--- title: "PARAFAC2 tensor factorization on EHR audit data and PCP work | Sutter Health" description: "Results demonstrate that EHR audit log data can be rapidly processed to create higher-level constructed features that represent time-stamped PCP tasks." url: "https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822" --- 1. [Home](https://www.sutterhealth.org/) / 2. [Research](https://www.sutterhealth.org/research) / 3. [Research publications](https://www.sutterhealth.org/research/publications) / 4. PARAFAC2 tensor factorization on EHR audit data and PCP work # Using the PARAFAC2 tensor factorization on EHR audit data to understand PCP desktop work. Perros I, Yan X, Jones JB, Sun J, & Stewart WF. _J Biomed Inform. 101:103312. doi: 10.1016/j.jbi.2019.103312. Epub 2019 Oct 15._ 2020-01-01 ## Abstract Background: Activity or audit log data are required for EHR privacy and security management but may also be useful for understanding desktop workflow. Objective: We determined if the EHR audit log file, a rich source of complex time-stamped data on desktop activities, could be processed to derive primary care provider (PCP) level workflow measures. Methods: We analyzed audit log data on 876 PCPs across 17,455 ambulatory care encounters that generated 578,394 time-stamped records. Each individual record represents a user interaction (e.g., point and click) that reflects all or part of a specific activity (e.g., order entry access). No dictionary exists to define how to combine clusters of sequential audit log records to represent identifiable PCP tasks. We determined if PARAFAC2 tensor factorization could: (1) learn to identify audit log record clusters that specifically represent defined PCP tasks; and (2) identify variation in how tasks are completed without the need for ground-truth labels. To interpret the result, we used the following PARAFAC2 factors: a matrix representing the task definitions and a matrix containing the frequency measure of each task for each encounter. Results: PARAFAC2 automatically identified 4 clusters of audit log records that represent 4 common clinical encounter tasks: (1) medications' access, (2) notes' access, (3) order entry access, and (4) diagnosis modification. PARAFAC2 also identified the most common variants in how PCPs accomplish these tasks. It discovered variation in how the notes' access task was done, including identification of 9 distinct variants of notes access that explained 77% of the input data variation for notes. The discovered variants mapped to two known workflows for notes' access and to two distinct PCP user groups who accessed notes by either using the Visit Navigator or the Wrap-Up option. Conclusions: Our results demonstrate that EHR audit log data can be rapidly processed to create higher-level constructed features that represent time-stamped PCP tasks. [PubMed abstract](https://pubmed.ncbi.nlm.nih.gov/31627022/) ![J.B. Jones, Ph.D., MBA](https://dyn.mktgcdn.com/p/rIQfkoa5XfKJYCHSVrDKsACQSNJ7jTljZTHKC4Lae2E/fit=crop,gravity=auto,dpr=2,width=188,height=250,quality=100) J.B. Jones, Ph.D., MBA Principal investigator [View profile](https://www.sutterhealth.org/research/investigators/jb-jones-phd-mba-1049680984) ![Xiaowei (Sherry) Yan, Ph.D.](https://dyn.mktgcdn.com/p/NTWox_hkmxIRiqJEc5PXKeBkfR_WMtpSQbEI4J69Xls/fit=crop,gravity=auto,dpr=2,width=188,height=250,quality=100) Xiaowei (Sherry) Yan, Ph.D. Principal investigator [View profile](https://www.sutterhealth.org/research/investigators/xiaowei-sherry-yan-phd-1049681042) ## Research topics - [Medical Informatics](https://www.sutterhealth.org/research-search-results?query=%22%5C%22Medical+Informatics%5C%22%22) ## Related publications [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) - Publication ### [NIH-Academia-Industry Workshop on Healthcare Intelligence Innovation.](https://www.sutterhealth.org/research/publications/nih-workshop-healthcare-intelligence-innovation-1055312779) Tai-Seale M. Carnegie Mellon University Silicon Valley campus website. 2010 Oct 04 - Publication ### [The human resource costs of implementing autopend clinical decision support to improve health maintenance.](https://www.sutterhealth.org/research/publications/hr-costs-to-implement-autopend-clinical-decision-support-1055312855) Panattoni L, Stults CD, Chan AS, Tai-Seale M. Am J Manag Care. 26(7):e232-e236. doi: 10.37765/ajmc.2020.43766. 2020 Jul 01 - Publication ### [Pragmatic study of clinician use of a personalized patient decision aid integrated into the electronic health record: an 8-year experience.](https://www.sutterhealth.org/research/publications/clinician-use-of-patient-decision-aid-integrated-into-ehr-1055312641) Coylewright M, Keevil JG, Xu K, Dodge SE, Frosch D, Field ME. Telemed J E Health. doi: 10.1089/tmj.2019.0112. \[Epub ahead of print\] 2019 Aug 05 - Publication ### [Multiple locations of advance care planning documentation in an electronic health record: are they easy to find?](https://www.sutterhealth.org/research/publications/advance-care-planning-documents-in-ehr-locatable-1055312697) Wilson CJ, Newman J, Tapper S, Lai S, Cheng PH, Wu FM, Tai-Seale M. J Palliat Med. 16(9):1089-94. doi: 10.1089/jpm.2012.0472. Epub 2013 Jun 6. 2013 Sep 01 - Publication ### [Beyond the threshold: real-time use of evidence in practice.](https://www.sutterhealth.org/research/publications/real-time-use-of-evidence-in-practice-1055312689) Jones JB, Stewart WF, Darer JD, Sittig DF. BMC Med Inform Decis Mak. 13:47. doi: 10.1186/1472-6947-13-47. 