Center Resources https://www.vumc.org/cpm/ en PheMAP–high-throughput Phenotyping by Measured, Automated Profile https://www.vumc.org/cpm/phemap <span class="field field--name-title field--type-string field--label-hidden">PheMAP–high-throughput Phenotyping by Measured, Automated Profile</span> <div class="field field--name-field-barista-posts-category field--type-entity-reference field--label-hidden field__items"> <div class="field__item"><a href="/cpm/cpm-blog?cat=64" hreflang="und">Center Resources</a></div> </div> <span class="field field--name-uid field--type-entity-reference field--label-hidden"><span lang="" about="/cpm/users/higbyfme-0" typeof="schema:Person" property="schema:name" datatype="">higbyfme</span></span> <span class="field field--name-created field--type-created field--label-hidden">Mon, 11/04/2019 - 14:42</span> <a href="/cpm/blog-post-rss/612" class="feed-icon" title="Subscribe to PheMAP–high-throughput Phenotyping by Measured, Automated Profile"> RSS: <i class="fa fa-rss-square"></i> </a> <div class="field field--name-field-barista-posts-author field--type-string field--label-hidden field__item">Neil Zheng, Wei-Qi Wei</div> <div class="clearfix text-formatted field field--name-body field--type-text-with-summary field--label-hidden field__item"><p>PheMAP is a general, automatic, and portable approach to enable accurate high-throughput phenotyping within electronic health records (EHR). PheMAP quantifies relationships between phenotypes and relevant clinical concepts represented by standard medical terminologies. For each individual, PheMAP assigns a score and probability of having a particular phenotype from identified related concepts within EHRs.</p> <p>We parsed phenotype descriptions from multiple publicly available resources (e.g.,MedlinePlus, MedicineNet, and Wikipedia) using natural language processing (NLP). We mapped the identified concepts to concept unique identifiers (CUIs) from the United Medical Language System (UMLS) and to codes of standard clinical terminologies(e.g., ICD-9-CM, ICD-10-CM, SNOMED CT, CPT, LOINC, and RxNorm). We then weighted each concept relative to a phenotype to reflect how important the concept is to the phenotype in a collection of all phenotype documents.</p> <p>PheMAP is available for free and is ready to be implemented for 1400 unique phenotypes with EHRs in the OMOP Common Data model. The knowledge base is provided for download as well as a Python script for calculating phenotype scores and phenotype probabilities.</p> <p>Please contact <a href="mailto:neil.zheng@vumc.org">neil.zheng@vumc.org</a> or <a href="mailto:wei-qi.wei@vumc.org">wei-qi.wei@vumc.org</a> with any questions.</p> <p><strong>Citation:</strong></p> <p>Zheng NS, Feng QP, Kerchberger VE, Zhao J, Edwards TL, Cox NJ, Stein CM, Roden DM, Denny JC, Wei WQ. PheMap: a Multi-resource Knowledgebase for High-throughput Phenotyping within Electronic Health Records. (Accepted for publication at Journal of American Medical Informatics Associations)</p> <p><strong>PheMap Knowledgebase Downloads<u>:</u></strong></p> <p><a href="https://phewascatalog.org/files/phemap/PheMap_Mapped_Terminologies_1.1.csv">PheMap_Mapped_Terminologies_1.1.csv</a> –The file contains weighted concepts mapped to standard medical terminologies, e.g.,ICDs, SNOMED CT, CPT, LOINC, and RxNorm.</p> <p><a href="https://phewascatalog.org/files/phemap/PheMap_UMLS_Concepts_1.1.csv">PheMap_UMLS_Concepts_1.1.csv</a> - The raw PheMap knowledge base containing weighted concepts mapped toCUIs from UMLS.</p> <p><a href="https://phewascatalog.org/files/phemap/ICD_to_Phecode_mapping.csv">ICD_to_Phecode_mapping.csv</a> - Mapping of ICD9CM and ICD10CM to phecode. Used in phemap_phenotyping.py.</p> <p><a href="https://phewascatalog.org/files/phemap/Phecode_Relationship.csv">Phecode_Relationship.csv</a> - The hierarchical relationship mapping between phecodes.Used in phemap_phenotyping.py.</p> <p><a href="https://phewascatalog.org/files/phemap/README.txt.zip">README.txt</a> –Description of data elements in the above files.</p> <p><strong>Scripts:</strong></p> <p><a href="https://phewascatalog.org/files/phemap/phemap_phenotyping.py.zip">phemap_phenotyping.py</a> – Python script that calculates PheMap phenotype score and probabilities for EHRs structured with OMOP Common Data Model. The script is meant to be run line-by-line.