bims-librar 2020-09-27 papers

bims-librar

Biomed News

on Biomedical librarianship

Issue of 2020‒09‒27
fifteen papers selected by
Thomas Krichel
Open Library Society

Clinical informationist educational needs and goals: A scoping review.
Supporting the development of information literacy skills and knowledge in undergraduate nursing students: An integrative review.
Piloting a Course to Heighten Awareness of Consumer Health Resources to Nurses and Patient Educators.
Where are We Now in Providing Medical Information in the Digital Space? A Benchmark Survey of PhactMI™ Member Companies.
Reporting and Appraising Research Studies.
Online resources for platelet-rich plasma injections for orthopedic therapy: What are patients reading? A survey of Turkish websites.
What Information Are Patients Receiving from the Internet about the Operative and Nonoperative Management of Acute Appendicitis?
Evaluation of websites reached using Google in the modern digital era related to approach to cholesterol.
Online Health Resource Use by Individuals With Inflammatory Bowel Disease: Analysis Using the National Health Interview Survey.
Health information seeking behaviour using mobile devices among people with diabetes: A comparison between Middle and high income country.
Social and Demographic Patterns of Health-Related Internet Use Among Adults in the United States: A Secondary Data Analysis of the Health Information National Trends Survey.
Health Information Seeking as a Coping Strategy to Reduce Alzheimer's Caregivers' Stress.
Supporting Topic Modeling and Trends Analysis in Biomedical Literature.
BERTMeSH: Deep Contextual Representation Learning for Large-scale High-performance MeSH Indexing with Full Text.
TermInformer: unsupervised term mining and analysis in biomedical literature.

J Educ Health Promot. 2020 ;9 193

Clinical informationist educational needs and goals: A scoping review.

Mohammadreza Hashemian, Alireza Rahimi, Nikoo Yamani, Peyman Adibi, Firoozeh Zare-Farashbandi.

  Clinical informationist (CI) is one of the current trends in the field of medical librarianship and information science. CIs are members of clinical care teams, and their main duty is to fill the gap in the information needs of health-care workers and patients using information sources. They need an official and standard education. This study aims to identify the educational goals and needs of CIs. To this end, a scoping review was conducted using the Preferred Reporting Item for Systematic Reviews and Meta-analyses guidelines. The ISI Web of Science, Scopus, Proquest (MEDLINE), Science Direct, Emerald, ERIC, Cochrane, and Library, Information Science and Technology Abstracts were searched. The Journal of the European Association for Health Information and Libraries was hand searched for relevant studies. A total of 1026 studies were extracted, and 38 studies were selected for the final review. The review resulted in identifying 18 goals in cognitive, emotional, and psychomotor areas. Furthermore, the educational needs were identified in eight educational needs including research method and statistics, education, medical knowledge, information and librarianship science, clinical environment knowledge, evidence-based knowledge, information technologies and systems, management, and leadership. Although part of these educational needs can be met through general medical librarianship and information science education, further specialized education for CIs requires specific aims and curriculum. Thus, the results of this study can be the basis for future studies regarding the competencies of CI in order to provide a more precise and detailed curriculum based on these educational needs.

Keywords:  Education; information science; librarians; library science

DOI:  https://doi.org/10.4103/jehp.jehp_272_20
Nurse Educ Today. 2020 Sep 03. pii: S0260-6917(20)31435-0. [Epub ahead of print]95 104585

Supporting the development of information literacy skills and knowledge in undergraduate nursing students: An integrative review.

Margaret Purnell, Bernadette Royal, Lyndall Warton.

  BACKGROUND: Undergraduate nursing students have the opportunity to develop information literacy skills while at university so they can work effectively in an increasingly information-intensive clinical environment. This can be achieved through learning how to effectively search for required information, critically evaluate it, apply and reference it. Librarians working in academic libraries can assist with this essential skill development through library instruction, delivery and support.OBJECTIVES: The aim of this integrative review was to undertake an analysis of the peer-reviewed research in the context of library instruction programs delivered in undergraduate nursing courses. A synthesis of the key themes was also undertaken.
METHODS: This paper takes the form of an integrative review. Four library databases were systematically searched for research articles investigating 'library instruction' within 'undergraduate nursing' courses. The search strategy was based on synonyms for these two concepts.
RESULTS: A total of 26 articles based on 25 studies were identified for review. Research was undertaken in a number of different countries with the most being in the United States of America (8). Total participants were 2820 nursing students. Sixteen of the studies were a quantitative approach, three were qualitative and six were mixed methods. A range of data collection methods were used that included surveys, interviews, focus groups and an observational study. One study was a randomised controlled trial and one used a mixed methods final year thesis analysis. The year level of participants varied with most being in the first year of their course (12 studies). Six studies were a mix of year levels. The four key inter-related themes identified were: collaboration, course-integration, linking to assessments, and confidence.
CONCLUSION: There is evidence to suggest a positive relationship between library instruction and information literacy skill development. Sustained training and support across year levels provides the opportunity for positive student outcomes.

