Evidence-Based Recommender System for a COVID-19 Publication Analytics Service

Abstract

The rapid growth of COVID-19 publications has driven clinical researchers and healthcare professionals in pursuit to reduce the knowledge gap on reliable information for effective pandemic solutions. The manual task of retrieving high-quality publications based on the evidence pyramid levels, however, presents a major bottleneck in researchers' workflows. In this paper, we propose an "evidencebased" recommender system namely, KnowCOVID-19 that utilizes an edge computing service to integrate recommender modules for data analytics using end-user thin-clients. The edge computing service features chatbot-based web interface that handles a given COVID-19 publication dataset using two recommender system modules: (i) evidence-based filtering that observes domain specific topics across the literature and classifies the filtered information according to a clinical category, and (ii) social filtering that allows diverse experts with similar objectives to collaborate via a "social plane" to jointly find answers to critical clinical questions to fight the pandemic. We compare the Domain-specific Topic Model (DSTM) used in our evidence-based filtering with state-of-the-art models considering the CORD-19 dataset (a COVID-19 publication archive) and show improved generalization effectiveness as well as knowledge pattern query effectiveness. In addition, we conduct a comparison study between a manual literature review process and the KnowCOVID-19 augmented process, and evaluate the benefits of our information retrieval techniques over important queries provided by COVID-19 clinical experts.

Deep learning: A taxonomy of modern weapons to combat Covid‐19 similar pandemics in smart cities

“…Figure 6 illustrates the proposed general taxonomy of the DL role in two categories: prevention and treatment. There are some excellent titles and sub‐applications 59–61 . Also, there are discriminative methods and generative methods for each sub‐application.…”

“…There are some excellent titles and sub-applications. [59][60][61] Also, there are discriminative methods and generative methods for each sub-application. Give an example, convolutional neural networks (CNN), 62 recurrent neural networks (RNN), 63 generative adversarial network (GAN), 64 auto encoders, 65 and restricted Boltzmann machines (RBM) 66 are essential methods in this section.…”

Science gateway adoption using plug‐in middleware for evidence‐based healthcare data management

“…In this work, our novelty is in the development of OnTimeEvidence, a next-generation science gateway that leverages an evidence-based filtering method 18 and a plug-in management middleware, namely, Vidura Advisor, for provisioning and managing of large collections of COVID-19…”

“…To simplify literature data selection and analysis for COVID-19 researchers, the components in the OnTimeEvidence cater to data consumers' needs by generating indicative responses to clinical queries that allows them to reduce the manual steps in their scientific workflows. The 50 We detail the AI-based plug-in modules that have been integrated within OnTimeEvidence that include: evidence-based filtering, 18 social filtering, and Vidura Advisor 4 :…”

“…54 The recommender modules include the evidence-based filtering using the DSTM 19 and social filtering 55 adopted from our prior work. 18 Figure 8 illustrates the process to configure middleware components to add and execute the different microservices. The steps for a science gateway data provider to customize plug-in management modules for a given science gateway are as follows:…”