</p> <p><strong>Changelog:</strong></p> <p>PheMap v1.1(07/07/20)</p> <ul><li>Added Medscape as an additional resource for concept extraction and weighting.</li> <li>Improved article text to phecode mapping, increasing available unique phenotypes from 841 to 1400.</li> <li>Improved UMLS CUI to ICD mapping, capturing additional ICD diagnosis codes.</li> </ul><p>PheMap v1.0 (05/14/20)</p> <ul><li>First release of PheMap built from information from five publicly available resources: Mayo Clinic, MedlinePlus, MedicineNet, WikiDoc, Wikipedia.</li> <li>Contains PheMap quantified concepts for 841 phenotypes.</li> <li>Please refer to original paper for more details.</li> </ul></div> <div class="field field--name-field-lockdown-auth field--type-string field--label-above"> <div class="field__label">Lockdown Auth</div> <div class="field__item">1</div> </div> Mon, 04 Nov 2019 20:42:04 +0000 higbyfme 612 at https://www.vumc.org/cpm DEB2 https://www.vumc.org/cpm/deb2 <span class="field field--name-title field--type-string field--label-hidden">DEB2</span> <div class="field field--name-field-barista-posts-category field--type-entity-reference field--label-hidden field__items"> <div class="field__item"><a href="/cpm/cpm-blog?cat=63" hreflang="und">Software</a>, <a href="/cpm/cpm-blog?cat=64" hreflang="und">Center Resources</a></div> </div> <span class="field field--name-uid field--type-entity-reference field--label-hidden"><span lang="" about="/cpm/users/higbyfme-0" typeof="schema:Person" property="schema:name" datatype="">higbyfme</span></span> <span class="field field--name-created field--type-created field--label-hidden">Fri, 08/23/2019 - 13:16</span> <a href="/cpm/blog-post-rss/606" class="feed-icon" title="Subscribe to DEB2"> RSS: <i class="fa fa-rss-square"></i> </a> <div class="clearfix text-formatted field field--name-body field--type-text-with-summary field--label-hidden field__item"><p><strong>DEB2</strong> is a medication indication and adverse effect knowledgebase derived from five publicly available sources: the VA’s National Drug File-Reference Terminology, MEDLINE, the US Food and Drug Administration’s drug product labels (via the SIDER2 database), the MedlinePlus consumer health information website, and DrugBank, a manually-curated drug target database. All medications, indications, and adverse effects in DEB2 are represented using the RxNorm and SNOMED-CT terminologies.</p> <p>Indications and adverse effects in DEB2 were extracted from the constituent sources using natural language processing and other ontology methods. The DEB2 knowledgebase requires indications and adverse effects to be corroborated by two or more of its constituent drug information sources, resulting in improved accuracy and precision over the original <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3885918/">DEB1</a>, and other popular medication databases.</p> <p>The DEB2 Dataset contains 6431 indications and 11,539 adverse effects. It includes 1163 distinct drugs and 1601 distinct clinical features (symptoms, findings, diseases, etc.). Based on physician review, DEB2 has an estimated precision of 86% (+/- 3.1%) overall, with indications being slightly more accurate and adverse effects slightly less. Indications and adverse effects for the most commonly-prescribed medications were shown to have a precision of 94% (+/- 3.5%). Drug relationships found in more sources were generally found more likely to be correct.</p> <p>The DEB2 Full Data Superset is also available for download. It includes all drug-indication and drug-adverse effect pairs found in any of the five sources (including those found in only 1 source and therefore not corroborated elsewhere). The DEB2 Full Data Superset includes over 131,000 pairs (consisting of 31,203 indications and 98,745 adverse effects). While it was not reviewed separately, we suspect the superset should have a higher recall and lower precision than the primary DEB2 Dataset.</p> <p>DEB2 is available for free download. It is intended for research and is not a substitute for professional clinical advice. We believe this resource can be useful for research in the areas of pharmacovigilance, clinical data mining, clinical phenotyping, and clinical decision support systems, among others. It can be used unaltered, or as a valuable starting point for developing manually-curated indication and adverse effect datasets.</p> <p>Please cite the reference below when using this resource. Contact <a href="mailto:joshua.smith@vumc.org">joshua.smith@vumc.org</a> with any questions.