Astragaloside IV promotes exosome secretion of endothelial progenitor cells to regulate PI3KR2/SPRED1 signaling and inhibit pyroptosis of diabetic endothelial cells.

BACKGROUND AIMS: Treating chronic non-healing diabetic wounds and achieving complete skin regeneration has always been a critical clinical challenge. METHODS: In order to address this issue, researchers conducted a study aiming to investigate the role of miR-126-3p in regulating the downstream gene PIK3R2 and promoting diabetic wound repair in endothelial progenitor cell (EPC)-derived extracellular vesicles. The study involved culturing EPCs with astragaloside IV, transfecting them with miR-126-3p inhibitor or mock plasmid, interfering with high glucose-induced damage in human umbilical vein endothelial cells (HUVECs) and treating diabetic skin wounds in rats. RESULTS: The healing of rat skin wounds was observed through histological staining. The results revealed that treatment with miR-126-3p-overexpressing EPC-derived extracellular vesicles accelerated the healing of rat skin wounds and resulted in better tissue repair with slower scar formation. In addition, the transfer of EPC-derived extracellular vesicles with high expression of miR-126-3p to high glucose-damaged HUVECs increased their proliferation and invasion, reduced necrotic and apoptotic cell numbers and improved tube formation. In this process, the expression of angiogenic factors vascular endothelial growth factor (VEGF)A, VEGFB, VEGFC, basic fibroblast growth factor and Ang-1 significantly increased, whereas the expression of caspase-1, NRLP3, interleukin-1ß, inteleukin-18, PIK3R2 and SPRED1 was suppressed. Furthermore, miR-126-3p was able to target and inhibit the expression of the PIK3R2 gene, thereby restoring the proliferation and migration ability of high glucose-damaged HUVEC. CONCLUSIONS: In summary, these research findings demonstrate the important role of miR-126-3p in regulating downstream genes and promoting diabetic wound repair, providing a new approach for treating chronic non-healing diabetic wounds.

Elevation of serum creatine kinase induced by anti-thyroid drugs: Two case reports and a literature review.

Anti-thyroid drugs (ATDs), such as methimazole (MMI) and propylthiouracil (PTU), are the most common treatment options for hyperthyroidism. Although effective, well-known adverse effects include agranulocytosis, toxic hepatitis, vasculitis, and arthralgias. Myalgia and elevation of serum creatine kinase (CK) are relatively rare, with an unclear mechanism. Rapid decrease in the thyroid hormone level may be associated with ATD-related myopathy; however, direct effects of the drug on muscle tissue cannot be excluded. Here we report on two Chinese patients with myalgia and an elevated CK due to ATDs. Early recognition of this rare medication-induced adverse effect and close monitoring of the CK level are particularly important. Physicians and pharmacists should inform the patients about the earliest symptoms of adverse effects for patients to know when to discontinue the drug. If adverse events occur, different treatment strategies such as ATD dose reduction and switching to alternative ATDs can be applied depending on the case.

A Study on the Mediating Role of Emotional Solidarity between Authenticity Perception Mechanism and Tourism Support Behavior Intentions within Rural Homestay Inn Tourism.

Rural homestay inns are an important part of rural tourism, and tourists' support behavior intentions are important factors affecting whether rural homestay inns can be developed sustainably. The local authentic life experiences and realization of actual communication between the host and tourists are the main influencing factors for tourists to revisit, recommend, or provide support. Although previous studies have confirmed the influence of authenticity perception on tourists' support behavior intentions from different perspectives, they have not analyzed the influence mechanism between them from the perspective of micro interpersonal emotional attitude. To further understand the impact mechanism between the two, this study introduces the variable of emotional solidarity; constructs a relationship model of authenticity perception, emotional solidarity, and tourists' support behavior intentions by adopting the theory of reasoned action; and verifies the established hypotheses through empirical analysis. The results show that both existential authenticity and objective authenticity positively influence tourism support behavior intentions, and the effect of objective authenticity on tourism support behavior intentions is greater than that of the presence of authenticity. Empathic understanding, feeling welcome, and emotional intimacy all play mediating roles between intrapersonal authenticity perception and tourism support behavior intentions. Findings also show empathic understanding and feeling welcome play mediating roles in objective authenticity perception and between the perception of objective authenticity and tourism support behavior intentions. Suggestions are also proposed for the development of homestay inn enterprises.