Keywords:  Information literacy; Library instruction; Literature review; Nursing students; Preregistration nurses; Undergraduate nurses

DOI:  https://doi.org/10.1016/j.nedt.2020.104585
J Consum Health Internet. 2019 ;23(2): 178-186

Piloting a Course to Heighten Awareness of Consumer Health Resources to Nurses and Patient Educators.

Lindsay Blake, Alice Jaggers.

  Through the library, patients and health professionals can interact with librarians to receive aid in searching and accessing consumer health literature on the internet. Patients are now seeking out consumer health resources and questioning health care providers. Academic health sciences librarians already play an important role in consumer health. They can also help health professionals with patient education by using a train the trainer model to teach nurses and patient educators about reliable and authoritative online resources. Two librarians at an academic health center created a course and online guide to walk participants through finding, navigating, and evaluating consumer health resources for their patients.

Keywords:  consumer health; nurses; outreach; patient education; patient educators

DOI:  https://doi.org/10.1080/15398285.2019.1614824
Ther Innov Regul Sci. 2020 Sep 25.

Where are We Now in Providing Medical Information in the Digital Space? A Benchmark Survey of PhactMI™ Member Companies.

Priya Patel, Rania Gaspo, Annamaria Crisan, Jung Lee, .

  OBJECTIVE: The Pharma Collaboration for Transparent Medical Information (phactMI™) benchmarking survey was conducted to evaluate the use of technology and websites associated with the medical information (MI) departments of 27 biopharmaceutical companies in the United States.METHODS: The e-survey was administered to phactMI™ members between December 2017 and February 2018 and included closed and open-ended questions with 7 distinct categories: existence of a MI website, content type available following a search query, website functions, search engine optimization (SEO), website traffic, internal communications/analytics, and additional technology capabilities.
RESULTS: Survey findings noted that 20 companies own a MI-specific website through which MI services are provided to healthcare providers (HCPs). When asked about the dissemination of MI content through varying formats, survey results indicated Portable Document Format (PDF) to be the most common (18/27), followed by videos (8/27), presentations (5/27), infographics (3/27), and Hypertext Markup Language (3/27). Many companies have a responsive design website (19/25), webform (24/25), and a 1-800 number (22/25) for MI services. Few companies have a live chat (10/25) or a chatbot (1/25) and 9 of 25 said that content is searchable on Google™. Although website traffic varied among companies, a significant driver of this appeared to be whether the site is indexed.
CONCLUSION: While most of the member companies have a MI website, there is significant room for improvement in content formats available as part of a search. Traditional website features, such as search functionality and webform, are commonly available on websites; however, newer technologies, such as chatbot and live chat, are less featured. Across most member companies, there is also a need for improvement in increasing website traffic, Google™ indexing, and SEO.

Keywords:  Benchmarking; Medical information; Pharmaceutical industry; Survey; Technology; Websites

DOI:  https://doi.org/10.1007/s43441-020-00222-3
J Pediatr Health Care. 2020 Sep 18. pii: S0891-5245(20)30230-3. [Epub ahead of print]

Reporting and Appraising Research Studies.

Regena Spratling, Donna Hallas.

  In today's fast-paced health care delivery system, new evidence for practice emerges on a daily basis, and research results are quickly disseminated. Nurse practitioners are challenged to evaluate the relevance of the evidence to their patient populations and whether clinical practice should be changed on the basis of the presenting evidence. Nurse researchers also need to report study findings in a relevant, organized, and scholarly manner using reporting guidelines. This paper discusses both critical appraisal checklists and reporting guidelines providing exemplars for using each of the available tools.