</p> <p><b>*The DEB2 manuscript has been submitted for publication. If this website has not been updated with the correct reference, please contact me for instructions on how to cite DEB2 in your work.</b></p> <p><a href="#">Browse DEB2 online</a> [coming soon]</p> <p> </p> <p><b>Download links:</b></p> <p> </p> <p><a href="https://phewascatalog.org/files/deb2/DEB2.txt.zip">DEB2.txt</a> - The DEB2 knowledgebase, containing medication indications and adverse effects found in at least two sources. Tab-Separated text file; first line contains column names; double-quotes around any field values with commas.</p> <p><a href="https://phewascatalog.org/files/deb2/DEB2.xlsx.zip">DEB2.xlsx</a> - The DEB2 knowledegbase in Microsoft Excel format. Color-coded for human readability.</p> <p><a href="https://phewascatalog.org/files/deb2/DEB2_full_data_superset.txt.zip">DEB2_full_data_superset.txt</a> - The raw data superset from which DEB2 was constructed, containing medication indications and adverse effects found in any of the sources. The vast majority of drug-CF pairs in this file are from only one source. Tab-Separated text file; first line contains column names; double-quotes around any field values with commas.</p> <p><a href="https://phewascatalog.org/files/deb2/README.zip">README.txt</a> - description of data elements in the above files.</p> <p><br /> DEB2 by Dr. Joshua C. Smith, et al., is licensed under a <a href="http://creativecommons.org/licenses/by-nc-sa/4.0/" rel="license">Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License</a>.</p> <p><b>Reference:</b></p> <p>Smith JC, Chen Q, Denny JC, Roden DM, Johnson KB, Miller RA. <i>DEB2: An Improved Drug Evidence Base for Biomedical Research</i>. <b>Manuscript submitted for publication. Currently under review.</b></p> </div> <div> <strong>Tags</strong> <div> <div><a href="/cpm/cpm-blog?tag=11" hreflang="und">phenotyping</a></div> </div> </div> <div class="field field--name-field-lockdown-auth field--type-string field--label-above"> <div class="field__label">Lockdown Auth</div> <div class="field__item">1</div> </div> Fri, 23 Aug 2019 18:16:48 +0000 higbyfme 606 at https://www.vumc.org/cpm KMCI - KnowledgeMap Concept Indexer https://www.vumc.org/cpm/cpm-blog/kmci-knowledgemap-concept-indexer <span class="field field--name-title field--type-string field--label-hidden">KMCI - KnowledgeMap Concept Indexer</span> <div class="field field--name-field-barista-posts-category field--type-entity-reference field--label-hidden field__items"> <div class="field__item"><a href="/cpm/cpm-blog?cat=64" hreflang="und">Center Resources</a>, <a href="/cpm/cpm-blog?cat=63" hreflang="und">Software</a></div> </div> <span class="field field--name-uid field--type-entity-reference field--label-hidden"><span lang="" typeof="schema:Person" property="schema:name" datatype="">Visitor</span></span> <span class="field field--name-created field--type-created field--label-hidden">Fri, 08/07/2015 - 15:52</span> <a href="/cpm/blog-post-rss/344" class="feed-icon" title="Subscribe to KMCI - KnowledgeMap Concept Indexer"> RSS: <i class="fa fa-rss-square"></i> </a> <div class="clearfix text-formatted field field--name-body field--type-text-with-summary field--label-hidden field__item"><p>The KnowledgeMap Concept Indexer (KMCI) is the underlying natural language processing engine used in the KnowledgeMap and Learning Portfolio website, and has been used for many clinical and genomic research studies.  It identifies biomedical concepts, mapped to Unified Medical Language System concepts, from natural language documents and clinical notes.<br /><br />&#13; KMCI employs part-of-speech information to develop a shallow sentence parse, and performs variant generation and normalization using the SPECIALIST Lexicon and related tools. The KMCI system was designed particularly for poorly-formatted documents containing ad hoc abbreviations and underspecified concepts (e.g., the document phrase “ST” implying the “ST segment” of an electrocardiogram instead of abnormal finding “ST elevation”).  Using probabilistic information and concept co-occurrence data derived from PubMed, KMCI can map ambiguous strings such as “CHF” to the UMLS concept C0018802 “Congestive heart failure” in an echocardiogram report but to the concept C0009714 “Congenital hepatic fibrosis” in a document discussing infantile polycystic kidney disease (a genetically related condition to congenital hepatic fibrosis).