{"id":10127,"date":"2014-05-29T11:31:48","date_gmt":"2014-05-29T18:31:48","guid":{"rendered":"http:\/\/nnlm.gov\/pnr\/dragonfly\/?p=10127"},"modified":"2026-02-03T16:50:03","modified_gmt":"2026-02-03T16:50:03","slug":"mesh-on-demand","status":"archive","type":"post","link":"https:\/\/news.nnlm.gov\/region_5\/mesh-on-demand\/","title":{"rendered":"MeSH On Demand"},"content":{"rendered":"<p>MeSH on Demand is a new tool announced in this month&#8217;s <a href=\"http:\/\/www.nlm.nih.gov\/pubs\/techbull\/mj14\/mj14_mesh_on_demand.html\">NLM Technical Bulletin<\/a>\u00a0and is available online for use: <a href=\"http:\/\/ii.nlm.nih.gov\/Interactive\/MeSHonDemand.shtml\">http:\/\/ii.nlm.nih.gov\/Interactive\/MeSHonDemand.shtml<\/a>. This is one of the <a href=\"http:\/\/lhncbc.nlm.nih.gov\/research-area\/natural-language-processing\">Natural Language Processing tools<\/a> being developed in the Cognitive Science Branch of the Lister Hill National Center for Biomedical Communications, a division of the NLM. The on Demand tool analyzes chunks of text (up to 10000 characters) and identifies potentially related MeSH terms. From the MeSH on Demand page a user simply pastes in a piece of text, hits the &#8220;Find MeSH Terms&#8221; button, and\u00a0a new page will be generated with suggested MeSH terms listed below the inputted\u00a0text. According to the Technical Bulletin article, the tool will find &#8220;MeSH Headings, Publication Types, and Supplementary Concepts, but not Qualifiers (Subheadings).&#8221;<\/p>\n<p>A disclaimer appears on the tool&#8217;s page that the results are generated via\u00a0an automated, machine logic driven system which is meant to emulate human indexer thought. One can deduce from the disclaimer that we shouldn&#8217;t expect the underlying algorithms to understand all of the same textual nuances that a seasoned indexer would and it notes that &#8220;results will undoubtedly differ from any human-generated indexing.&#8221; This got me wondering though about how much the tool&#8217;s generated terms would differ from human-generated ones. To evaluate, I pasted in an abstract from an article on <a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942\">Computerized Provider Order Entry systems causing medication errors<\/a>. \u00a0This was by no means meant as a methodical and thorough evaluation of MeSH on Demand. \u00a0Rather, this was simply meant to address personal curiosity and this particular article was selected using\u00a0a &#8220;convenience sampling&#8221; technique (it was already open in a different tab). \u00a0This article had previously been indexed for MEDLINE with the following MeSH terms:<!--more--><\/p>\n<ul style=\"color: #000000\">\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Clinical Pharmacy Information Systems\/standards*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Data Display<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Decision Support Systems, Clinical\/standards*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Group Processes<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Hospitals, Teaching<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Humans<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Medication Errors\/statistics &amp; numerical data*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Medication Systems, Hospital*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Questionnaires<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">Risk Assessment<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/15755942?log$=activity#\">User-Computer Interface<\/a><\/li>\n<\/ul>\n<p>MeSH on Demand meanwhile came up with the following after processing the article abstract:<\/p>\n<ul>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Focus Groups\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Focus%20Groups\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Focus Groups<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Humans\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Humans\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Humans<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Internship and Residency\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Internship%20and%20Residency\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Internship and Residency<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Male\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Male\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Male<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Medical Errors\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Medical%20Errors\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Medical Errors<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Medical Order Entry Systems\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Medical%20Order%20Entry%20Systems\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Medical Order Entry Systems<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Medication Errors\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Medication%20Errors\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Medication Errors<\/a><\/li>\n<\/ul>\n<p>The aboutness of medication errors comes through in both sets of MeSH terms, but on Demand introduces a personnel focus (particularly male?), possibly drawing from the described audience of who took the administered questionnaire, whereas the MEDLINE indexers focused on the relevancy of the questionnaire itself. \u00a0Anti-bacterial agents can be chalked up to the tool only having access to the abstract of the article, while\u00a0indexers who have\u00a0<a href=\"http:\/\/www.nlm.nih.gov\/bsd\/disted\/meshtutorial\/principlesofmedlinesubjectindexing\/theindexingprocess\/\">scanned the whole article\u00a0<\/a>know that while the word antibacterial appears in the abstract, the\u00a0<span style=\"color: #000000\">antibiotic renewal notices are just a small piece of a bigger information system discussion (hence, Decision Support Systems, Clinical\/standards* and Decision Support Systems, Clinical\/standards*).