Anti-saccade as a Tool to Evaluate Neurocognitive Impairment in Alcohol Use Disorder.

It has been widely shown that chronic alcohol use leads to cognitive dysfunctions, especially inhibitory control. In an extension of the traditional approach, this research field has benefited from the emergence of innovative measures, among which is an anti-saccade, allowing direct and sensitive measure of the eye movements indexing attention bias to alcohol-related cues and the capability of inhibiting the reflexive saccades to the cues. During the past decade, there are numerous reports showing that drinkers make more unwanted reflexive saccades and longer latency in the anti-saccade task. These increased errors are usually explained by the deficits in inhibitory control. It has been demonstrated that inhibitory control on eye movement may be one of the earliest biomarkers of the onset of alcohol-related cognitive impairments. This review summarizes how an anti-saccade task can be used as a tool to investigate and assess the cognitive dysfunctions and the early detection of relapsing risk of alcohol dependence.

A Sensitive Liquid Chromatography-Mass Spectrometry Method for Determination of Toosendanin in Rat Plasma and its Application to Pharmacokinetic Study.

A simple, rapid and sensitive analytical method was developed for the determination of toosendanin in rat plasma using liquid chromatography tandem mass spectrometry (LC-MS/MS). Andrographolide was selected as the internal standard, and the plasma samples were extracted by liquid-liquid extraction with diethyl ether. Chromatographic separation was performed on a Dikma Spursil C18, 3.5 µm (150 × 2.1 mm i.d) analytical column with 85% methanol:water (v/v) containing 0.025% formic acid (pH = 3.9) as mobile phase. The flow rate was 0.25 mL/min, and the total run time was 3 min. Detection was performed with a triple-quadrupole tandem mass spectrometer using negative ion mode electrospray ionization (ESI) in the multiple reaction monitoring (MRM) mode. The MS/MS ion transitions monitored were m/z 573.1 â†’ 531.1 and 349.0 â†’ 287.0 for toosendanin and andrographolide, respectively. Good linearity was observed over the concentration range of 3.125-500 ng/mL in 100 µL of rat plasma with a correlation coefficient ˃0.9997. Intra- and inter-assay variabilities were ˂8.5% in plasma. The recovery and the matrix effect were in the range 71.8-73.5% and 96.4-103.8%, respectively. The analyte was stable under various conditions (at room temperature, during freeze-thaw settings, in the autosampler, and under deep-freeze conditions). The method was successfully applied to a pharmacokinetic study of toosendanin after its oral administration in rats at a dose of 10 mg/kg.

Extracting Concepts for Precision Oncology from the Biomedical Literature.

This paper describes an initial dataset and automatic natural language processing (NLP) method for extracting concepts related to precision oncology from biomedical research articles. We extract five concept types: Cancer, Mutation, Population, Treatment, Outcome. A corpus of 250 biomedical abstracts were annotated with these concepts following standard double-annotation procedures. We then experiment with BERT-based models for concept extraction. The best-performing model achieved a precision of 63.8%, a recall of 71.9%, and an F1 of 67.1. Finally, we propose additional directions for research for improving extraction performance and utilizing the NLP system in downstream precision oncology applications.

Prediction of Health Risk Preventative Behavior of Amateur Marathon Runners: A Cross-Sectional Study.

