Topics and Trends Analysis in eHealth Literature
eHealth is an interdisciplinary research area that fosters application of informatics and communication technologies for the improvement of healthcare delivery. In this paper, we present an overall analysis of eHealth topics and trends in published litera
- PDF / 1,066,736 Bytes
- 4 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 196 Views
INTRODUCTION
eHealth is an interdisciplinary research area that fosters application of informatics and communication technologies for the improvement of healthcare delivery. In general, eHealth systems and services are applied to assist patients in managing their disease at home and to help healthcare givers to provide remotely health services (and not only) [1]. The MeSH controlled vocabulary (by National Library of Medicine, USA) classifies eHealth in the group of terms including telemedicine, telehealth and mobile health (mHealth). A number of recent reviews cover different areas of the field, for example service models [2,3] or specific diseases [4,5,6]. In this paper, we present an overall analysis of eHealth topics and trends in published literature indexed in PubMed, based on unsupervised topics modeling [7,8].
II.
METHODOLOGY
The analysis of eHealth literature trends followed a threestep approach. First, a generic PubMed query was used to build the corpus of published literature on eHealth. Then, main topics in the area of eHealth were identified via unsupervised topics modeling. Finally, trends were deduced based on the popularity of each topic per year.
© Springer Nature Singapore Pte Ltd. 2018 H. Eskola et al. (eds.), EMBEC & NBC 2017, IFMBE Proceedings 65, DOI: 10.1007/978-981-10-5122-7_141
A. Data collection The corpus of publications that represents the eHealth domain was identified via a PubMed query that was built to include the most generic terms pertaining to the field, including the top MeSH term of the category and its synonyms as defined in MeSH. The search terms were restricted to title (TI) or abstract (AB) [Note: MeSH term “telemedicine” explodes the search to include synonyms: telehealth, ehealth, mobile health, mhealth]: ("telemedicine"[MeSH Terms] OR "telemedicine"[TIAB] OR "ehealth"[TIAB]OR "e-health"[TIAB] OR "e*health"[TIAB] OR "tele-health"[TIAB] OR "telecare"[TIAB] OR "home monitoring"[TIAB] OR "telemonitoring"[TIAB])AND ("0001/01/01"[PDAT] : "2016/12/31"[PDAT]) The results of the query were exported as a XML file. The title, keywords and abstract of each publication was used to formulate the corpus for the topics modeling. B. Topic modeling Topic modeling algorithms are statistical methods that automatically extract topics from a large and unstructured collection of documents. In this work, we employ the algorithm of Latent Dirichlet Allocation (LDA) [7,8], as it has been shown to achieve highest precision in comparison to other topic modeling algorithms in corpora of Wikipedia and New York Times documents [9]. Furthermore, LDA has been successfully been applied in many other research areas, for example to analyze and classify genomic sequences [10], classify images based on visual words topic modeling [11], detect discussion themes in social networks [12] and analyze source code [13]. The LDA model assumes that each document is a mixture of topics. A topic is characterized by a collection of words, each word contributing with each own weight. A word can belong to multiple topi
Data Loading...