2013 Apr 15 [View all publications](https://www.sutterhealth.org/research-search-results?verticalKey=research_publication) ```json {"@context":"https://schema.org","@type":"MedicalOrganization","name":"Sutter Health","@id":"https://www.sutterhealth.org/#medicalorganization","url":"https://www.sutterhealth.org","logo":"https://www.sutterhealth.org/static/images/sutter-health-logo.svg","address":{"@type":"PostalAddress","streetAddress":"2200 River Plaza Drive","addressLocality":"Sacramento","addressRegion":"CA","postalCode":"95833","addressCountry":"US"},"areaServed":{"@type":"AdministrativeArea","name":"California"},"sameAs":["https://www.facebook.com/SutterHealth","https://www.instagram.com/sutterhealth/","https://x.com/SutterHealth","https://www.youtube.com/sutterhealth","https://www.linkedin.com/company/sutter-health","https://en.wikipedia.org/wiki/Sutter_Health"]} ``` ```json {"@context":"https://schema.org","@type":"BreadcrumbList","@id":"https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822#breadcrumblist","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://www.sutterhealth.org/"},{"@type":"ListItem","position":2,"name":"Research","item":"https://www.sutterhealth.org/research"},{"@type":"ListItem","position":3,"name":"Research publications","item":"https://www.sutterhealth.org/research/publications"},{"@type":"ListItem","position":4,"name":"PARAFAC2 tensor factorization on EHR audit data and PCP work"}]} ``` ```json {"@context":"https://schema.org","@type":"MedicalScholarlyArticle","@id":"https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822#medicalscholarlyarticle","name":"Using the PARAFAC2 tensor factorization on EHR audit data to understand PCP desktop work.","headline":"PARAFAC2 tensor factorization on EHR audit data and PCP work","abstract":"Background: Activity or audit log data are required for EHR privacy and security management but may also be useful for understanding desktop workflow. Objective: We determined if the EHR audit log file, a rich source of complex time-stamped data on desktop activities, could be processed to derive primary care provider (PCP) level workflow measures. Methods: We analyzed audit log data on 876 PCPs across 17,455 ambulatory care encounters that generated 578,394 time-stamped records. Each individual record represents a user interaction (e.g., point and click) that reflects all or part of a specific activity (e.g., order entry access). No dictionary exists to define how to combine clusters of sequential audit log records to represent identifiable PCP tasks. We determined if PARAFAC2 tensor factorization could: (1) learn to identify audit log record clusters that specifically represent defined PCP tasks; and (2) identify variation in how tasks are completed without the need for ground-truth labels. To interpret the result, we used the following PARAFAC2 factors: a matrix representing the task definitions and a matrix containing the frequency measure of each task for each encounter. Results: PARAFAC2 automatically identified 4 clusters of audit log records that represent 4 common clinical encounter tasks: (1) medications' access, (2) notes' access, (3) order entry access, and (4) diagnosis modification. PARAFAC2 also identified the most common variants in how PCPs accomplish these tasks. It discovered variation in how the notes' access task was done, including identification of 9 distinct variants of notes access that explained 77% of the input data variation for notes. The discovered variants mapped to two known workflows for notes' access and to two distinct PCP user groups who accessed notes by either using the Visit Navigator or the Wrap-Up option. Conclusions: Our results demonstrate that EHR audit log data can be rapidly processed to create higher-level constructed features that represent time-stamped PCP tasks.","description":"Results demonstrate that EHR audit log data can be rapidly processed to create higher-level constructed features that represent time-stamped PCP tasks.","keywords":["Medical Informatics"],"datePublished":"2020-01-01","url":"https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822","inLanguage":"en-US","identifier":[{"@type":"PropertyValue","propertyID":"PMID","value":"31627022"},{"@type":"PropertyValue","propertyID":"DOI","value":"10.1016/j.jbi.2019.103312"}],"sameAs":["https://pubmed.ncbi.nlm.nih.gov/31627022/","https://doi.org/10.1016/j.jbi.2019.103312"],"isPartOf":{"@type":"Periodical","name":"J Biomed Inform"},"author":[{"@type":"Person","name":"Perros I"},{"@type":"Person","@id":"https://www.sutterhealth.org/research/investigators/xiaowei-sherry-yan-phd-1049681042","name":"Yan X","url":"https://www.sutterhealth.org/research/investigators/xiaowei-sherry-yan-phd-1049681042"},{"@type":"Person","@id":"https://www.sutterhealth.org/research/investigators/jb-jones-phd-mba-1049680984","name":"Jones JB","url":"https://www.sutterhealth.org/research/investigators/jb-jones-phd-mba-1049680984"},{"@type":"Person","name":"Sun J"},{"@type":"Person","name":"Stewart WF"}],"about":[{"@type":"DefinedTerm","name":"Medical Informatics","url":"https://www.sutterhealth.org/research-search-results?facets=%5B%7B%22i%22%3A%22c_researchTopics.name%22%2C%22v%22%3A%5B%22Medical+Informatics%22%5D%7D%5D&verticalKey=research_publication"}],"mainEntityOfPage":{"@type":"WebPage","@id":"https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822","breadcrumb":{"@id":"https://www.sutterhealth.org/research/publications/parafac2-tensor-factorization-on-ehr-audit-data-pcp-work-1055312822#breadcrumblist"}}} ```