Chemical identification and indexing in full-text articles: an overview of the NLM-Chem track at BioCreative VII.

The BioCreative National Library of Medicine (NLM)-Chem track calls for a community effort to fine-tune automated recognition of chemical names in the biomedical literature. Chemicals are one of the most searched biomedical entities in PubMed, and-as highlighted during the coronavirus disease 2019 pandemic-their identification may significantly advance research in multiple biomedical subfields. While previous community challenges focused on identifying chemical names mentioned in titles and abstracts, the full text contains valuable additional detail. We, therefore, organized the BioCreative NLM-Chem track as a community effort to address automated chemical entity recognition in full-text articles. The track consisted of two tasks: (i) chemical identification and (ii) chemical indexing. The chemical identification task required predicting all chemicals mentioned in recently published full-text articles, both span [i.e. named entity recognition (NER)] and normalization (i.e. entity linking), using Medical Subject Headings (MeSH). The chemical indexing task required identifying which chemicals reflect topics for each article and should therefore appear in the listing of MeSH terms for the document in the MEDLINE article indexing. This manuscript summarizes the BioCreative NLM-Chem track and post-challenge experiments. We received a total of 85 submissions from 17 teams worldwide. The highest performance achieved for the chemical identification task was 0.8672 F-score (0.8759 precision and 0.8587 recall) for strict NER performance and 0.8136 F-score (0.8621 precision and 0.7702 recall) for strict normalization performance. The highest performance achieved for the chemical indexing task was 0.6073 F-score (0.7417 precision and 0.5141 recall). This community challenge demonstrated that (i) the current substantial achievements in deep learning technologies can be utilized to improve automated prediction accuracy further and (ii) the chemical indexing task is substantially more challenging. We look forward to further developing biomedical text-mining methods to respond to the rapid growth of biomedical literature. The NLM-Chem track dataset and other challenge materials are publicly available at https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/. Database URL https://ftp.ncbi.nlm.nih.gov/pub/lu/BC7-NLM-Chem-track/.

Chemical identification and indexing in PubMed full-text articles using deep learning and heuristics.

The identification of chemicals in articles has attracted a large interest in the biomedical scientific community, given its importance in drug development research. Most of previous research have focused on PubMed abstracts, and further investigation using full-text documents is required because these contain additional valuable information that must be explored. The manual expert task of indexing Medical Subject Headings (MeSH) terms to these articles later helps researchers find the most relevant publications for their ongoing work. The BioCreative VII NLM-Chem track fostered the development of systems for chemical identification and indexing in PubMed full-text articles. Chemical identification consisted in identifying the chemical mentions and linking these to unique MeSH identifiers. This manuscript describes our participation system and the post-challenge improvements we made. We propose a three-stage pipeline that individually performs chemical mention detection, entity normalization and indexing. Regarding chemical identification, we adopted a deep-learning solution that utilizes the PubMedBERT contextualized embeddings followed by a multilayer perceptron and a conditional random field tagging layer. For the normalization approach, we use a sieve-based dictionary filtering followed by a deep-learning similarity search strategy. Finally, for the indexing we developed rules for identifying the more relevant MeSH codes for each article. During the challenge, our system obtained the best official results in the normalization and indexing tasks despite the lower performance in the chemical mention recognition task. In a post-contest phase we boosted our results by improving our named entity recognition model with additional techniques. The final system achieved 0.8731, 0.8275 and 0.4849 in the chemical identification, normalization and indexing tasks, respectively. The code to reproduce our experiments and run the pipeline is publicly available. Database URL https://github.com/bioinformatics-ua/biocreativeVII_track2.

Opinions and options about COVID-19: Personality correlates and sex differences in two European countries.

In the initial months of the COVID-19 pandemic in 2020, we collected data (N = 1,420) from Portugal and Spain in relation to personality (i.e., Dark Triad traits, Big Five traits, religiousness, and negative affect) and attitudes related to COVID-19 about its origins, opinions on how to deal with it, and fear of it. The most pervasive patterns we found were: (1) neurotic-type dispositions were associated with stronger opinions about the origins of the virus and leave people to have more fear of the virus but also more trust in tested establishments to provide help. (2): religious people were less trusting of science, thought prayer was answer, and attributed the existence of the virus to an act of God. We also found that sex differences and country differences in attitudes towards COVID-19 were mediate by sex/country differences in personality traits like emotional stability, religiousness, and negative affect. For instance, women reported more fear of COVID-19 than men did, and this was verified by women's greater tendency to have negative affect and low emotional stability relative to men. Results point to the central role of neuroticism in accounting for variance in broad-spectrum attitudes towards COVID-19.