INTRODUCTION: Prevention of the health risk of amateur marathon runners is of great significance for the sustainable development of marathon. To reduce the psychological burden of amateur marathon runners and improve the participation experience, the current study used the health belief model to study the relationship among health beliefs, attitude to preventative behavior, self-efficacy, and health values of amateur marathon runners. METHODS: A total of 342 data were collected, and using the PROCESS (analytical procedures developed for mediating and moderating effects tests based on SPSS and SAS). A series of multiple linear regression models were established to study the relationship between variables, and the bootstrap confidence interval was selected to test the mediating and moderating effect. RESULTS: The results showed that perceived health threat (b = 0.463, p <0.05), health behavior expectations (b = 0.373, p <0.001), self-efficacy (b = 0.322, p <0.001), and behavioral attitudes (b = 0.230, p <0.001) can be regarded as antecedent variables for predicting preventative behaviors. In addition, the results also show that health behavior expectations, self-efficacy, and behavioral attitudes play chain-mediating role between perceived health threat and preventative behaviors. Health values appear to play a moderating role in the direct/indirect effects of perceived health threat on preventive behavior through a number of mediating variables. DISCUSSION: This study emphasizes that the amateur marathon runners must improve their health concept and take effective preventive measures before participating in the competition. According to this research, it is the responsibility of the event parties, public health officials and relevant departments of the host city to provide rich health information and risk education to amateur marathon runners. More public service advertisements or educational materials are needed to be placed on runners to enhance their awareness of the necessity and importance of taking preventive measures.

Dramatic Increases in Telehealth-Related Tweets during the Early COVID-19 Pandemic: A Sentiment Analysis.

The COVID-19 pandemic resulted in a large expansion of telehealth, but little is known about user sentiment. Tweets containing the terms "telehealth" and "telemedicine" were extracted (n = 192,430) from the official Twitter API between November 2019 and April 2020. A random subset of 2000 tweets was annotated by trained readers to classify tweets according to their content, including telehealth, sentiment, user type, and relation to COVID-19. A state-of-the-art NLP model (Bidirectional Encoder Representations from Transformers, BERT) was used to categorize the remaining tweets. Following a low and fairly stable level of activity, telehealth tweets rose dramatically beginning the first week of March 2020. The sentiment was overwhelmingly positive or neutral, with only a small percentage of negative tweets. Users included patients, clinicians, vendors (entities that promote the use of telehealth technology or services), and others, which represented the largest category. No significant differences were seen in sentiment across user groups. The COVID-19 pandemic produced a large increase in user tweets related to telehealth and COVID-19, and user sentiment suggests that most people feel positive or neutral about telehealth.

Emodin palliates high-fat diet-induced nonalcoholic fatty liver disease in mice via activating the farnesoid X receptor pathway.

BACKGROUND: Cassia mimosoides Linn (CMD) is a traditional Chinese herb that clears liver heat and dampness. It has been widely administered in clinical practice to treat jaundice associated with damp-heat pathogen and obesity. Emodin (EMO) is a major bioactive constituent of CMD that has apparent therapeutic efficacy against obesity and fatty liver. Here, we investigated the protective effects and underlying mechanisms of EMO against high-fat diet (HFD)-induced nonalcoholic fatty liver disease (NAFLD). OBJECTIVE: We aimed to investigate whether EMO activates farnesoid X receptor (FXR) signaling to alleviate HFD-induced NAFLD. MATERIALS AND METHODS: In vivo assays included serum biochemical indices tests, histopathology, western blotting, and qRT-PCR to evaluate the effects of EMO on glucose and lipid metabolism disorders in wild type (WT) and FXR knockout mice maintained on an HFD. In vitro experiments included intracellular triglyceride (TG) level measurement and Oil Red O staining to assess the capacity of EMO to remove lipids induced by oleic acid and palmitic acid in WT and FXR knockout mouse primary hepatocytes (MPHs). We also detected mRNA expression of FXR signaling genes in MPHs. RESULTS: After HFD administration, body weight and serum lipid and inflammation levels were dramatically increased in the WT mice. The animals also presented with impaired glucose tolerance, insulin resistance, and antioxidant capacity, liver tissue attenuation, and pathological injury. EMO remarkably reversed the foregoing changes in HFD-induced mice. EMO improved HFD-induced lipid accumulation, insulin resistance, inflammation, and oxidative stress in a dose-dependent manner in WT mice by inhibiting FXR expression. EMO also significantly repressed TG hyperaccumulation by upregulating FXR expression in MPHs. However, it did not improve lipid accumulation, insulin sensitivity, or glucose tolerance in HFD-fed FXR knockout mice. CONCLUSIONS: The present study demonstrated that EMO alleviates HFD-induced NAFLD by activating FXR signaling which improves lipid accumulation, insulin resistance, inflammation, and oxidative stress.

