taxonomy. Dryophytes flaviventris has been separated from the endangered anuran species, D. suweonensis, based on small variations in genetic, morphometric, and temporal call properties observed in South Korea. The Chilgap Mountain (CM) was considered as the potential geographic barrier for the speciation. However, it initiated taxonomic debates as CM has been hardly used and is considered a potential barrier for other species. The calls of populations from both sides are also apparently similar. Thus, to verify the differences in call properties among populations of D. suweonensis sensu lato (s.l.; both of the species), we sampled and analyzed call data from five localities covering its distribution range, including the southern (S) and northern (N) parts of CM. We found significant differences in many call properties among populations; however, no specific pattern was observed. Some geographically close populations, such as Iksan (S), Wanju (S), and Gunsan (S), had significant differences, whereas many distant populations, such as Pyeongtaek (N) and Wanju (S), had no significant differences. Considering the goal of this study was only to observe the call properties, we cautiously conclude that the differences are at the population level rather than the species level. Our study indicates the necessity of further investigation into the specific status of D. flaviventris using robust integrated taxonomic approaches, including genetic and morphological parameters from a broader array of localities.

A Context-Enhanced De-identification System.

Many modern entity recognition systems, including the current state-of-the-art de-identification systems, are based on bidirectional long short-term memory (biLSTM) units augmented by a conditional random field (CRF) sequence optimizer. These systems process the input sentence by sentence. This approach prevents the systems from capturing dependencies over sentence boundaries and makes accurate sentence boundary detection a prerequisite. Since sentence boundary detection can be problematic especially in clinical reports, where dependencies and co-references across sentence boundaries are abundant, these systems have clear limitations. In this study, we built a new system on the framework of one of the current state-of-the-art de-identification systems, NeuroNER, to overcome these limitations. This new system incorporates context embeddings through forward and backward n -grams without using sentence boundaries. Our context-enhanced de-identification (CEDI) system captures dependencies over sentence boundaries and bypasses the sentence boundary detection problem altogether. We enhanced this system with deep affix features and an attention mechanism to capture the pertinent parts of the input. The CEDI system outperforms NeuroNER on the 2006 i2b2 de-identification challenge dataset, the 2014 i2b2 shared task de-identification dataset, and the 2016 CEGS N-GRID de-identification dataset (p < 0.01). All datasets comprise narrative clinical reports in English but contain different note types varying from discharge summaries to psychiatric notes. Enhancing CEDI with deep affix features and the attention mechanism further increased performance.

Transferability of neural network clinical deidentification systems.

OBJECTIVE: Neural network deidentification studies have focused on individual datasets. These studies assume the availability of a sufficient amount of human-annotated data to train models that can generalize to corresponding test data. In real-world situations, however, researchers often have limited or no in-house training data. Existing systems and external data can help jump-start deidentification on in-house data; however, the most efficient way of utilizing existing systems and external data is unclear. This article investigates the transferability of a state-of-the-art neural clinical deidentification system, NeuroNER, across a variety of datasets, when it is modified architecturally for domain generalization and when it is trained strategically for domain transfer. MATERIALS AND METHODS: We conducted a comparative study of the transferability of NeuroNER using 4 clinical note corpora with multiple note types from 2 institutions. We modified NeuroNER architecturally to integrate 2 types of domain generalization approaches. We evaluated each architecture using 3 training strategies. We measured transferability from external sources; transferability across note types; the contribution of external source data when in-domain training data are available; and transferability across institutions. RESULTS AND CONCLUSIONS: Transferability from a single external source gave inconsistent results. Using additional external sources consistently yielded an F1-score of approximately 80%. Fine-tuning emerged as a dominant transfer strategy, with or without domain generalization. We also found that external sources were useful even in cases where in-domain training data were available. Transferability across institutions differed by note type and annotation label but resulted in improved performance.

Adverse drug event detection using reason assignments in FDA drug labels.

Adverse drug events (ADEs) are unintended incidents that involve the taking of a medication. ADEs pose significant health and financial problems worldwide. Information about ADEs can inform health care and improve patient safety. However, much of this information is buried in narrative texts and needs to be extracted with Natural Language Processing techniques, in order to be useful to computerized methods. ADEs can be found on drug labels, contained in the different sections such as descriptions of the drug's active components or more prominently in descriptions of studied side-effects. Extracting these automatically could be useful in triaging and processing drug reports. In this paper, we present three base methods consisting of a Conditional Random Field (CRF), a bi-directional Long Short Term Memory unit with a CRF layer (biLSTM+CRF), and a pre-trained Bi-directional Encoder Representations from Transformers (BERT) model. We also present several ensembles of the CRF and biLSTM+CRF methods for extracting ADEs and their Reason from FDA drug labels. We show that all three methods perform well on our task, and that combining the models through different ensemble methods can improve results, providing increases in recall for the majority class and improving precision for all other classes. We also show the potential of framing ADE extraction from drug labels as a multi-class classification task on the Reason, or type, of ADE.

Normalizing Adverse Events using Recurrent Neural Networks with Attention.

Adverse events (AEs) are undesirable outcomes of medication administration and cause many hospitalizations as well as even deaths per year. Information about AEs can enable their prevention. Natural language processing (NLP) techniques can identify AEs from narratives and match them to a structured terminology. We propose a novel neural network for AE normalization utilizing bidirectional long short-term memory (biLSTM) with attention mechanism that generalizes to diverse datasets. We train this network to first learn a framework for general AE normalization and then to learn the specifics of the task on individual corpora. Our results on the datasets from the Text Analysis Conference (TAC) 2017-ADR track, FDA adverse drug event evaluation shared task, and the Social Media Mining for Health Applications Workshop & Shared Task 2019 show that our approach outperforms widely used rule-based normalizers on a diverse set of narratives. Additionally, it outperforms the best normalization system by 4.86 in macro-averaged F1-score in the TAC 2017-ADR track.