An open-source UFBGA µ-board for wearable devices.

This paper presents the development of an open-source, low-sized, BGA microcontroller breakout board, that can be used for the development of wearable and cyber-physical prototypes. The board is based on the low power, 8-bit, ATtiny20-CCU Microchip AVR microcontroller. The ATtiny20-CCU can be programmed without bootloader, using the Atmel Tiny Programming Interface (TPI), instead of In-System Programming (ISP). The C code used to program the microcontroller can be written and compiled using the Microchip Studio freeware platform. The ATtiny20-CCU Ultra Fine-pitch Ball Grid Array (UFBGA) packaging technology allows the shrinkage of the conceived Electroless Nickel-Immersion Gold (ENIG) Printed Circuit Board (PCB) to a size of only 15.5 × 13 mm. Its low cost also makes it a viable option for developing many educational electronic projects, especially for Instrumentation and Assistive Technology. The contribution of this paper is mainly the hardware prototype design, the PCB manufacturing, building and test of a very low-sized open source µ-breakout PCB board, for wearable Instrumentation applications, towards the emergent Society/Industry 5.0.

Tuberculosis Presenting as Acute Sepsis and Secondary Hemophagocytic Lymphohistiocytosis.

We report the case of a 61-year-old man admitted to our emergency department with fever. At admission, he was hypotensive and tachycardic. In the initial investigation, elevation of inflammatory parameters, acute kidney injury (Kidney Disease Improving Global Outcomes (KDIGO) 3), hyperbilirubinemia, and hepatic cytocholestasis were evident. Empirical antibiotic therapy was started, after sepsis was assumed without an identifiable cause. His condition took an unfavorable clinical course, with respiratory failure, hepatosplenomegaly, pancytopenia, hyperferritinemia and hypofibrinogenemia. Microbial culture studies and a general immunological study were negative and lymphoproliferative disease was therefore excluded. Bone marrow aspirate revealed hemophagocytosis without granulomas. A diagnosis of hemophagocytic lymphohistiocytosis was assumed and pulse methylprednisolone therapy initiated. As this resulted in only a transient improvement, immunoglobulin and rituximab were initiated as a second-line therapy. The patient sadly had an unfavorable outcome despite all measures undertaken. In the postmortem study, Mycobacterium tuberculosis complex was isolated in the bone marrow aspirate, which led to the postmortem diagnosis of disseminated tuberculosis and angioinvasive pulmonary aspergillosis. The clinical presentation of disseminated tuberculosis is non-specific and hemophagocytic lymphohistiocytosis is one of its rare presentations. The mortality rate of hemophagocytic lymphohistiocytosis is high and increases with delayed diagnosis of the underlying condition and respective treatment. LEARNING POINTS: Hemophagocytic lymphohistiocytosis should be considered in patients presenting with fever, lymphadenopathy, splenomegaly, cytopenias, hyperferritinaemia and hypertriglyceridemia.Despite its rarity, tuberculosis should be considered as an etiology of hemophagocytic lymphohistiocytosis and, if suspected, antituberculosis therapy should be initiated early, even in the absence of a definite diagnosis.Immunosuppressant therapy increases the risk of opportunistic infections, which establishes the need for prophylactic antibiotic, antifungal, and antiviral drugs.

Early plasma biomarker dynamic profiles are associated with acute ischemic stroke outcomes.

BACKGROUND: Early outcome prediction after acute ischemic stroke (AIS) might be improved with blood-based biomarkers. We investigated whether the longitudinal profile of a multi-marker panel could predict the outcome of successfully recanalized AIS patients. METHODS: We used ultrasensitive single-molecule array (Simoa) to measure glial fibrillary acidic protein (GFAP), neurofilament light chain (NfL), total-tau (t-tau) and ELISA for brevican in a prospective study of AIS patients with anterior circulation large vessel occlusion successfully submitted to thrombectomy. Plasma was obtained at admission, upon treatment, 24 h and 72 h after treatment. Clinical and neuroimaging outcomes were assessed independently. RESULTS: Thirty-five patients (64.8%) had good early clinical or neuroimaging outcome. Baseline biomarker levels did not distinguish between outcomes. However, longitudinal intra-individual biomarker changes followed different dynamic profiles with time and according to outcome. GFAP levels exhibited an early and prominent increase between admission and just after treatment. NfL increase was less pronounced between admission and up to 24 h. T-tau increased between treatment and 24 h. Interestingly, GFAP rate-of-change (pg/ml/h) between admission and immediately after recanalization had a good discriminative capacity between clinical outcomes (AUC = 0.88, p < 0.001), which was higher than admission CT-ASPECTS (AUC = 0.75, p < 0.01). T-tau rate-of-change provided moderate discriminative capacity (AUC = 0.71, p < 0.05). Moreover, in AIS patients with admission CT-ASPECTS <9 both GFAP and NfL rate-of-change were good outcome predictors (AUC = 0.82 and 0.77, p < 0.05). CONCLUSION: Early GFAP, t-tau and NfL rate-of-change in plasma can predict AIS clinical and neuroimaging outcome after successful recanalization. Such dynamic measures match and anticipate neuroimaging predictive capacity, potentially improving AIS patient stratification for treatment, and targeting individualized stroke care.

