Discovery and Visualization of New Information from Clinical Reports




Electronic Health Record (EHR) systems improve patient care by reducing redundancy in prescribing and computerized ordering but paradoxically also generate other types of information redundancy that lead to information overload. This presents a challenge for clinicians in providing safe and effective care especially with complex patients requiring synthesis of many clinical elements across a lengthy medical history. We hypothesize that provider usage of clinical notes can be supported through refinement of automatedmethods to detect new information, facilitation of new information visualization in practice, and EHR clinical note interface optimization. While there is much interest in supporting evidence-based medicine, little attention has been given to assisting clinicians in navigating and synthesizing growing amounts of electronic data for individual patients. Unstructured narrative text is an important part of modern EHRs. Text allows clinicians to communicate complex and nuanced information in a manner that is easily comprehended by others. While analyzing a collection of patient’s notes can be formidable, it is necessary for making diagnostic and therapeutic decisions. Currently, this process is hindered by many factors, including large amounts of redundant information in these texts, increasing numbers of documents, suboptimal user interface (UI) design, and limited time to interact with patients.

Goals & Aims

There is a critical need to optimize the use of EHR clinical notes for providers, which we propose to address in three aims: 1) Refine computational methods to identify new information in clinical notes, 2) Assess the effect of visualizing new information in clinical notes in an inpatient hospitalist setting, and 3) Discover elements of a rationally designed EHR graphical UI to facilitate clinical document usage in practice. Successful accomplishment of these aims will lay a foundation to make clinicians more efficient, improve decision-making, decrease cognitive load, and potentially increase clinician satisfaction associated with using clinical documents in EHR systems.


This work is funded by the Agency for Healthcare Research and Quality grant R01HS022085.





  • Zhang R, Pakhomov SVS, Arsoniadis EG, Lee JT, Wang Y, Melton GB. Detecting clinically relevant new information in clinical notes across specialties and settings. BMC Medical Informatics and Decision Making. 2017: 17(suppl2):68.
  • Rizvi RF, Marquard JL, Seywerd MA, Adam TJ, Elison JT, Hultman GM, Harder KA, Melton GB. Usability Evaluation of an EHR’s Clinical Notes Interface from Attendings and Residents Perspectives-An Exploratory Study. Studies in Health Technology and Informatics (MedInfo 2017). Accepted.


  • Hultman G, Marquard J, Arsoniadis E, Mink PJ, Rizvi R, Ramer T, Khairat S, Fickau K, Melton GB. Usability Testing of Two Ambulatory EHR Navigators. Applied Clinical Informatics. 2016. 7(2): 502-15.
  • Rizvi R, Harder K, Hultman G, Adam TJ, Kim K, Pakhomov S, Melton GB. A comparative observational study of inpatient clinical note entry and reading/retrieval styles adopted by physicians. International Journal of Medical Informatics. 2016 Jun;90:1-11. doi: 10.1016/j.ijmedinf.2016.02.011. Epub 2016 Mar 2. PMID: 27103191.


  • Zhang R, Manohar N, Arsoniadis E, Wang Y, Adam TJ, Pakhomov SV, Melton GB. Evaluating Term Coverage of Herbal and Dietary Supplements in Electronic Health Records. Proceedings of the American Medical Informatics Association Symposium. 2015: 1361-70. PMID: 26958277. PMCID: PMC4765597.
  • Rajamani S, Chen ES, Akre ME, Wang Y, Melton GB. Assessing the adequacy of the HL7/LOINC Document Ontology Role axis. J Am Med Inform Assoc. 2015 May;22(3):615-20. doi: 10.1136/amiajnl-2014-003100. Epub 2014 Oct 28. PubMed PMID: 25352569.
  • Melton GB, Wang Y, Arsoniadis E, Pakhomov SV, Adam TJ, Kwaan MR, Rothenberger DA, Chen ES. Analyzing Operative Note Structure in Development of a Section Header Resource. Stud Health Technol Inform. 2015;216:821-6. PubMed PMID: 26262166; PubMed Central PMCID: PMC4781788.
  • Manohar N, Adam TJ, Pakhomov SV, Melton GB, Zhang R. Evaluation of Herbal and Dietary Supplement Resource Term Coverage. Stud Health Technol Inform. 2015;216:785-9. PubMed PMID: 26262159; PubMed Central PMCID: PMC4801024.
  • Zhang R, Adam T, Simon G, Cairelli M, Rindflesch T, Pakhomov S, Melton GB. Mining Biomedical Literature to Explore Interactions between Cancer Drugs and Dietary Supplements. American Medical Informatics Association Joint Summits Translational Science Proceedings. 2015 Mar 23;2015:69-73. PMID: 26306241. PMCID: PMC4525230. 


  • Zhang R, Cairelli MJ, Fiszman M, Kilicoglu H, Rindflesch TC, Pakhomov SV, Melton GB. Exploiting Literature-Derived Knowledge and Semantics to Identify Potential Prostate Cancer Drugs. Cancer Informatics. 2014 Oct 14;13(Suppl 1):103-11. doi: 10.4137/CIN.S13889. PMID: 25392688. PMCID: PMC4216049.
  • Zhang R, Pakhomov S, Melton GB. Longitudinal analysis of new information types in clinical notes. AMIA Jt Summits Transl Sci Proc. 2014 Apr 7;2014:232-7. eCollection 2014. PubMed PMID: 25717418; PubMed Central PMCID: PMC4333708.
  • Zhang R, Cairelli MJ, Fiszman M, Rosemblat G, Kilicoglu H, Rindflesch TC, Pakhomov SV, Melton GB. Using semantic predications to uncover drug-drug interactions in clinical data. J Biomed Inform. 2014 Jun;49:134-47. doi: 10.1016/j.jbi.2014.01.004. Epub 2014 Jan 19. PubMed PMID: 24448204; PubMed Central PMCID: PMC4058371.
  • Wang Y, Pakhomov S, Dale JL, Chen ES, Melton GB. Application of HL7/LOINC Document Ontology to a University-Affiliated Integrated Health System Research Clinical Data Repository. AMIA Jt Summits Transl Sci Proc. 2014 Apr 7;2014:230-4. eCollection 2014. PubMed PMID: 25954591; PubMed Central PMCID: PMC4419769.
  • Zhang R, Pakhomov SV, Lee JT, Melton GB. Using language models to identify relevant new information in inpatient clinical notes. AMIA Annu Symp Proc. 2014 Nov 14;2014:1268-76. eCollection 2014. PubMed PMID: 25954438; PubMed Central PMCID: PMC4419897.
  • Rajamani S, Chen ES, Wang Y, Melton GB. Extending the HL7/LOINC Document Ontology Settings of Care. AMIA Annu Symp Proc. 2014 Nov 14;2014:994-1001. eCollection 2014. PubMed PMID: 25954408; PubMed Central PMCID: PMC4419877.



  • BioMedICUS
    The BioMedical Information Collection and Understanding System (BioMedICUS) leverages open source solutions for text analysis and provides new analytic tools for processing and analyzing text of biomedical and clinical reports.