CMC Resource Catalog

Processing Language in Health Care: Benefit or Boondoggle?

$0.00

Click to enlarge

Processing Language in Health Care: Benefit or Boondoggle?
October 12, 2007, 10am – 2pm, Room 1103-1104, Merc Building
Cincinnati Children’s Oak Campus - 620 Oak St, Cincinnati, OH

Objectives: Natural Language Processing (NLP) is proving its worth to Internet search engines, newspapers and other classical text, but is there a role for text analysis in health care? This seminar reviews examples of how NLP is being used in health care. Topics discussed will include clinical data warehouses, data analytics, the impact of verbs, and some of the current research at Cincinnati Children’s Hospital Medical Center.

Organizers: NLP Group, Cincinnati Children’s Biomedical Informatics; University of Cincinnati Department of Biomedical Engineering; and the Computational Medicine Center

Leveraging Enterprise Data Warehousing to Support Translational Research
Presenter: Phillip Payne, PhD, Associate Professor, Biomedical Informatics, The Ohio State University, Columbus, OH
Abstract: With the increasing availability of high-throughput data collection platforms in the clinical care and basic science settings, significant opportunities exist to increase the translational research capacity of academic medical centers. However, this opportunity is accompanied by several challenges, including: 1) the identification and use of appropriate electronic data interchange modalities; 2) the provision of knowledge structures capable of enabling semantic interoperability between data sources and reasoning upon data warehouse contents; and 3) the selection and application of technologies capable of “unlocking” data contained in numerous types of narrative text. This presentation will explore the preceding three challenges, using specific examples drawn from historical and ongoing initiatives within The Ohio State University Medical Center Information Warehouse and Department of Biomedical Informatics.

Using Natural Language Processing to Support Pediatric Clinical Care Delivery
Presenter: John Pestian, PhD, Associate Professor, Pediatrics and Biomedical Engineering, CCHMC/UC, Cincinnati, OH
Abstract: This presentation will review some of natural language processing initiatives at Cincinnati Children's Hospital Medical Center (CCHMC). Three particular initiatives that are rooted in various collaborations, and are in various stages of development, will be discussed. They are the development of visual languages to present complex clinical reports, the development of artificial experts for personalized medicine feature selection, and the results of a shared task in developing autocoding algorithms for clinical billing.

Developing a Clinical Data Analytics Language
Presenter: Jon Patrick, PhD, Professor, School of Information Technologies, University of Sydney, Sydney, Australia
Abstract: General purpose access to data from clinical information systems, beyond retrieval for point of care work, is needed for many aspects of the hospital’s work, particularly for clinical research, logistics and operational planning, and auditing patient safety. Current systems, perhaps with the exception of the HIE (within NSW), only provide access to data identified in standard reports with no flexibility to make ad hoc inquiries or to pursue new directions of inquiry. The clinical data analytics language the Unit has developed enables the expression of any question that can be answered from the data in the database in a restricted natural language. A prototype of the language has been developed for the CareVue information system used in the ICU at the Royal Prince Alfred Hospital. It provides for the use of local medical dialects, SNOMED CT terminology including all forms of collective expressions in SNOMED (e.g. ,infectious diseases), specification of patient groups, a variety of statistical functions, and constraints over any medical variable, time, and location. CDAL is general in that it can be bolted on to any clinical information system and is applicable to any clinical specialization.

Call Me a Cab, or Call Me a Fool? Mining for Lexical Information
Presenter: Chris Brew, PhD, Professor of Linguistics, The Ohio State University, Columbus OH
Abstract: Text and speech are the native encoding standards for much of the information that is crucially important to modern societies. Even highly structured scientific databases (such as those associated with genomic or toxicological data) make copious use of free text. Among the major obstacles to working with such data is the difficulty of obtaining reliable lexical information (i.e., information about the meaning and behavior of words). This is especially acute in technical fields because existing lexical resources are unlikely to suffice. Therefore, it seems appropriate to explore techniques that allow lexical information to be learnt from data. This talk will describe the methods and results of a strand of work that aims to derive and extend a technologically useful classification of verbs. The inputs to this process include both corpus data and the linguistically motivated prior information that so-called "diathesis alternations" are likely to be relevant and important to the classification. I will argue that the prior information is crucial; even the availability of really big (gigaword) training corpora will not necessarily allow useful resources to be induced from corpus data alone.

This product was added to our catalog on Friday 12 October, 2007.

Customers who bought this product also purchased

Challenge Testing Data - NO CODES, 2007	CMC 2007 Challenge Data Description	Challenge Testing Data - CODES, 2007
CONFERENCE: NLP & Clinical Text	Challenge Training Data, 2007	A Shared Task Involving Multi-label Classification of Clinical F