Generalized and transferable patient language representation for phenotyping with limited data.

The paradigm of representation learning through transfer learning has the potential to greatly enhance clinical natural language processing. In this work, we propose a multi-task pre-training and fine-tuning approach for learning generalized and transferable patient representations from medical language. The model is first pre-trained with different but related high-prevalence phenotypes and further fine-tuned on downstream target tasks. Our main contribution focuses on the impact this technique can have on low-prevalence phenotypes, a challenging task due to the dearth of data. We validate the representation from pre-training, and fine-tune the multi-task pre-trained models on low-prevalence phenotypes including 38 circulatory diseases, 23 respiratory diseases, and 17 genitourinary diseases. We find multi-task pre-training increases learning efficiency and achieves consistently high performance across the majority of phenotypes. Most important, the multi-task pre-training is almost always either the best-performing model or performs tolerably close to the best-performing model, a property we refer to as robust. All these results lead us to conclude that this multi-task transfer learning architecture is a robust approach for developing generalized and transferable patient language representations for numerous phenotypes.

Extracting postmarketing adverse events from safety reports in the vaccine adverse event reporting system (VAERS) using deep learning.

OBJECTIVE: Automated analysis of vaccine postmarketing surveillance narrative reports is important to understand the progression of rare but severe vaccine adverse events (AEs). This study implemented and evaluated state-of-the-art deep learning algorithms for named entity recognition to extract nervous system disorder-related events from vaccine safety reports. MATERIALS AND METHODS: We collected Guillain-Barré syndrome (GBS) related influenza vaccine safety reports from the Vaccine Adverse Event Reporting System (VAERS) from 1990 to 2016. VAERS reports were selected and manually annotated with major entities related to nervous system disorders, including, investigation, nervous_AE, other_AE, procedure, social_circumstance, and temporal_expression. A variety of conventional machine learning and deep learning algorithms were then evaluated for the extraction of the above entities. We further pretrained domain-specific BERT (Bidirectional Encoder Representations from Transformers) using VAERS reports (VAERS BERT) and compared its performance with existing models. RESULTS AND CONCLUSIONS: Ninety-one VAERS reports were annotated, resulting in 2512 entities. The corpus was made publicly available to promote community efforts on vaccine AEs identification. Deep learning-based methods (eg, bi-long short-term memory and BERT models) outperformed conventional machine learning-based methods (ie, conditional random fields with extensive features). The BioBERT large model achieved the highest exact match F-1 scores on nervous_AE, procedure, social_circumstance, and temporal_expression; while VAERS BERT large models achieved the highest exact match F-1 scores on investigation and other_AE. An ensemble of these 2 models achieved the highest exact match microaveraged F-1 score at 0.6802 and the second highest lenient match microaveraged F-1 score at 0.8078 among peer models.

Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review.

