One Hundred Years of Hypertension Research: Topic Modeling Study

Background Due to scientific and technical advancements in the field, published hypertension research has developed substantially during the last decade. Given the amount of scientific material published in this field, identifying the relevant information is difficult. We used topic modeling, which is a strong approach for extracting useful information from enormous amounts of unstructured text. Objective This study aims to use a machine learning algorithm to uncover hidden topics and subtopics from 100 years of peer-reviewed hypertension publications and identify temporal trends. Methods The titles and abstracts of hypertension papers indexed in PubMed were examined. We used the latent Dirichlet allocation model to select 20 primary subjects and then ran a trend analysis to see how popular they were over time. Results We gathered 581,750 hypertension-related research articles from 1900 to 2018 and divided them into 20 topics. These topics were broadly categorized as preclinical, epidemiology, complications, and therapy studies. Topic 2 (evidence review) and topic 19 (major cardiovascular events) are the key (hot topics). Most of the cardiopulmonary disease subtopics show little variation over time, and only make a small contribution in terms of proportions. The majority of the articles (414,206/581,750; 71.2%) had a negative valency, followed by positive (119, 841/581,750; 20.6%) and neutral valency (47,704/581,750; 8.2%). Between 1980 and 2000, negative sentiment articles fell somewhat, while positive and neutral sentiment articles climbed substantially. Conclusions The number of publications has been increasing exponentially over the period. Most of the uncovered topics can be grouped into four categories (ie, preclinical, epidemiology, complications, and treatment-related studies).