Trends in major intensive care medicine journals: A machine learning approach

• Published in: Journal of critical care Vol. 72; p. 154163
• Main Authors: Popoff, Benjamin, Occhiali, Émilie, Grangé, Steven, Bergis, Alexandre, Carpentier, Dorothée, Tamion, Fabienne, Veber, Benoit, Clavier, Thomas
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2022; Elsevier Limited
• Subjects: Algorithms; Application programming interface; Artificial intelligence; Bibliometrics; Critical Care; Data mining; Humans; Intensive care; Machine Learning; Medicine; Natural language processing; Periodicals as Topic; Semantics; Severe acute respiratory syndrome coronavirus 2; Trends; AJRCCM; CC; MEDLINE; EJICM; Intensive care; JN; LRM; LDA; HTTP; CCM; ER; STM; ICM; NLP; Bibliometrics; Machine learning; JCR; NCBI; Natural language processing; API; AIC; IF
• ISSN: 0883-9441; 1557-8615
• DOI: 10.1016/j.jcrc.2022.154163

Intensive care medicine (ICM) has the particularity of being a multidisciplinary specialty and its literature reflects this multidisciplinarity. However, the proportion of each field in this literature and its trend dynamics are not known. The objective of this study was to analyze the ICM literature, extract latent topics and search for the presence of research trends. Abstracts of original articles from the top ICM journals, from their inception until December 31st, 2019, were included. This corpus was fed into a structural topic modeling algorithm to extract latent semantic topics. The temporal distribution was then analyzed and the presence of trends was searched by Mann-Kendall trends tests. Finally, 49,276 articles from 10 journals were included. After topic modeling analysis and experts' feedback, 124 research topics were selected and labeled. Topics were categorized into 19 categories, the most represented being respiratory, fundamental and neurological research. Increasing trends were observed for research on mechanical ventilation and decreasing trends for cardiopulmonary resuscitation. This study reviewed all articles from major ICM journals in a comprehensive way. It provides a better understanding of ICM research landscape by analyzing the temporal evolution of latent research topics in the ICM literature. •Research in intensive care is multidisciplinary and covers a wide range of topics.•Topic modeling, a machine learning algorithm, allows the extraction of latent research topics from published articles.•Respiratory topics represent an important part of intensive care research and has an increasing trend.•Resuscitation research has a declining publication trend.