OBJECTIVES: Patient representation learning refers to learning a dense mathematical representation of a patient that encodes meaningful information from Electronic Health Records (EHRs). This is generally performed using advanced deep learning methods. This study presents a systematic review of this field and provides both qualitative and quantitative analyses from a methodological perspective. METHODS: We identified studies developing patient representations from EHRs with deep learning methods from MEDLINE, EMBASE, Scopus, the Association for Computing Machinery (ACM) Digital Library, and the Institute of Electrical and Electronics Engineers (IEEE) Xplore Digital Library. After screening 363 articles, 49 papers were included for a comprehensive data collection. RESULTS: Publications developing patient representations almost doubled each year from 2015 until 2019. We noticed a typical workflow starting with feeding raw data, applying deep learning models, and ending with clinical outcome predictions as evaluations of the learned representations. Specifically, learning representations from structured EHR data was dominant (37 out of 49 studies). Recurrent Neural Networks were widely applied as the deep learning architecture (Long short-term memory: 13 studies, Gated recurrent unit: 11 studies). Learning was mainly performed in a supervised manner (30 studies) optimized with cross-entropy loss. Disease prediction was the most common application and evaluation (31 studies). Benchmark datasets were mostly unavailable (28 studies) due to privacy concerns of EHR data, and code availability was assured in 20 studies. DISCUSSION & CONCLUSION: The existing predictive models mainly focus on the prediction of single diseases, rather than considering the complex mechanisms of patients from a holistic review. We show the importance and feasibility of learning comprehensive representations of patient EHR data through a systematic review. Advances in patient representation learning techniques will be essential for powering patient-level EHR analyses. Future work will still be devoted to leveraging the richness and potential of available EHR data. Reproducibility and transparency of reported results will hopefully improve. Knowledge distillation and advanced learning techniques will be exploited to assist the capability of learning patient representation further.

Patient Representation Transfer Learning from Clinical Notes based on Hierarchical Attention Network.

To explicitly learn patient representations from longitudinal clinical notes, we propose a hierarchical attention-based recurrent neural network (RNN) with greedy segmentation to distinguish between shorter and longer, more meaningful gaps between notes. The proposed model is evaluated for both a direct clinical prediction task (mortality) and as a transfer learning pre-training model to downstream evaluation (phenotype prediction of obesity and its comorbidities). Experimental results first show the proposed model with appropriate segmentation achieved the best performance on mortality prediction, indicating the effectiveness of hierarchical RNNs in dealing with longitudinal clinical text. Attention weights from the models highlight those parts of notes with the largest impact on mortality prediction and hopefully provide a degree of interpretability. Following the transfer learning approach, we also demonstrate the effectiveness and generalizability of pre-trained patient representations on target tasks of phenotyping.

Understanding spatial language in radiology: Representation framework, annotation, and spatial relation extraction from chest X-ray reports using deep learning.

Radiology reports contain a radiologist's interpretations of images, and these images frequently describe spatial relations. Important radiographic findings are mostly described in reference to an anatomical location through spatial prepositions. Such spatial relationships are also linked to various differential diagnoses and often described through uncertainty phrases. Structured representation of this clinically significant spatial information has the potential to be used in a variety of downstream clinical informatics applications. Our focus is to extract these spatial representations from the reports. For this, we first define a representation framework based on the Spatial Role Labeling (SpRL) scheme, which we refer to as Rad-SpRL. In Rad-SpRL, common radiological entities tied to spatial relations are encoded through four spatial roles: Trajector, Landmark, Diagnosis, and Hedge, all identified in relation to a spatial preposition (or Spatial Indicator). We annotated a total of 2,000 chest X-ray reports following Rad-SpRL. We then propose a deep learning-based natural language processing (NLP) method involving word and character-level encodings to first extract the Spatial Indicators followed by identifying the corresponding spatial roles. Specifically, we use a bidirectional long short-term memory (Bi-LSTM) conditional random field (CRF) neural network as the baseline model. Additionally, we incorporate contextualized word representations from pre-trained language models (BERT and XLNet) for extracting the spatial information. We evaluate both gold and predicted Spatial Indicators to extract the four types of spatial roles. The results are promising, with the highest average F1 measure for Spatial Indicator extraction being 91.29 (XLNet); the highest average overall F1 measure considering all the four spatial roles being 92.9 using gold Indicators (XLNet); and 85.6 using predicted Indicators (BERT pre-trained on MIMIC notes). The corpus is available in Mendeley at http://dx.doi.org/10.17632/yhb26hfz8n.1 and https://github.com/krobertslab/datasets/blob/master/Rad-SpRL.xml.

