Automation of literature screening using machine learning in medical evidence synthesis: a diagnostic test accuracy systematic review protocol

Background Systematic review is an indispensable tool for optimal evidence collection and evaluation in evidence-based medicine. However, the explosive increase of the original literatures makes it difficult to accomplish critical appraisal and regular update. Artificial intelligence (AI) algorithms have been applied to automate the literature screening procedure in medical systematic reviews. In these studies, different algorithms were used and results with great variance were reported. It is therefore imperative to systematically review and analyse the developed automatic methods for literature screening and their effectiveness reported in current studies. Methods An electronic search will be conducted using PubMed, Embase, ACM Digital Library, and IEEE Xplore Digital Library databases, as well as literatures found through supplementary search in Google scholar, on automatic methods for literature screening in systematic reviews. Two reviewers will independently conduct the primary screening of the articles and data extraction, in which nonconformities will be solved by discussion with a methodologist. Data will be extracted from eligible studies, including the basic characteristics of study, the information of training set and validation set, and the function and performance of AI algorithms, and summarised in a table. The risk of bias and applicability of the eligible studies will be assessed by the two reviewers independently based on Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Quantitative analyses, if appropriate, will also be performed. Discussion Automating systematic review process is of great help in reducing workload in evidence-based practice. Results from this systematic review will provide essential summary of the current development of AI algorithms for automatic literature screening in medical evidence synthesis and help to inspire further studies in this field. Systematic review registration PROSPERO CRD42020170815 (28 April 2020).

PENINGKATAN LAYANAN PERPUSTAKAAN IPDN KAMPUS JAKARTA MELALUI SISTEM PERPUSTAKAAN DIGITAL

Digital library system is an application of information technology that keep, obtain and disseminate the scientific information in digital format. In a simple analogy, it is a place to keep the digital library collections. Currently, Campus IPDN Jakarta Library does not yet have a digital library system due to the lack of attention from the leadership, limited budget, and lack of human resources who manage the library. The constraints faced by the Campus IPDN Jakarta Library have led to a decline in lending services, reference services, information retrieval services, and Internet services. To overcome it, a digital library system is needed in Campus IPDN Jakarta Library environment. This requires the adequate facilities and infrastructure, human resources who master technology, and an adequate budget. ABSTRAKSistem perpustakaan digital adalah penerapan teknologi informasi sebagai sarana untuk menyimpan, mendapatkan dan menyebarluaskan informasi ilmu pengetahuan dalam format digital. Atau secara sederhana dapat dianalogikan sebagai tempat menyimpan koleksi perpustakaan yang sudah dalam bentuk digital. Saat ini, Perpustakaan IPDN Kampus Jakarta belum memiliki sistem perpustakaan digital dikarenakan kurangnya perhatian Pimpinan, terbatasnya anggaran, dan kurangnya Sumber Daya Manusia yang mengelola perpustakaan. Kendala yang dihadapi Perpustakaan IPDN Kampus Jakarta ini menyebabkan menurunnya layanan peminjaman, layanan referensi, layanan Penelusuran Informasi, dan layanan Internet. Untuk mengatasi ini, diperlukan sistem perpustakaan digital di lingkungan Perpustakan Kampus Jakarta. Hal ini memerlukan sarana dan prasarana yang memadai, sumber daya manusia yang menguasai teknologi, dan anggaran yang mencukupi.

Digital library services to support online learning amid COVID-19: a study of a private university library in Bangladesh

Purpose The purpose of this paper is to discuss the East West University Library’s (EWUL’s) response to COVID-19 situation through their transformation to digital services. The paper tries to explain how these digital library services support the user community of East West University (EWU) in online teaching and access to information resources. Design/methodology/approach This paper describes the EWUL’s several digital services that are used to meet the needs of its user community during the COVID-19 pandemic. The reflective practice approach has been undertaken for this study on the basis of the authors’ personal experiences working at an academic library. The authors used the reflective practice approach to assess the library’s practice during crisis situation, make the use of technological interventions in service providing and also to re-innovate the digital services for future. Findings During the pandemic, the library shifted all the possible physical or on-site services to digital services, i.e. online resource facilities and remote access to these, federated searching, Web online public access catalog, engaging users through social media, specialized knowledge space, online document delivery, article on request, information literacy training, virtual reference service, etc. The user engagement in all these services is also notable. Research limitations/implications The nature of this study is limited to the COVID-19 pandemic and within a particular geographic location. Practical implications This paper has implications and possible applications for other university libraries in developing countries, which intends to transform their services into digital for ensuring better service quality for their respective user community. Originality/value This paper makes a valuable contribution to the literature on how a private university library of a developing country is responding to pandemics such as COVID-19.