<br /><br />&#13; KMCI has performed favorably in comparison to MetaMap and has been validated in a variety of clinical and education contexts (see publications).  Later additions to KMCI include the ability to detect negated terms (e.g., "no chest pain) via a Perl implementation of NegEx.   </p>&#13; &#13; <p> </p>&#13; &#13; <p>For further information, please contact <a href="mailto:josh.denny@vumc.org">Josh Denny</a></p>&#13; </div> <div class="field field--name-field-lockdown-auth field--type-string field--label-above"> <div class="field__label">Lockdown Auth</div> <div class="field__item">1</div> </div> Fri, 07 Aug 2015 20:52:37 +0000 Visitor 344 at https://www.vumc.org/cpm MEDI--an Ensemble MEDication Indication Resource https://www.vumc.org/cpm/cpm-blog/medi-ensemble-medication-indication-resource-0 <span class="field field--name-title field--type-string field--label-hidden">MEDI--an Ensemble MEDication Indication Resource</span> <div class="field field--name-field-barista-posts-category field--type-entity-reference field--label-hidden field__items"> <div class="field__item"><a href="/cpm/cpm-blog?cat=7" hreflang="und">Genomics/Pharmacogenomics</a>, <a href="/cpm/cpm-blog?cat=62" hreflang="und">PheWAS</a>, <a href="/cpm/cpm-blog?cat=64" hreflang="und">Center Resources</a>, <a href="/cpm/cpm-blog?cat=63" hreflang="und">Software</a></div> </div> <span class="field field--name-uid field--type-entity-reference field--label-hidden"><span lang="" typeof="schema:Person" property="schema:name" datatype="">Visitor</span></span> <span class="field field--name-created field--type-created field--label-hidden">Tue, 01/01/2013 - 00:00</span> <a href="/cpm/blog-post-rss/334" class="feed-icon" title="Subscribe to MEDI--an Ensemble MEDication Indication Resource"> RSS: <i class="fa fa-rss-square"></i> </a> <div class="clearfix text-formatted field field--name-body field--type-text-with-summary field--label-hidden field__item"><p>MEDI (MEDication Indication) is an ensemble medication indication resource for primary and secondary uses of electronic medical record (EMR) data.  MEDI was created based on multiple commonly used medication resources (RxNorm, MedlinePlus, SIDER 2, and Wikipedia ) and by leveraging both ontology and natural language processing (NLP) techniques. <br />&#13;  </p>&#13; &#13; <p>MEDI contains 3,112 medications and 63,343 medication-indication pairs. The MEDI high precision subset (MEDI-HPS) includes indications found within either RxNorm or at least two of the three other resources. MEDI-HPS contains ~13,400 unique indication pairs regarding 2,136 medications. The average (±standard deviation) number of indications for each medication in MEDI-HPS is 6.22±6.09. The mode for each medication is 2 while the median is 4. The estimated precision MEDI-HPS is &gt;92% based on physician review.<br /><br />&#13; The download of MEDI is for free. Right click and select the download linked file or similar option in your browser to save the files on your computer.</p>&#13; &#13; <p><a href="https://vumc.org/cpm/sites/vumc.org.cpm/files/public_files/MEDI_01212013.csv">MEDI.csv</a></p>&#13; &#13; <p><a href="https://vumc.org/cpm/sites/vumc.org.cpm/files/public_files/MEDI_01212013_HPS.csv">MEDI_HPS.csv</a> (High Precision Set)</p>&#13; &#13; <p><a href="https://www.vumc.org/cpm/sites/vumc.org.cpm/files/public_files/MEDI_11242015.csv">MEDI_UMLS.csv</a> (including RxCUI, UMLS, ATC, NDDF concepts and their indications)</p>&#13; &#13; <p><a href="https://vumc.org/cpm/sites/vumc.org.cpm/files/public_files/MEDI_wPrevalence_Published.csv">MEDI_wPrevalence_Published.csv</a></p>&#13; &#13; <p> </p>&#13; &#13; <p><img alt="88x31.png" src="https://www.vumc.org/cpm/sites/vumc.org.cpm/files/public_files/88x31.png" style="width:88px;height:31px;" /></p>&#13; &#13; <p>MEDI by Dr. Wei-Qi Wei &amp; Dr. Joshua Denny is licensed under a <a href="http://creativecommons.org/licenses/by-nc-sa/3.0/deed.en_US">Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License.</a><br /><br />&#13; Key references:<br />&#13; 1. WQ Wei, RM Cronin, H Xu, TA Lasko, L Bastarache, JC Denny, Development and evaluation of an ensemble resource linking medications to their indications, Journal of the American Medical Informatics Association. 