Deep learning in clinical natural language processing: a methodical review.

OBJECTIVE: This article methodically reviews the literature on deep learning (DL) for natural language processing (NLP) in the clinical domain, providing quantitative analysis to answer 3 research questions concerning methods, scope, and context of current research. MATERIALS AND METHODS: We searched MEDLINE, EMBASE, Scopus, the Association for Computing Machinery Digital Library, and the Association for Computational Linguistics Anthology for articles using DL-based approaches to NLP problems in electronic health records. After screening 1,737 articles, we collected data on 25 variables across 212 papers. RESULTS: DL in clinical NLP publications more than doubled each year, through 2018. Recurrent neural networks (60.8%) and word2vec embeddings (74.1%) were the most popular methods; the information extraction tasks of text classification, named entity recognition, and relation extraction were dominant (89.2%). However, there was a "long tail" of other methods and specific tasks. Most contributions were methodological variants or applications, but 20.8% were new methods of some kind. The earliest adopters were in the NLP community, but the medical informatics community was the most prolific. DISCUSSION: Our analysis shows growing acceptance of deep learning as a baseline for NLP research, and of DL-based NLP in the medical community. A number of common associations were substantiated (eg, the preference of recurrent neural networks for sequence-labeling named entity recognition), while others were surprisingly nuanced (eg, the scarcity of French language clinical NLP with deep learning). CONCLUSION: Deep learning has not yet fully penetrated clinical NLP and is growing rapidly. This review highlighted both the popular and unique trends in this active field.

Deep Patient Representation of Clinical Notes via Multi-Task Learning for Mortality Prediction.

We propose a deep learning-based multi-task learning (MTL) architecture focusing on patient mortality predictions from clinical notes. The MTL framework enables the model to learn a patient representation that generalizes to a variety of clinical prediction tasks. Moreover, we demonstrate how MTL enables small but consistent gains on a single classification task (e.g., in-hospital mortality prediction) simply by incorporating related tasks (e.g., 30-day and 1-year mortality prediction) into the MTL framework. To accomplish this, we utilize a multi-level Convolutional Neural Network (CNN) associated with a MTL loss component. The model is evaluated with 3, 5, and 20 tasks and is consistently able to produce a higher-performing model than a single-task learning (STL) classifier. We further discuss the effect of the multi-task model on other clinical outcomes of interest, including being able to produce high-quality representations that can be utilized to great effect by simpler models. Overall, this study demonstrates the efficiency and generalizability of MTL across tasks that STL fails to leverage.

Enhancing clinical concept extraction with contextual embeddings.

OBJECTIVE: Neural network-based representations ("embeddings") have dramatically advanced natural language processing (NLP) tasks, including clinical NLP tasks such as concept extraction. Recently, however, more advanced embedding methods and representations (eg, ELMo, BERT) have further pushed the state of the art in NLP, yet there are no common best practices for how to integrate these representations into clinical tasks. The purpose of this study, then, is to explore the space of possible options in utilizing these new models for clinical concept extraction, including comparing these to traditional word embedding methods (word2vec, GloVe, fastText). MATERIALS AND METHODS: Both off-the-shelf, open-domain embeddings and pretrained clinical embeddings from MIMIC-III (Medical Information Mart for Intensive Care III) are evaluated. We explore a battery of embedding methods consisting of traditional word embeddings and contextual embeddings and compare these on 4 concept extraction corpora: i2b2 2010, i2b2 2012, SemEval 2014, and SemEval 2015. We also analyze the impact of the pretraining time of a large language model like ELMo or BERT on the extraction performance. Last, we present an intuitive way to understand the semantic information encoded by contextual embeddings. RESULTS: Contextual embeddings pretrained on a large clinical corpus achieves new state-of-the-art performances across all concept extraction tasks. The best-performing model outperforms all state-of-the-art methods with respective F1-measures of 90.25, 93.18 (partial), 80.74, and 81.65. CONCLUSIONS: We demonstrate the potential of contextual embeddings through the state-of-the-art performance these methods achieve on clinical concept extraction. Additionally, we demonstrate that contextual embeddings encode valuable semantic information not accounted for in traditional word representations.

