Academic literature on the topic 'Biomedical summarisation'

According to the growing interest in mobile healthcare, multi-document summarisation techniques are increasingly required to cope with health information overload and effectively deliver personalised online healthcare information. However, because of the peculiarities of medical terminology and the diversity of subtopics in health documents, multi-document summarisation must consider technical aspects that are different from those of the general domain. In this article, we propose a personalised health document summarisation system that provides a reliable personal health-related summary to general healthcare consumers via mobile devices. Our system generates a personalised summary from multiple online health documents by exploiting biomedical concepts, semantic types and semantic relations extracted from the Unified Medical Language System (UMLS) and analysing individual health records derived from mobile personal health record (PHR) applications. Furthermore, to increase the diversity and coverage of summarised results and to display them in a user-friendly manner on mobile devices, we create a summary that is categorised into subtopics by grouping semantically related sentences through topic-based clustering. The experimental evaluations demonstrate the effectiveness of our proposed system.

The surface properties of polymer membranes are crucial to their separation performances. For the microporous polypropylene membranes, the high hydrophobicity and lack of functionality easily cause protein adsorption and subsequent microorganism attachment and biofilm formation, i.e. biofouling. Thus, their applications in water treatment, bioseparation and biomedical fields are largely limited. Surface hydrophilisation and antibacterial functionalisation are, therefore, reasonably necessary. This review provides a concise summarisation of related studies according to the surface modification strategies. Especially, the interfacial crosslinking approach developed in our previous studies is presented in detail.

Abstract Using natural language processing, it is possible to extract structured information from raw text in the electronic health record (EHR) at reasonably high accuracy. However, the accurate distinction between negated and non-negated mentions of clinical terms remains a challenge. EHR text includes cases where diseases are stated not to be present or only hypothesised, meaning a disease can be mentioned in a report when it is not being reported as present. This makes tasks such as document classification and summarisation more difficult. We have developed the rule-based EdIE-R-Neg, part of an existing text mining pipeline called EdIE-R (Edinburgh Information Extraction for Radiology reports), developed to process brain imaging reports, (https://www.ltg.ed.ac.uk/software/edie-r/) and two machine learning approaches; one using a bidirectional long short-term memory network and another using a feedforward neural network. These were developed on data from the Edinburgh Stroke Study (ESS) and tested on data from routine reports from NHS Tayside (Tayside). Both datasets consist of written reports from medical scans. These models are compared with two existing rule-based models: pyConText (Harkema et al. 2009. Journal of Biomedical Informatics42(5), 839–851), a python implementation of a generalisation of NegEx, and NegBio (Peng et al. 2017. NegBio: A high-performance tool for negation and uncertainty detection in radiology reports. arXiv e-prints, p. arXiv:1712.05898), which identifies negation scopes through patterns applied to a syntactic representation of the sentence. On both the test set of the dataset from which our models were developed, as well as the largely similar Tayside test set, the neural network models and our custom-built rule-based system outperformed the existing methods. EdIE-R-Neg scored highest on F1 score, particularly on the test set of the Tayside dataset, from which no development data were used in these experiments, showing the power of custom-built rule-based systems for negation detection on datasets of this size. The performance gap of the machine learning models to EdIE-R-Neg on the Tayside test set was reduced through adding development Tayside data into the ESS training set, demonstrating the adaptability of the neural network models.