Keywords:  CASP critical appraisals checklist; nurse practitioners; reporting guidelines

DOI:  https://doi.org/10.1016/j.pedhc.2020.08.008
Jt Dis Relat Surg. 2020 ;pii: ehc.2020.72391. [Epub ahead of print]31(3): 582-588

Online resources for platelet-rich plasma injections for orthopedic therapy: What are patients reading? A survey of Turkish websites.

Bilgehan Çatal, Oğuzhan Çimen, Abdullah Demirtaş, İbrahim Azboy.

OBJECTIVES: This study aims to evaluate the quality, accuracy, and readability of Turkish online resources for platelet-rich plasma (PRP) injections for orthopedic therapy.PATIENTS AND METHODS: In this retrospective study, online searches using Google, Yandex, and Yahoo search engines were performed on 21-22-23 May 2019, respectively. "Platelet-rich plasma", "platelet-rich plasma treatment", "PRP", and "PRP treatment" were entered in Turkish into these three search engines. The first 50 websites from each search were collected. The quality and accuracy of online information related to PRP injections for orthopedic therapy were evaluated by three reviewers with the use of scoring criteria specific to PRP. The Flesch-Kincaid (FK) score was used to determine readability.
RESULTS: Eighty-six unique websites were evaluated. The average quality and accuracy scores of all websites were 7.1±4.3 out of a maximum of 25 points and 7.3±2 out of a maximum of 12 points, respectively. The average FK score of all websites was 10.8±2.2. Only 27 websites (31.4%) had a FK score that was at or below the eighth-grade level. There were no significant differences among the mean scores of websites categorized by search terms, search results ranking, owners or reading level for both quality and accuracy scores.
CONCLUSION: The information regarding PRP usage in orthopedic conditions provided by Turkish online resources has low quality and low accuracy ratings and is also difficult to read.

DOI: https://doi.org/10.5606/ehc.2020.72391
Dig Surg. 2020 Sep 24. 1-8

What Information Are Patients Receiving from the Internet about the Operative and Nonoperative Management of Acute Appendicitis?

Luke Conlon, Zarrukh Baig, Michael A J Moser.

  INTRODUCTION: Recent studies suggest that nonoperative management of appendicitis (NOMA) may be a reasonable option for managing uncomplicated acute appendicitis. We examined the Internet to see if patients are likely to find the information they need to make an informed decision between the 2 options.METHODS: A list of 29 search terms was established by a focus group and then entered into Google, resulting in 49 unique webpages, each reviewed by 3 reviewers. Consensus was obtained for bias (surgery, NOMA, or balanced), webpage type, JAMA score, reading grade, and DISCERN score, a measure of quality of written information for patients.
RESULTS: Thirty of the 49 websites (61%) favored surgery, while 13 (27%) favored NOMA, and 6 sites (12%) provided balanced information. Twelve of 49 sites (24%) did not list NOMA as an option. The majority of patient-directed (11/12 = 92%) and physician-directed (7/9 = 78%) webpages favored surgery, whereas academic webpages presented a more balanced distribution. Academic and physician-directed webpages ranked higher than commercial and news webpages (median ranks 3 and 4 vs. 7.5 and 8). Only 8/49 sites (16%) mentioned that the presence of a fecalith predicts the failure of NOMA. Reading grades were almost all well above the recommended grade 8 level.
CONCLUSION: Most of the webpages available on the Internet do not provide enough information, nor are they sufficiently understandable to allow most patients to make an informed decision about the current options for the management of acute appendicitis.

Keywords:  Antibiotics; Appendicitis; Nonoperative management; Online medical information

DOI:  https://doi.org/10.1159/000510383
Turk Kardiyol Dern Ars. 2020 Sep;48(6): 576-584

Evaluation of websites reached using Google in the modern digital era related to approach to cholesterol.

Mert İlker Hayıroğlu, Göksel Çinier, Nurgül Keser, Mehmet Uzun, Ali Karagoz, Ali Serdar Fak, Ertugrul Okuyan, Can Altundaş, Ilker Tekkesin.