2013;20:954-961 doi:10.1136/amiajnl-2012-001431<br />&#13; 2. WQ Wei, JD Mosley et al. Validation and Enhancement of a Computable Medication Indication Resource (MEDI) Using a Large Practice-based Dataset. AMIA Annual Symposium, 2013, Washington DC.</p>&#13; </div> <div class="field field--name-field-lockdown-auth field--type-string field--label-above"> <div class="field__label">Lockdown Auth</div> <div class="field__item">1</div> </div> Tue, 01 Jan 2013 06:00:00 +0000 Visitor 334 at https://www.vumc.org/cpm SecTag -- Tagging Clinical Note Section Headers https://www.vumc.org/cpm/cpm-blog/sectag-tagging-clinical-note-section-headers <span class="field field--name-title field--type-string field--label-hidden">SecTag -- Tagging Clinical Note Section Headers</span> <div class="field field--name-field-barista-posts-category field--type-entity-reference field--label-hidden field__items"> <div class="field__item"><a href="/cpm/cpm-blog?cat=64" hreflang="und">Center Resources</a>, <a href="/cpm/cpm-blog?cat=7" hreflang="und">Genomics/Pharmacogenomics</a>, <a href="/cpm/cpm-blog?cat=63" hreflang="und">Software</a></div> </div> <span class="field field--name-uid field--type-entity-reference field--label-hidden"><span lang="" typeof="schema:Person" property="schema:name" datatype="">Visitor</span></span> <span class="field field--name-created field--type-created field--label-hidden">Sun, 03/21/2010 - 00:00</span> <a href="/cpm/blog-post-rss/92" class="feed-icon" title="Subscribe to SecTag -- Tagging Clinical Note Section Headers"> RSS: <i class="fa fa-rss-square"></i> </a> <div class="clearfix text-formatted field field--name-body field--type-text-with-summary field--label-hidden field__item"><p>Clinical notes are often divided into sections, or segments, such as "history of present illness" or "past medical history." These sections often have subsections as well, such as the "cardiovascular exam" section of the "physical exam." One can gain greater understanding of clinical notes by recognition of the section in which a concept lives. For instance, both a "past medical history" and the "family medical history" sections can contain a list of diseases, but the context decribes very different import to the patient about whom the note was written. Section tagging is an important early step in natural language processing applications applied to clinical notes.</p>&#13; &#13; <p><span style="line-height: 1.428571429;">To improve recognition of section headers, we have developed </span>SecTag<span style="line-height: 1.428571429;">. </span>SecTag<span style="line-height: 1.428571429;"> recognizes note section headers using NLP, </span>Bayesian<span style="line-height: 1.428571429;">, spelling correction, and scoring techniques.  The algorithm can auto-train through multiple iterations on a single corpus.</span></p>&#13; &#13; <p>Since some codes are borrowed from Logical Observation Identifiers Names and Codes (LOINC®), users must have either a valid LOINC or UMLS license:</p>&#13; &#13; <p>LOINC license - visit <a href="http://loinc.org/downloads">http://loinc.org/downloads</a><br />&#13; UMLS license - <a href="http://www.nlm.nih.gov/databases/umls.html">http://www.nlm.nih.gov/databases/umls.html</a></p>&#13; &#13; <p><strong><u>Download SecTag vocabulary</u></strong></p>&#13; &#13; <p><a href="https://vumc.org/cpm/sites/vumc.org.cpm/files/public_files/sec_tag.zip">sec_tag.zip</a></p>&#13; &#13; <p> </p>&#13; &#13; <p><u><strong>Primary references</strong></u>:</p>&#13; &#13; <p>Denny JC, Spickard A 3rd, Johnson KB, Peterson NB, Peterson JF, Miller RA. <a href="http://www.ncbi.nlm.nih.gov/pubmed/19717800">Evaluation of a method to identify and categorize section headers in clinical documents</a>.J Am Med Inform Assoc. 2009 Nov-Dec;16(6):806-15.</p>&#13; &#13; <p><br />&#13; Denny JC, Miller RA, Johnson KB, Spickard A 3rd. <a href="http://www.ncbi.nlm.nih.gov/pubmed/18999303">Development and evaluation of a clinical note section header terminology</a>. AMIA Annu Symp Proc. 2008 Nov 6:156-60.</p>&#13; &#13; <p> </p>&#13; </div> <div> <strong>Tags</strong> <div> <div><a href="/cpm/cpm-blog?tag=34" hreflang="und">sectag</a>, <a href="/cpm/cpm-blog?tag=18" hreflang="und">NLP</a></div> </div> </div> <div class="field field--name-field-lockdown-auth field--type-string field--label-above"> <div class="field__label">Lockdown Auth</div> <div class="field__item">1</div> </div> Sun, 21 Mar 2010 05:00:00 +0000 Visitor 92 at https://www.vumc.org/cpm