Time-sensitive clinical concept embeddings learned from large electronic health records.

BACKGROUND: Learning distributional representation of clinical concepts (e.g., diseases, drugs, and labs) is an important research area of deep learning in the medical domain. However, many existing relevant methods do not consider temporal dependencies along the longitudinal sequence of a patient's records, which may lead to incorrect selection of contexts. METHODS: To address this issue, we extended three popular concept embedding learning methods: word2vec, positive pointwise mutual information (PPMI) and FastText, to consider time-sensitive information. We then trained them on a large electronic health records (EHR) database containing about 50 million patients to generate concept embeddings and evaluated them for both intrinsic evaluations focusing on concept similarity measure and an extrinsic evaluation to assess the use of generated concept embeddings in the task of predicting disease onset. RESULTS: Our experiments show that embeddings learned from information within one visit (time window zero) improve performance on the concept similarity measure and the FastText algorithm usually had better performance than the other two algorithms. For the predictive modeling task, the optimal result was achieved by word2vec embeddings with a 30-day sliding window. CONCLUSIONS: Considering time constraints are important in training clinical concept embeddings. We expect they can benefit a series of downstream applications.

Relation Extraction from Clinical Narratives Using Pre-trained Language Models.

Natural language processing (NLP) is useful for extracting information from clinical narratives, and both traditional machine learning methods and more-recent deep learning methods have been successful in various clinical NLP tasks. These methods often depend on traditional word embeddings that are outputs of language models (LMs). Recently, methods that are directly based on pre-trained language models themselves, followed by fine-tuning on the LMs (e.g. the Bidirectional Encoder Representations from Transformers (BERT)), have achieved state-of-the-art performance on many NLP tasks. Despite their success in the open domain and biomedical literature, these pre-trained LMs have not yet been applied to the clinical relation extraction (RE) task. In this study, we developed two different implementations of the BERT model for clinical RE tasks. Our results show that our tuned LMs outperformed previous state-of-the-art RE systems in two shared tasks, which demonstrates the potential of LM-based methods on the RE task.

The Data Gap in the EHR for Clinical Research Eligibility Screening.

Much effort has been devoted to leverage EHR data for matching patients into clinical trials. However, EHRs may not contain all important data elements for clinical research eligibility screening. To better design research-friendly EHRs, an important step is to identify data elements frequently used for eligibility screening but not yet available in EHRs. This study fills this knowledge gap. Using the Alzheimer's disease domain as an example, we performed text mining on the eligibility criteria text in Clinicaltrials.gov to identify frequently used eligibility criteria concepts. We compared them to the EHR data elements of a cohort of Alzheimer's Disease patients to assess the data gap by usingthe OMOP Common Data Model to standardize the representations for both criteria concepts and EHR data elements. We identified the most common SNOMED CT concepts used in Alzheimer 's Disease trials, andfound 40% of common eligibility criteria concepts were not even defined in the concept space in the EHR dataset for a cohort of Alzheimer 'sDisease patients, indicating a significant data gap may impede EHR-based eligibility screening. The results of this study can be useful for designing targeted research data collection forms to help fill the data gap in the EHR.