<\/span><\/p>\n<p>Users of MeSH on Demand aren&#8217;t limited to copying and pasting from the medical literature though. \u00a0I plugged in the first 10,000 characters of this New York Times article &#8220;<a href=\"http:\/\/www.nytimes.com\/2014\/05\/27\/science\/all-circuits-are-busy.html?ref=health\">All Circuits Are Busy<\/a>&#8221; about\u00a0a\u00a0neuroscience researcher determined to map the brian&#8217;s complete neural network. The results from on Demand for this article are interesting not because of the MeSH terms themselves so much as the number of them it generated: 36, plus one supplementary concept (<span style=\"color: #000000\">icodextrin). \u00a0Those familiar with MEDLINE subject\u00a0indexing may be surprised at this result, as a typical indexed journal article will have 6-15 terms. \u00a0<\/span><\/p>\n<p>Setting the tool&#8217;s disclaimer and discrepancies on the above test cases aside, one potential use for this tool is to identify possible MeSH terms for recently published articles of interest that are still listed as &#8220;in process&#8221; in PubMed.\u00a0 \u00a0An article I recently read that fits this bill is <a href=\"http:\/\/www.ploscompbiol.org\/article\/info:doi\/10.1371\/journal.pcbi.1003581\">one from PLOS Computational Biology<\/a> on using Wikipedia to detect flu trends (spoiler: Wikipedia article usage more accurately determined prevalence of flu-like illnesses than Google Flu trends). I pasted\u00a0the abstract for this article into MeSH on Demand and these MeSH terms were suggested:<\/p>\n<ul>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Humans\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Humans\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Humans<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Pandemics\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Pandemics\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Pandemics<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Population Surveillance\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Population%20Surveillance\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Population Surveillance<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: Seasons\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=Seasons\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">Seasons<\/a><\/li>\n<li><a style=\"color: #000000\" title=\"MeSH Browser: United States\" href=\"http:\/\/www.nlm.nih.gov\/cgi\/mesh\/2014\/MB_cgi?term=United%20States\" target=\"MeSH_Browser\" rel=\"noopener noreferrer\">United States<\/a><\/li>\n<\/ul>\n<p>These terms would be able to give me a starting place for searching for related literature, and they happen to\u00a0have a fair\u00a0amount of overlap with the terms generated by a human indexer on a similar, older\u00a0<a href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553\">article about using Google Flu Trends to look for flu outbreaks<\/a>:<\/p>\n<ul style=\"color: #000000\">\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">Centers for Disease Control and Prevention (U.S.)<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">Disease Outbreaks*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">Humans<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">Influenza, Human\/epidemiology*<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">Population Surveillance<\/a><\/li>\n<li><a style=\"color: #660066\" href=\"http:\/\/www.ncbi.nlm.nih.gov\/pubmed\/23037553#\">United States<\/a><\/li>\n<\/ul>\n<p><span style=\"color: #000000\">While\u00a0<\/span>this tool certainly has some further development in its future, it is currently a viable\u00a0tool for brainstorming MeSH terms to help build a\u00a0PubMed query.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>MeSH on Demand is a new tool announced in this month&#8217;s NLM Technical Bulletin\u00a0and is available online for use: http:\/\/ii.nlm.nih.gov\/Interactive\/MeSHonDemand.shtml. This is one of the Natural Language Processing tools being developed in the Cognitive Science Branch of the Lister Hill National Center for Biomedical Communications, a division of the NLM. The on Demand tool analyzes&#8230; <a href=\"https:\/\/news.nnlm.gov\/region_5\/mesh-on-demand\/\">Read More &raquo;<\/a><\/p>\n","protected":false},"author":54,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[6,8],"tags":[],"class_list":["post-10127","post","type-post","status-archive","format-standard","hentry","category-national-news","category-technology"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/posts\/10127","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/users\/54"}],"replies":[{"embeddable":true,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/comments?post=10127"}],"version-history":[{"count":5,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/posts\/10127\/revisions"}],"predecessor-version":[{"id":17269,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/posts\/10127\/revisions\/17269"}],"wp:attachment":[{"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/media?parent=10127"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/categories?post=10127"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/news.nnlm.gov\/region_5\/wp-json\/wp\/v2\/tags?post=10127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}