OBJECTIVE: The Google search engine is widely used as a source of medical information; however, legal and medical governance of the accuracy of the content retrieved is lacking. The aim of this study was to assess the most read Turkish-language texts related to cholesterol during a specific period according to the validity of the content.METHODS: Google Trends was queried on January 5, 2019 for the search term 'cholesterol' and the 9 other most popular search phrases used in Turkey that included the word cholesterol. In all, 100 links were obtained for each phrase, generating a total of 1000 links. Once duplicates were eliminated, a total of 604 links was used for the study. Since there is currently no validation scoring system for this purpose in the literature, the authors created a checklist according to well-accepted recent guidelines focused on cholesterol. The content of the texts acquired was classified as misleading, insufficient but favorable, or sufficient and favorable.
RESULTS: The source of the online texts studied was universities (n=8, 1.3%), hospitals (n=6, 0.9%), personal blogs (n=200, 33.1%), health websites (n=183, 30.2%), and medical journals (n=207, 34.2%). In all, 235 texts (38.9%) were classified as sufficient and favorable and 35 (5.7%) were categorized as misleading. A medical practitioner was named in 378 texts (62.5%). All of the results from universities and hospitals were ranked in the favorable group. A statistical difference in the word count was seen in a comparison of the misleading and favorable texts.
CONCLUSION: Google can connect users to a significant quantity of material related to cholesterol that includes a wide range from misleading information to sufficient and favorable texts. The variation in the quality of the content on websites accessible via Google necessitates that cholesterol resource material should be selected with great care.

DOI: https://doi.org/10.5543/tkda.2020.40306
J Med Internet Res. 2020 Sep 24. 22(9): e15352

Online Health Resource Use by Individuals With Inflammatory Bowel Disease: Analysis Using the National Health Interview Survey.

Rong Yin, David M Neyens.

  BACKGROUND: The internet has enabled convenient and efficient health information searching which is valuable for individuals with chronic conditions requiring some level of self-management. However, there is little research evaluating what factors may impact the use of the internet for health-related tasks for specific clinical populations, such as individuals with inflammatory bowel diseases.OBJECTIVE: Our goal was to investigate the factors that influence internet use in acquiring health information by individuals with inflammatory bowel diseases. Specifically, we identified factors associated with internet searching behavior and using the internet for completing health-related tasks.
METHODS: We used 2016 National Health Interview Survey weighted data to develop logistic regression models to predict the likelihood that individuals with inflammatory bowel diseases would use the internet for 2 types of tasks: seeking health information through online searches and using the internet to perform health-related tasks including scheduling appointments and emailing care providers.
RESULTS: 2016 National Health Interview Survey weighted data include more than 3 million weighted adult respondents with inflammatory bowel diseases (approximately 1.29% of adults in the weighted data set). Our results suggest that approximately 66.3% of those with inflammatory bowel diseases reported using the internet at least once a day, and approximately 14.7% reported being dissatisfied with their current health care. About 62.3% of those with inflammatory bowel diseases reported that they had looked up health information online, 16.3% of those with inflammatory bowel diseases reported that they had scheduled an appointment with a health care provider online, and 21.6% reported having used a computer to communicate with a health provider by email. We found that women who were self-regulating their care were more likely to look up health information online than others. Both middle-aged and older adults with inflammatory bowel diseases who were unsatisfied with their current health care were less likely to look up health information online. Frequent internet users who were worried about medical costs were more likely to look up health information online. Similarly, the results from our statistical models suggest that individuals with inflammatory bowel diseases who were frequent internet users were more likely to use the internet for specific health-related tasks. Additionally, women with inflammatory bowel diseases who reported being married were less likely to use the internet for specific health-related tasks.
CONCLUSIONS: For those with inflammatory bowel diseases, there are additional socioeconomic and behavioral factors that impact the use of the internet for health information and health-related tasks. Future research should evaluate how these factors moderate the use of the internet and identify how online resources can support clinical populations in ways that improve access to information, support health self-management, and subsequently improve health outcomes.

Keywords:  National Health Interview Survey; access to information; inflammatory bowel disease; internet; logistic regression model; searching behavior

DOI:  https://doi.org/10.2196/15352
Digit Health. 2020 Jan-Dec;6:6 2055207620956457

Health information seeking behaviour using mobile devices among people with diabetes: A comparison between Middle and high income country.

Jason Wy Lee, Yin-Leng Theng, Shaun Wh Lee.