Escritura en espejo en epilepsia / Mirror writing in epilepsy

No disponible

Clinical Concept Normalization on Medical Records Using Word Embeddings and Heuristics.

Electronic health records contain valuable information on patients' clinical history in the form of free text. Manually analyzing millions of these documents is unfeasible and automatic natural language processing methods are essential for efficiently exploiting these data. Within this, normalization of clinical entities, where the aim is to link entity mentions to reference vocabularies, is of utmost importance to successfully extract knowledge from clinical narratives. In this paper we present sieve-based models combined with heuristics and word embeddings and present results of our participation in the 2019 n2c2 (National NLP Clinical Challenges) shared-task on clinical concept normalization.

Extraction of chemical-protein interactions from the literature using neural networks and narrow instance representation.

The scientific literature contains large amounts of information on genes, proteins, chemicals and their interactions. Extraction and integration of this information in curated knowledge bases help researchers support their experimental results, leading to new hypotheses and discoveries. This is especially relevant for precision medicine, which aims to understand the individual variability across patient groups in order to select the most appropriate treatments. Methods for improved retrieval and automatic relation extraction from biomedical literature are therefore required for collecting structured information from the growing number of published works. In this paper, we follow a deep learning approach for extracting mentions of chemical-protein interactions from biomedical articles, based on various enhancements over our participation in the BioCreative VI CHEMPROT task. A significant aspect of our best method is the use of a simple deep learning model together with a very narrow representation of the relation instances, using only up to 10 words from the shortest dependency path and the respective dependency edges. Bidirectional long short-term memory recurrent networks or convolutional neural networks are used to build the deep learning models. We report the results of several experiments and show that our best model is competitive with more complex sentence representations or network structures, achieving an F1-score of 0.6306 on the test set. The source code of our work, along with detailed statistics, is publicly available.

Overview of the BioCreative VI Precision Medicine Track: mining protein interactions and mutations for precision medicine.

The Precision Medicine Initiative is a multicenter effort aiming at formulating personalized treatments leveraging on individual patient data (clinical, genome sequence and functional genomic data) together with the information in large knowledge bases (KBs) that integrate genome annotation, disease association studies, electronic health records and other data types. The biomedical literature provides a rich foundation for populating these KBs, reporting genetic and molecular interactions that provide the scaffold for the cellular regulatory systems and detailing the influence of genetic variants in these interactions. The goal of BioCreative VI Precision Medicine Track was to extract this particular type of information and was organized in two tasks: (i) document triage task, focused on identifying scientific literature containing experimentally verified protein-protein interactions (PPIs) affected by genetic mutations and (ii) relation extraction task, focused on extracting the affected interactions (protein pairs). To assist system developers and task participants, a large-scale corpus of PubMed documents was manually annotated for this task. Ten teams worldwide contributed 22 distinct text-mining models for the document triage task, and six teams worldwide contributed 14 different text-mining systems for the relation extraction task. When comparing the text-mining system predictions with human annotations, for the triage task, the best F-score was 69.06%, the best precision was 62.89%, the best recall was 98.0% and the best average precision was 72.5%. For the relation extraction task, when taking homologous genes into account, the best F-score was 37.73%, the best precision was 46.5% and the best recall was 54.1%. Submitted systems explored a wide range of methods, from traditional rule-based, statistical and machine learning systems to state-of-the-art deep learning methods. Given the level of participation and the individual team results we find the precision medicine track to be successful in engaging the text-mining research community. In the meantime, the track produced a manually annotated corpus of 5509 PubMed documents developed by BioGRID curators and relevant for precision medicine. The data set is freely available to the community, and the specific interactions have been integrated into the BioGRID data set. In addition, this challenge provided the first results of automatically identifying PubMed articles that describe PPI affected by mutations, as well as extracting the affected relations from those articles. Still, much progress is needed for computer-assisted precision medicine text mining to become mainstream. Future work should focus on addressing the remaining technical challenges and incorporating the practical benefits of text-mining tools into real-world precision medicine information-related curation.