Accessibility and Usability Evaluation of Digital Library Article Pages

This study aims to present an exploratory study about the accessibility and usability evaluation of digital library article pages. For this purpose, four widely known digital libraries (DLs), namely Science Direct, Institute of Electric and Electronic Engineering Xplore, Association for Computing Machinery, and SpringerLink, were examined. In the first stage, article web interfaces of these selected DLs were analyzed based on standard web guidelines using automatic evaluation tools to assess their accessibility. In the second stage, to evaluate the usability of these web interfaces, eye-tracking experiments with 30 participants were conducted. Obtained results of the analysis show that article pages of digital libraries are not of free of accessibility and usability problems. Overall, this study highlights accessibility and usability problems of digital library article interfaces, and these findings can provide the feedback to web developers in making their article pages more accessible and usable for their users.

Gender Diversity and Financial Risk

This chapter intends to contribute to the analysis of gender diversity and financial risk through a bibliometric review of the existent literature to understand the current state of financial risk research as well as to contribute to the analysis of the influence of gender diversity on financial risk. Although there is extensive research on financial risk, no recent study tries to update the current state of the research over the influence of gender on financial risk practices. This chapter describes the evolutional research studies published in the digital library Scopus, between 2010 and June 2021, and compares the results obtained in evolutionary terms. When the research is concentrated on the bibliometric analysis in the Scopus database and the keyword “financial risk,” it leads to a total of 15,979 documents. Regarding the analysis concentrated on the keywords “gender diversity” and “financial risk” for the period between 2010 and June 2021, the authors end with a final sample of 96 documents. Proposals for further research are provided based on the current state of the art.

The Computer Will See You Now: A Scoping Review of Digital Tools Designed to Obtain the History of Present Illness from Patients (Preprint)

BACKGROUND Many medical conditions—perhaps 80% of them—can be diagnosed by taking a thorough history of present illness (HPI). In the clinical setting, however, situational factors such as interruptions and time pressure may cause interactions with patients to be brief and/or fragmented. One solution for improving clinicians’ ability to collect a thorough HPI and maximize efficiency and quality of care could be to use a digital tool to obtain the HPI prior to face-to-face evaluation by a clinician. OBJECTIVE Our objective was to identify and characterize digital tools that have been designed to (1) obtain the history of present illness (HPI) directly from patients or caregivers and (2) present this information to clinicians before a face-to-face encounter. We also sought to describe outcomes reported in testing of these tools, especially those related to usability, efficiency, and quality of care. METHODS We conducted a scoping review using pre-defined search terms in the following databases: MEDLINE, CINAHL, PsychInfo, Web of Science, Embase, IEEE Digital Library, ACM Digital Library, and ProQuest Dissertations. Two reviewers screened titles and abstracts for relevance, performed full-text reviews of articles meeting inclusion criteria, and used a pile sorting procedure to identify distinguishing characteristics of the tools. Information describing the tools was primarily obtained from identified peer-reviewed sources; supplementary information was also obtained from tool websites and through direct communications with tool creators. RESULTS We identified 18 tools meeting inclusion criteria. Among them, 14 tools used primarily close-ended and/or multi-choice questions, 1 tool used free-text input, and 3 used conversational (chatbot) style. In total, 10 tools were tailored to specific patient subpopulations, and 8 did not specify a target subpopulation. Seven tools included multilingual support, and 12 had the capability to transfer data directly into the electronic health record. Studies of the tools reported on various outcome measures related to usability, efficiency, and/or quality of care. CONCLUSIONS The 18 HPI tools we identified varied greatly in their purpose and functionality. There was no consensus on how patient-generated information should be collected or presented to clinicians. Existing tools have undergone inconsistent levels of testing with a wide variety of different outcome measures used in evaluation, including some related to usability, efficiency, and quality of care. There is substantial interest in using digital tools to obtain the HPI from patients, but the outcomes measured have been inconsistent. Future research should focus on whether using HPI tools can lead to improved patient experience and health outcomes. CLINICALTRIAL N/A

Social Robots for the Care of Persons with Dementia

Intelligent assistive robots can enhance the quality of life of people with dementia and their caregivers. They can increase the independence of older adults, reduce tensions between a person with dementia and their caregiver, and increase social engagement. This article provides a review of assistive robots designed for and evaluated by persons with dementia. Assistive robots that only increased mobility or brain-computer interfaces were excluded. Google Scholar, IEEE Digital Library, PubMed, and ACM Digital Library were searched. A final set of 53 articles covering research in 16 different countries are reviewed. Assistive robots are categorized into five different applications and evaluated for their effectiveness, as well as the robots’ social and emotional capabilities. Our findings show that robots used in the context of therapy or for increasing engagement received the most attention in the literature, whereas the robots that assist by providing health guidance or help with an activity of daily living received relatively limited attention. PARO was the most commonly used robot in dementia care studies. The effectiveness of each assistive robot and the outcome of the studies are discussed, and particularly, the social/emotional capabilities of each assistive robot are summarized. Gaps in the research literature are identified and we provide directions for future work.