Forty-two Million Ways to Describe Pain: Topic Modeling of 200,000 PubMed Pain-Related Abstracts Using Natural Language Processing and Deep Learning–Based Text Generation

• Published in: Pain medicine (Malden, Mass.) Vol. 21; no. 11; pp. 3133 - 3160
• Main Authors: Tighe, Patrick J, Sannapaneni, Bharadwaj, Fillingim, Roger B, Doyle, Charlie, Kent, Michael, Shickel, Ben, Rashidi, Parisa
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.11.2020
• Subjects: Clinical trials; Computational linguistics; Data mining; Deep Learning; Endometriosis; Female; General & Selected Populations Section; Humans; Language; Language processing; Machine learning; Medical research; Medicine, Experimental; Natural language interfaces; Natural Language Processing; Obstetrics; Pain; Placebos; PubMed; United States; Pain; Biomedical Informatics; Machine Learning; word2vec; Deep Learning; Natural Language Processing
• ISSN: 1526-2375; 1526-4637; 1526-4637
• DOI: 10.1093/pm/pnaa061

Abstract Objective Recent efforts to update the definitions and taxonomic structure of concepts related to pain have revealed opportunities to better quantify topics of existing pain research subject areas. Methods Here, we apply basic natural language processing (NLP) analyses on a corpus of >200,000 abstracts published on PubMed under the medical subject heading (MeSH) of “pain” to quantify the topics, content, and themes on pain-related research dating back to the 1940s. Results The most common stemmed terms included “pain” (601,122 occurrences), “patient” (508,064 occurrences), and “studi-” (208,839 occurrences). Contrarily, terms with the highest term frequency–inverse document frequency included “tmd” (6.21), “qol” (6.01), and “endometriosis” (5.94). Using the vector-embedded model of term definitions available via the “word2vec” technique, the most similar terms to “pain” included “discomfort,” “symptom,” and “pain-related.” For the term “acute,” the most similar terms in the word2vec vector space included “nonspecific,” “vaso-occlusive,” and “subacute”; for the term “chronic,” the most similar terms included “persistent,” “longstanding,” and “long-standing.” Topic modeling via Latent Dirichlet analysis identified peak coherence (0.49) at 40 topics. Network analysis of these topic models identified three topics that were outliers from the core cluster, two of which pertained to women’s health and obstetrics and were closely connected to one another, yet considered distant from the third outlier pertaining to age. A deep learning–based gated recurrent units abstract generation model successfully synthesized several unique abstracts with varying levels of believability, with special attention and some confusion at lower temperatures to the roles of placebo in randomized controlled trials. Conclusions Quantitative NLP models of published abstracts pertaining to pain may point to trends and gaps within pain research communities.