Supervised Learning and Knowledge-Based Approaches Applied to Biomedical Word Sense Disambiguation.

Word sense disambiguation (WSD) is an important step in biomedical text mining, which is responsible for assigning an unequivocal concept to an ambiguous term, improving the accuracy of biomedical information extraction systems. In this work we followed supervised and knowledge-based disambiguation approaches, with the best results obtained by supervised means. In the supervised method we used bag-of-words as local features, and word embeddings as global features. In the knowledge-based method we combined word embeddings, concept textual definitions extracted from the UMLS database, and concept association values calculated from the MeSH co-occurrence counts from MEDLINE articles. Also, in the knowledge-based method, we tested different word embedding averaging functions to calculate the surrounding context vectors, with the goal to give more importance to closest words of the ambiguous term. The MSH WSD dataset, the most common dataset used for evaluating biomedical concept disambiguation, was used to evaluate our methods. We obtained a top accuracy of 95.6 % by supervised means, while the best knowledge-based accuracy was 87.4 %. Our results show that word embedding models improved the disambiguation accuracy, proving to be a powerful resource in the WSD task.

Protein-Protein Interaction Article Classification Using a Convolutional Recurrent Neural Network with Pre-trained Word Embeddings.

Curation of protein interactions from scientific articles is an important task, since interaction networks are essential for the understanding of biological processes associated with disease or pharmacological action for example. However, the increase in the number of publications that potentially contain relevant information turns this into a very challenging and expensive task. In this work we used a convolutional recurrent neural network for identifying relevant articles for extracting information regarding protein interactions. Using the BioCreative III Article Classification Task dataset, we achieved an area under the precision-recall curve of 0.715 and a Matthew's correlation coefficient of 0.600, which represents an improvement over previous works.

On Writing and Reading Artistic Computational Ecosystems.

We study the use of the generative systems known as computational ecosystems to convey artistic and narrative aims. These are virtual worlds running on computers, composed of agents that trade units of energy and emulate cycles of life and behaviors adapted from biological life forms. In this article we propose a conceptual framework in order to understand these systems, which are involved in processes of authorship and interpretation that this investigation analyzes in order to identify critical instruments for artistic exploration. We formulate a model of narrative that we call system stories (after Mitchell Whitelaw), characterized by the dynamic network of material and conceptual processes that define these artefacts. They account for narrative constellations with multiple agencies from which meaning and messages emerge. Finally, we present three case studies to explore the potential of this model within an artistic and generative domain, arguing that this understanding expands and enriches the palette of the language of these systems.

[Streptococcus pyogenes toxic-shock syndrome]. / Síndrome do choque tóxico por Streptococcus pyogenes.

Recently there has been an exponential increase in invasive infections caused by Streptococcus ß hemolyticus group A. In about one third of cases they are complicated by toxic shock syndrome, characterized by septic shock and multiorgan failure. The authors, by their rarity, report a case of bacteraemia caused by Streptococcus pyogenes complicated by toxic shock syndrome.

Acute kidney injury in severe trauma assessed by RIFLE criteria: a common feature without implications on mortality?

BACKGROUND: Acute kidney injury (AKI) has been hard to assess due to the lack of standard definitions. Recently, the Risk, Injury, Failure, Loss and End-Stage Kidney (RIFLE) classification has been proposed to classify AKI in a number of clinical settings. This study aims to estimate the frequency and levels of severity of AKI and to study its association with patient mortality and length of stay (LOS) in a cohort of trauma patients needing intensive care. METHODS: Between August 2001 and September 2007, 436 trauma patients consecutively admitted to a general intensive care unit (ICU), were assessed using the RIFLE criteria. Demographic data, characteristics of injury, and severity of trauma variables were also collected. RESULTS: Half of all ICU trauma admissions had AKI, which corresponded to the group of patients with a significantly higher severity of trauma. Among patients with AKI, RIFLE class R (Risk) comprised 47%, while I (Injury) and F (Failure) were, 36% and 17%, respectively. None of these patients required renal replacement therapy. No significant differences were found among these three AKI classes in relation to patient's age, gender, type and mechanism of injury, severity of trauma or mortality. Nevertheless, increasing severity of acute renal injury was associated with a longer ICU stay. CONCLUSIONS: AKI is a common feature among trauma patients requiring intensive care. Although the development of AKI is associated with an increased LOS it does not appear to influence patient mortality.