NewsMeSH: A new classifier designed to annotate health news with MeSH headings

• Published in: Artificial intelligence in medicine Vol. 114; p. 102053
• Main Authors: Pita Costa, Joao, Rei, Luis, Stopar, Luka, Fuart, Flavio, Grobelnik, Marko, Mladenić, Dunja, Novalija, Inna, Staines, Anthony, Pääkkönen, Jarmo, Konttila, Jenni, Bidaurrazaga, Joseba, Belar, Oihana, Henderson, Christine, Epelde, Gorka, Gabaráin, Mónica Arrúe, Carlin, Paul, Wallace, Jonathan
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.04.2021
• Subjects: Big Data; Classification; COVID-19; COVID-19 - epidemiology; Diabetes; Diabetes Mellitus - epidemiology; Health Communication - standards; Healthcare; Humans; Medical Subject Headings; MEDLINE; MEDLINE - organization & administration; MEDLINE - standards; Mental health; Mental Health - statistics & numerical data; MeSH headings; Public health; PubMed; Research - organization & administration; SARS-CoV-2; Semantic technologies; Semantics; Text mining; Text mining; MEDLINE; COVID-19; MeSH headings; Mental health; Healthcare; Big data; Diabetes; Semantic technologies; PubMed; Public health
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2021.102053

•We present an automated text classifier based on the MEDLINE/MeSH thesaurus, for the classification of health news.•The classifier evaluates scientific text (ref annotated articles) and news (ref news articles annotated by experts).•This classifier is tailor-fit to public health and healthcare experts, in the light of their specific challenges and needs.•We focused on three domains: Coronavirus, Mental Health and Diabetes, considering the known relations between them. In the age of big data, the amount of scientific information available online dwarfs the ability of current tools to support researchers in locating and securing access to the necessary materials. Well-structured open data and the smart systems that make the appropriate use of it are invaluable and can help health researchers and professionals to find the appropriate information by, e.g., configuring the monitoring of information or refining a specific query on a disease. We present an automated text classifier approach based on the MEDLINE/MeSH thesaurus, trained on the manual annotation of more than 26 million expert-annotated scientific abstracts. The classifier was developed tailor-fit to the public health and health research domain experts, in the light of their specific challenges and needs. We have applied the proposed methodology on three specific health domains: the Coronavirus, Mental Health and Diabetes, considering the pertinence of the first, and the known relations with the other two health topics. A classifier is trained on the MEDLINE dataset that can automatically annotate text, such as scientific articles, news articles or medical reports with relevant concepts from the MeSH thesaurus. The proposed text classifier shows promising results in the evaluation of health-related news. The application of the developed classifier enables the exploration of news and extraction of health-related insights, based on the MeSH thesaurus, through a similar workflow as in the usage of PubMed, with which most health researchers are familiar.