Program

Location

Tutorial I

Role of Semantic Web in Health Informatics
[tutorial slides]

Leveraging the rapidly increasing amount of health care data to demonstrably enhance quality of clinical research and patient care has become a critical challenge for health care providers, researchers, and informaticians. In addition to the sheer volume of the data, the large disparity in storage formats, distributed locations, and variable quality of data, is exacerbating data management issues. There is an urgent need to address these issues to enable multi-center clinical studies, comply with new health care policies that encourage adoption of Electronic Health Records (EHR), and effectively move towards the National Institutes of Health roadmap of translational research.

The Semantic Web initiative by the World Wide Web Consortium (W3C) has defined a set of standards and technologies for representing, integration, and querying large-scale data with increasing use in health care, exemplified by the W3C Health Care and Life Sciences (HCLS) Interest Group. 

This tutorial will weave together three themes and the associated topics:
  1. The role of biomedical ontologies as a community driven and agreed upon knowledge model, in health care data integration, interoperability, sharing, and storage. 
  2. Key technologies with focus on Semantic provenance and integration to ensure data quality, compliance with regulatory requirements, and preserving audit trails in health informatics. 
  3. In-practice tools and real world use cases built to serve the needs of sleep medicine researchers, cardiologists involved in clinical practice, and work on vaccine development for human pathogen will be used as real world experience in the use of Semantic Web technologies in health informatics. 
Presenters:

Satya Sahoo is assistant professor in the division of medical informatics at the Case Western Reserve University. Satya has led the development of three NCBO-listed ontologies. In addition, he has collaborated with the NLM, National Institute on Drug Abuse, Microsoft Research, and the Center for Tropical and Global Emerging Diseases on use of Semantic provenance for data management. Satya is member of the W3C HCLS for past 4 years and is also an invited expert in the W3C Provenance Interchange Working Group.

Amit Sheth is the LexisNexis Ohio Eminent Scholar at the Wright State University, Dayton OH. He directs Kno.e.sis - the Ohio Center of Excellence in Knowledge-enabled Computing (http://knoesis.org). He is an IEEE fellow and is one of the highly cited authors in Computer Science (h-index = 68). He has led NIH funded projects that used Semantic Web technologies in biomedical research.

Guo-Qiang Zhang is chief of biomedical informatics division at the Case Western Reserve University with 20 years of experience in ontologies, algorithms, and image analysis. He is also the informatics co-director of Case Clinical and Translational Science Award (CTSA) center and the associate Director in the Case Comprehensive Cancer Center. He led the development of the ontology-driven Physio-MIMI platform for multi-center sleep medicine research involving Case Western Reserve University, University of Michigan, University of Wisconsin and Marshfield Clinic.


Tutorial II

Measuring the Similarity and Relatedness of Concepts in the Medical Domain 

The ability to quantify the degree to which concepts are similar or related to each other is a key component in many Natural Language Processing and Artificial Intelligence applications. For example, in a document search application, it can be very useful to identify text snippets that contain terms that are similar to (but not identical) to those provided by a user. This tutorial will introduce the underlying theory behind measures of semantic similarity and relatedness, and show how these can be applied in the medical domain by using open source software (UMLS::Similarity http://umls-similarity.sourceforge.net) which takes advantage of information found in the Unified Medical Language System (UMLS) of the National Library of Medicine. The tutorial will also show users how to use recently created human reference standard data to calibrate and evaluate existing measures.

Those who attend this tutorial will learn how to:
  1. understand the distinction between semantic relatedness and semantic similarity,
  2. measure semantic similarity and relatedness using information from ontologies, definitions, and corpora,
  3. use these measures from the command line, API, and web services using the open--source software package UMLS::Similarity,
  4. integrate these measures into different NLP and AI applications, and
  5. conduct experiments using freely available human reference standard data.
This tutorial will be accessible to any Health Informatics student, professional, or researcher with an interest in Natural Language Processing, ontologies, or Artificial Intelligence. No prior knowledge is assumed.

Presenters:

Ted Pedersen (Ph.D., 1998, Computer Science, Southern Methodist University) is a Professor in the Department of Computer Science at the University of Minnesota, Duluth.  His research interests are in natural language processing and computational linguistics, and focus on identifying the meaning of words and phrases in written text. He is the recipient of a National Science Foundation CAREER award.

Serguei Pakhomov (Ph.D., 2001, Linguistics, University of Minnesota) is an Associate Professor at the College of Pharmacy, University of Minnesota. His research interests include natural language processing of the text of electronic health records for the purposes of extracting information useful for clinical practice and research. He is the recipient of the National Institutes of Health Clinical and Translational Scholar Award.

Bridget T. McInnes (Ph.D., 2009, Computer Science, University of Minnesota) is a Postdoctoral Associate at the College of Pharmacy, University of Minnesota. Her research interests are in natural language processing in the biomedical domain and focus on quantifying the relatedness between biomedical and clinical concepts.  She was the recipient of a National Library of Medicine Research Participation Fellowship in 2008.

Ying Liu (Ph.D., 2007, Computer Science, University of Alabama at Birmingham) is a Postdoctoral Associate at the College of Pharmacy, University of Minnesota. Her research interests are in data mining in both general and biomedical texts. She won first place in the University of Alabama at Birmingham Graduate Student Research Day 2005 for her work on outlier detection.


Tutorial III

Assisted Living Technologies for Older Adults

The increasing aging population is a challenging health care problem in US and many other parts of the world. The population of the US, as well as the other industrialized countries is aging rapidly. This aging population is going to bring new challenges to our society, such as an increase in age-related diseases, rising health care costs, shortage of health care professionals, and lack of quality care for everyone.

This tutorial will explore intelligent technologies and methods that can help health care professionals to provide better quality care for the older adults, monitor their health conditions in place, as well as technologies that allow the older adults to live more independently. It will highlight current challenges and important future directions in the field. It will also cover a number of successful case studies such as smart homes and intelligent reminder systems.

Presenters:

Parisa Rashidi is a research scientist at University of Florida, Gainesville. She has been working on smart environments and assisted living technology since 2006. She received her BS.c degree in computer engineering from University of Tehran in 2005, her MS.c in computer science from Washington State University in 2007, and her PhD degree in computer science from Washington State University in 2011. Her interests include applying data mining and artificial intelligence techniques to assisted living technology, health informatics problems, and smart environments. She worked on the CASAS smart home project for dementia patients from 2006 to 2010 and has published numerous papers in this area. She also has served on the reviewing board of several international journals and conferences, as well as related NSF panels.