  Objective: The internet has become a primary source of information for many individuals especially those with chronic diseases. This study aims to understand and compare the health seeking behaviour using mobile devices among individuals with diabetes and between a high (Singapore) and middle (Malaysia) income country.Methods: A cross sectional survey was conducted among people with diabetes in Malaysia and Singapore. Participants attending the primary health clinic for the treatment of diabetes were approached to participate in this survey. Data on demographics, health status and beliefs to health were collected and compared.
Results: A total of 673 respondents were included in the study. Most of the respondents reported to have access to the Internet, with a high ownership of mobile phones (99.3%). However, only one in every three respondents sought information online. Younger individuals (≤50 years) and those with higher education more likely to seek information using mobile devices. Respondents in Singapore reported to be more likely to use mobile devices to monitor their health as compared to respondents in Malaysia. However, most respondents would seek health information from their healthcare professionals' especially physicians.
Conclusion: There was limited differences in the health-seeking behaviour among the respondents from both countries, suggesting for a need to identify for more effective means of distribution of health related information.

Keywords:  Type 2 diabetes; cross-sectional survey; health-seeking behaviour; m-health

DOI:  https://doi.org/10.1177/2055207620956457
Int J Environ Res Public Health. 2020 Sep 19. pii: E6856. [Epub ahead of print]17(18):

Social and Demographic Patterns of Health-Related Internet Use Among Adults in the United States: A Secondary Data Analysis of the Health Information National Trends Survey.

Rose Calixte, Argelis Rivera, Olutobi Oridota, William Beauchamp, Marlene Camacho-Rivera.

  National surveys of U.S. adults have observed significant increases in health-related internet use (HRIU), but there are documented disparities. The study aims to identify social and demographic patterns of health-related internet use among U.S. adults. Using data from the Health Information National Trends Survey (HINTS) 4 cycle 3 and HINTS 5 cycle 1, we examined HRIU across healthcare, health information seeking, and participation on social media. Primary predictors were gender, race/ethnicity, age, education, income, and nativity with adjustments for smoking and survey year. We used multivariable logistic regression with survey weights to identify independent predictors of HRIU. Of the 4817 respondents, 43% had used the internet to find a doctor; 80% had looked online for health information. Only 20% had used social media for a health issue; 7% participated in an online health support group. In multivariable models, older and low SES participants were significantly less likely to use the internet to look for a provider, use the internet to look for health information for themselves or someone else, and less likely to use social media for health issues. Use of the internet for health-related purposes is vast but varies significantly by demographics and intended use.

Keywords:  health communication; internet use; mobile health

DOI:  https://doi.org/10.3390/ijerph17186856
Health Commun. 2020 Sep 24. 1-10

Health Information Seeking as a Coping Strategy to Reduce Alzheimer's Caregivers' Stress.

Nia F Mason, Diane B Francis, Loretta L Pecchioni.

Individuals with Alzheimer's disease and other forms of dementia (referred to as AD) deteriorate over time, and there will likely be a corresponding increase in levels of burden and stress for caregivers. Despite the significant contributions made by informal caregivers, there are no widely available mechanisms that meet the information needs of informal caregivers. Using a qualitative approach, the current study focuses on AD caregiver information seeking. The study involved conducting interviews to answer the following research questions: (1) What motivating factors lead informal caregivers of people with AD to seek out information?; (2) Is there a relationship between information seeking and resulting perceived stress levels?; and (3) Why do informal caregivers choose to utilize certain resources more than others during their information seeking process? Findings revealed that caregivers' largest motivation for seeking information is to learn how to better care for their loved one. Caregivers tend to rely on mediated resources that they find credible, and interpersonal resources such as people with similar experiences to their own. Many participants were satisfied with information available, but others felt that their interactions with healthcare professionals created more stress and emotional anguish than anticipated. This study offers an initial step in finding ways to meet the needs of those who seek to mitigate their stress through information seeking. By studying the information needs of the caregiving population, healthcare workers and communicators will be more knowledgeable about the relationship between information seeking and stress and coping.

DOI: https://doi.org/10.1080/10410236.2020.1824665
J Biomed Inform. 2020 Sep 21. pii: S1532-0464(20)30197-0. [Epub ahead of print] 103574

Supporting Topic Modeling and Trends Analysis in Biomedical Literature.

Spyridon Kavvadias, George Drosatos, Eleni Kaldoudi.