An Empirical Test of GRUs and Deep Contextualized Word Representations on De-Identification.

De-identification aims to remove 18 categories of protected health information from electronic health records. Ideally, de-identification systems should be reliable and generalizable. Previous research has focused on improving performance but has not examined generalizability. This paper investigates both performance and generalizability. To improve current state-of-the-art performance based on long short-term memory (LSTM) units, we introduce a system that uses gated recurrent units (GRUs) and deep contextualized word representations, both of which have never been applied to de-identification. We measure performance and generalizability of each system using the 2014 i2b2/UTHealth and 2016 CEGS N-GRID de-identification datasets. We show that deep contextualized word representations improve state-of-the-art performance, while the benefit of switching LSTM units with GRUs is not significant. The generalizability of de-identification system significantly improved with deep contextualized word representations; in addition, LSTM units-based system is more generalizable than the GRUs-based system.

An Exploratory Study on Pseudo-Data Generation in Prescription and Adverse Drug Reaction Extraction.

Prescription information and adverse drug reactions (ADR) are two components of detailed medication instructions that can benefit many aspects of clinical research. Automatic extraction of this information from free-text narratives via Information Extraction (IE) can open it up to downstream uses. IE is commonly tackled by supervised Natural Language Processing (NLP) systems which rely on annotated training data. However, training data generation is manual, time-consuming, and labor-intensive. It is desirable to develop automatic methods for augmenting manually labeled data. We propose pseudo-data generation as one such automatic method. Pseudo-data are synthetic data generated by combining elements of existing labeled data. We propose and evaluate two sets of pseudo-data generation methods: knowledge-driven methods based on gazetteers and data-driven methods based on deep learning. We use the resulting pseudo-data to improve medication and ADR extraction. Data-driven pseudo-data are suitable for concept categories with high semantic regularities and short textual spans. Knowledge-driven pseudo-data are effective for concept categories with longer textual spans, assuming the knowledge base offers good coverage of these concepts. Combining the knowledge- and data-driven pseudo-data achieves significant performance improvement on medication names and ADRs over baselines limited to the use of available labeled data.

Altered functional efficacy of hippocampal interneuron during epileptogenesis following febrile seizures.

Febrile seizure (FS) is the most common seizure type in infants and young children. FS may induce functional changes in the hippocampal circuitries. Abnormality of excitatory and inhibitory neurotransmissions was previously related to wide-spread seizure attack in the hippocampus following recurrent seizure onset. To clarify the involvement of expressional changes and functional alterations of hippocampal interneurons with epileptogenesis following FS, we investigated long-term effects following recurrent seizure in a hyperthermia-induced seizure animal model. At 12 weeks following FS, the recurrent seizure time period, local field potentials (LFP) revealed high amplitude potential and a sharp wave characteristic of epilepsy. Mossy fiber reorganization in the hippocampus was also detected as abnormal synaptic connection at 8 weeks. Calretinin (CR) -positive interneurons were transiently enhanced during epileptogenic period at 7-9 weeks after FS in the CA1 and DG region and it is double labeled with VGLUT-1. However, although GABAA-α1 immunoreactivities were un-changed as similar to control hippocampus at 7-9 weeks after seizure onset, its expression was significantly enhanced at 4 weeks and 12 weeks and it is colocalized with GABA. Furthermore, the field excitatory postsynaptic potential (fEPSP) and the paired-pulse responses including population spike (PS) latency, excitability ratio and PS2/PS1 ratio were markedly altered in the CA1 and DG region at 12 weeks after FS. Therefore, our findings in present study indicate that these time-dependent changes may be based on the persistent alterations of hippocampal neuronal circuits in balance between excitatory and inhibitory responses, and may lead to the epileptogenesis and spread of seizure activity following FS.

Subfoveal choroidal thickness in idiopathic choroidal neovascularization and treatment outcomes after intravitreal bevacizumab therapy.

PURPOSE: To determine subfoveal choroidal thickness in idiopathic choroidal neovascularization (CNV) and evaluate visual and anatomical outcomes in patients with idiopathic CNV after intravitreal bevacizumab. METHODS: Retrospective observation case series. Seventeen eyes of 17 patients with idiopathic CNV were treated with a single intravitreal bevacizumab injection, followed by additional doses based on optical coherence tomography findings, including intraretinal fluid, subretinal fluid, or pigment epithelial detachment. We analyzed best-corrected visual acuity, central subfield thickness, and subfoveal choroidal thickness at presentation and final visit. Seventeen unaffected fellow eyes and 17 healthy eyes constituted the control group for subfoveal choroidal thickness. RESULTS: The subfoveal choroidal thickness was significantly thinner in eyes with idiopathic CNV (237.59 ± 53.84 µm) than in the unaffected fellow eyes (281.71 ± 59.01 µm, P = 0.001) or normal control eyes (290.38 ± 58.94 µm, P = 0.028). Mean logarithm of the minimum angle of resolution best-corrected visual acuity improved from 0.46 initially to 0.26 after treatment (P = 0.024). Mean central subfield thickness decreased from 387.88 ± 97.52 µm at baseline to 261.41 ± 31.18 µm after treatment (P < 0.001). CONCLUSION: Subfoveal choroidal thickness is reduced and may be associated with the pathophysiology of idiopathic CNV. Intravitreal bevacizumab resulted in significant visual and anatomical improvement in patients with idiopathic CNV.