Search

Neural network models enjoy success on language tasks related to Web documents, including news and Wikipedia articles. However, the characteristics of scientific publications pose specific challenges that have yet to be satisfactorily addressed: the discourse structure of scientific documents crucial in scholarly document processing (SDP) tasks, the interconnected nature of scientific documents, and their multimodal nature. We survey modern neural network learning methods that tackle these challenges: those that can model discourse structure and their interconnectivity and use their multimodal nature. We also highlight efforts to collect large-scale datasets and tools developed to enable effective deep learning deployment for SDP. We conclude with a discussion on upcoming trends and recommend future directions for pursuing neural natural language processing approaches for SDP., (© The Author(s) 2023.)

Background: Health 2.0 allows patients and caregivers to conveniently seek medical information and advice via e-portals and online discussion forums, especially regarding potential drug side effects. Although online health communities are helpful platforms for obtaining non-professional opinions, they pose risks in communicating unreliable and insufficient information in terms of quality and quantity. Existing methods in extracting user-reported adverse drug reactions (ADRs) in online health forums are not only insufficiently accurate as they disregard user credibility and drug experience, but are also expensive as they rely on supervised ground truth annotation of individual statement. We propose a NEural ArchiTecture for Drug side effect prediction (NEAT), which is optimized on the task of drug side effect discovery based on a complete discussion while being attentive to user credibility and experience, thus, addressing the mentioned shortcomings. We train our neural model in a self-supervised fashion using ground truth drug side effects from mayoclinic.org. NEAT learns to assign each user a score that is descriptive of their credibility and highlights the critical textual segments of their post., Results: Experiments show that NEAT improves drug side effect discovery from online health discussion by 3.04% from user-credibility agnostic baselines, and by 9.94% from non-neural baselines in term of F 1 . Additionally, the latent credibility scores learned by the model correlate well with trustworthiness signals, such as the number of "thanks" received by other forum members, and improve credibility heuristics such as number of posts by 0.113 in term of Spearman's rank correlation coefficient. Experience-based self-supervised attention highlights critical phrases such as mentioned side effects, and enhances fully supervised ADR extraction models based on sequence labelling by 5.502% in terms of precision., Conclusions: NEAT considers both user credibility and experience in online health forums, making feasible a self-supervised approach to side effect prediction for mentioned drugs. The derived user credibility and attention mechanism are transferable and improve downstream ADR extraction models. Our approach enhances automatic drug side effect discovery and fosters research in several domains including pharmacovigilance and clinical studies.

Crucial study data in research articles, such as patient details, study design and results, need to be extracted and presented explicitly for the ease of applicability and validity judgment in evidence-based practice. To perform this extraction, we propose to use two soft classifications, one at the sentence level and the other at the word level, and exploit the correlations between them for better accuracy. Our evaluation results show that propagating the results from the first classification to second improves performance of the second and vice versa. Moreover, the two classifications may benefit each other and help improve performance through joint inference algorithms. Another key finding of our work is that irrelevant sentences in the training data need to be properly filtered out; otherwise they compromise system accuracy and make joint inference models less scalable and more expensive to train.

We propose to collect freely available articles from the web to build an evidence-based practice resource collection with up-to-date coverage, and then apply automated classification and key information extraction on the collected articles to provide means for sounder relevance judgments. We implement these features into a dual-interface system that allows users to choose between an active or passive information seeking process depending on the amount of time available.

The search for applicable and valid research evidence-based practice articles is not supported well in common EBP resources, as some crucial study data, such as patient details, study design and results, are not available or presented explicitly. We propose to extract these data from research articles using a two-step supervised soft classification method. Compared to manual annotation, our approach is less labor-intensive and more flexible, hence opening up the possibility of utilizing these data to facilitate the evidence selection process in information seeking support systems.

Nursing demands that all care offered to patients is appropriately assessed, delivered and evaluated; the care offered must be up to date and supported by adequately researched published evidence. A basic logic suggests that information and communications technology can help the nurse in maintaining his/her care provision to the highest level through presenting relevant evidence. The nursing need for evidence to support the delivery of care is a global phenomenon. Within the project this is demonstrated by the fact that the project lead is resident in England and the project is being carried out in Singapore with the help of the National University Hospital, the Alice Lee Centre of Nursing Studies and the School of Computing at the National University of Singapore. The project commenced in January 2008, this paper will present the background thinking to the project design and will describe the outcomes which will provide nurses with individual supportive evidence for their practice gleaned from quality assured sources. The project will use information and communications technology to provide the evidence on an individual basis. The paper will outline the four key elements of the project, these being the development of user (professional) profiles; the design and development of an automatic crawler search engine to deliver quality assured evidence sources and software design; there will be some mention of hardware design and maintenance which is the fourth key element. Within the paper, consideration will be given to the added value of the project to the nurses, their patients/clients, the research agenda and the employing organisation: The drive for information is determined by the nurses in clinical and community practice. Evidence available immediately at the point of intervention with patient/client. No patient information stored within structure. All technology and almost all support software already available. Additional information can flow both ways for quality and activity audits. Identification of areas weak in evidence requiring supportive research will be driven by practice. Immediate dissemination of new generic practices and principles can be delivered to each nurse on syncopation, removing the requirements for paper updates etc. Process can be transferred across all healthcare clinical professions In conclusion, information will be given on progress to date in terms of technical applicability and user acceptance by the nursing staff. In addition, an insight will be given as to managing a multiprofessional, multi-organisational project from a distance.