  Topic modeling refers to a suite of probabilistic algorithms for extracting popular topics from a collection of documents. A common approach involves the use of the Latent Dirichlet Allocation (LDA) algorithm, and, although free implementations are available, their deployment in general requires a certain degree of programming expertise. This paper presents a user-friendly web-based application, specifically designed for the biomedical professional, that supports the entire process of topic modeling and comparative trends analysis of scientific literature. The application was evaluated for its efficacy and usability by intended users with no programming expertise (15 biomedical professionals). Results of evaluation showed a positive acceptance of system functionalities and an overall usability score of 76/100 in the System Usability Score (SUS) scale. This suggests that literature topic modeling can become more popular amongst biomedical professionals via the use of a user-friendly application that fully supports the entire workflow, thus opening new perspectives for literature review and scientific research.

Keywords:  Semantic Analysis; Topic Modeling; Trend Analysis; Visualization; Web Application

DOI:  https://doi.org/10.1016/j.jbi.2020.103574
Bioinformatics. 2020 Sep 25. pii: btaa837. [Epub ahead of print]

BERTMeSH: Deep Contextual Representation Learning for Large-scale High-performance MeSH Indexing with Full Text.

Ronghui You, Yuxuan Liu, Hiroshi Mamitsuka, Shanfeng Zhu.

MOTIVATION: With the rapid increase of biomedical articles, large-scale automatic Medical Subject Headings (MeSH) indexing has become increasingly important. FullMeSH, the only method for large-scale MeSH indexing with full text, suffers from three major drawbacks: FullMeSH 1) uses Learning To Rank (LTR), which is time-consuming, 2) can capture some pre-defined sections only in full text, and 3) ignores the whole MEDLINE database.RESULTS: We propose a computationally lighter, full-text and deep learning based MeSH indexing method, BERTMeSH, which is flexible for section organization in full text. BERTMeSH has two technologies: 1) the state-of-the-art pre-trained deep contextual representation, BERT (Bidirectional Encoder Representations from Transformers), which makes BERTMeSH capture deep semantics of full text. 2) a transfer learning strategy for using both full text in PubMed Central (PMC) and title and abstract (only and no full text) in MEDLINE, to take advantages of both. In our experiments, BERTMeSH was pre-trained with 3 million MEDLINE citations and trained on approximately 1.5 million full text in PMC. BERTMeSH outperformed various cutting edge baselines. For example, for 20K test articles of PMC, BERTMeSH achieved a Micro F-measure of 69.2%, which was 6.3% higher than FullMeSH with the difference being statistically significant. Also prediction of 20K test articles needed 5 minutes by BERTMeSH, while it took more than 10 hours by FullMeSH, proving the computational efficiency of BERTMeSH.
SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

DOI: https://doi.org/10.1093/bioinformatics/btaa837
Neural Comput Appl. 2020 Sep 16. 1-14

TermInformer: unsupervised term mining and analysis in biomedical literature.

Prayag Tiwari, Sagar Uprety, Shahram Dehdashti, M Shamim Hossain.

  Terminology is the most basic information that researchers and literature analysis systems need to understand. Mining terms and revealing the semantic relationships between terms can help biomedical researchers find solutions to some major health problems and motivate researchers to explore innovative biomedical research issues. However, how to mine terms from biomedical literature remains a challenge. At present, the research on text segmentation in natural language processing (NLP) technology has not been well applied in the biomedical field. Named entity recognition models usually require a large amount of training corpus, and the types of entities that the model can recognize are limited. Besides, dictionary-based methods mainly use pre-established vocabularies to match the text. However, this method can only match terms in a specific field, and the process of collecting terms is time-consuming and labour-intensive. Many scenarios faced in the field of biomedical research are unsupervised, i.e. unlabelled corpora, and the system may not have much prior knowledge. This paper proposes the TermInformer project, which aims to mine the meaning of terms in an open fashion by calculating terms and find solutions to some of the significant problems in our society. We propose an unsupervised method that can automatically mine terms in the text without relying on external resources. Our method can generally be applied to any document data. Combined with the word vector training algorithm, we can obtain reusable term embeddings, which can be used in any NLP downstream application. This paper compares term embeddings with existing word embeddings. The results show that our method can better reflect the semantic relationship between terms. Finally, we use the proposed method to find potential factors and treatments for lung cancer, breast cancer, and coronavirus.

Keywords:  Biomedical literature; GloVe; Sequence labelling; Term embeddings; Term mining; Unsupervised learning

DOI:  https://doi.org/10.1007/s00521-020-05335-2