This novel hybrid approach can accurately locate negated concepts in clinical radiology reports not only when in close proximity to, but also at a distance from, negation signals.

No abstract

BACKGROUND: Although substantial concerns about the inflammatory effects of engineered nanomaterial (ENM) have been raised, experimentally assessing toxicity of various ENMs is challenging and time-consuming. Alternatively, quantitative structure-activity relationship (QSAR) models have been employed to assess nanosafety. However, no previous attempt has been made to predict the inflammatory potential of ENMs. OBJECTIVES: By employing metal oxide nanoparticles (MeONPs) as a model ENM, we aimed to develop QSAR models for prediction of the inflammatory potential by their physicochemical properties. METHODS: We built a comprehensive data set of 30 MeONPs to screen a proinflammatory cytokine interleukin (IL)-1 beta (IL-1b) release in THP-1 cell line. The in vitro hazard ranking was validated in mouse lungs by oropharyngeal instillation of six randomly selected MeONPs. We established QSAR models for prediction of MeONP-induced inflammatory potential via machine learning. The models were further validated against seven new MeONPs. Density functional theory (DFT) computations were exploited to decipher the key mechanisms driving inflammatory responses of MeONPs. RESULTS: Seventeen out of 30 MeONPs induced excess IL-1b production in THP-1 cells. In vivo disease outcomes were highly relevant to the in vitro data. QSAR models were developed for inflammatory potential, with predictive accuracy (ACC) exceeding 90%. The models were further validated experimentally against seven independent MeONPs (ACC = 86%). DFT computations and experimental results further revealed the underlying mechanisms: MeONPs with metal electronegativity lower than 1.55 and positive f-potential were more likely to cause lysosomal damage and inflammation. CONCLUSIONS: IL-1b released in THP-1 cells can be an index to rank the inflammatory potential of MeONPs. QSAR models based on IL-1b were able to predict the inflammatory potential of MeONPs. Our approach overcame the challenge of time-and labor-consuming biological experiments and allowed for computational assessment of MeONP inflammatory potential by characterization of their physicochemical properties.

A b s t r a c t Objective: The aim of this study was to develop and evaluate a method of extracting noun phrases with full phrase structures from a set of clinical radiology reports using natural language processing (NLP) and to investigate the effects of using the UMLSÒ Specialist Lexicon to improve noun phrase identification within clinical radiology documents.Design: The noun phrase identification (NPI) module is composed of a sentence boundary detector, a statistical natural language parser trained on a nonmedical domain, and a noun phrase (NP) tagger. The NPI module processed a set of 100 XML-represented clinical radiology reports in Health Level 7 (HL7)Ò Clinical Document Architecture (CDA)-compatible format. Computed output was compared with manual markups made by four physicians and one author for maximal (longest) NP and those made by one author for base (simple) NP, respectively. An extended lexicon of biomedical terms was created from the UMLS Specialist Lexicon and used to improve NPI performance.Results: The test set was 50 randomly selected reports. The sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%. Conclusion:The sentence boundary detector performs excellently. After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.

Objective Detecting adverse drug events (ADEs) and medications related information in clinical notes is important for both hospital medical care and medical research. We describe our clinical natural language processing (NLP) system to automatically extract medical concepts and relations related to ADEs and medications from clinical narratives. This work was part of the 2018 National NLP Clinical Challenges Shared Task and Workshop on Adverse Drug Events and Medication Extraction. Materials and Methods The authors developed a hybrid clinical NLP system that employs a knowledge-based general clinical NLP system for medical concepts extraction, and a task-specific deep learning system for relations identification using attention-based bidirectional long short-term memory networks. Results The systems were evaluated as part of the 2018 National NLP Clinical Challenges challenge, and our attention-based bidirectional long short-term memory networks based system obtained an F-measure of 0.9442 for relations identification task, ranking fifth at the challenge, and had <2% difference from the best system. Error analysis was also conducted targeting at figuring out the root causes and possible approaches for improvement. Conclusions We demonstrate the generic approaches and the practice of connecting general purposed clinical NLP system to task-specific requirements with deep learning methods. Our results indicate that a well-designed hybrid NLP system is capable of ADE and medication-related information extraction, which can be used in real-world applications to support ADE-related researches and medical decisions.