METHODS IN MEDICAL INFORMATICS

File parsing is a computational method of reading file piece by piece. In most parsing routines, the pieces can be matched against a pattern and then extracted or modified. This chapter will explore basic text file parsing techniques and scripts.

Continue 

Data Files

Utility scripts are small programs that perform a specific task, very efficiently. Potential uses include file compression, file searching, image conversion, etc. This chapter will introduce some general utility scripts that will be applied in later chapters. 

Continue 

Data Files

Everyone who deals with data will eventually need a simple way of representing their data in images. There are many different image formats and operations for modifying images. This chapter will introduce some scripts that introduce the user to viewing and modifying images. 

Continue 

 

Data Files

Text indexing is a method for organizing textual data which increases the speed of textual searches and processing. In thi chapter, you will learn the rudiments of text indexing. These fundamental algorithms will also be encountered again in chapter 14, autocoding. 

Continue 

Data Files

Nomenclatures are comprehensive repositories of domain terminologies. A well-organized, comprehensive nomenclature can be used to annotate and index any information in any document, and permits that information to be retrieved and merged with relevant information contained in other documents. MeSH (Medical Subject Headings) is a nomenclature of medical terms available from the U.S. National Library of Medicine (NLM). In this chapter, we will be exploring scripts interacting with MeSH data provided by the NLM website. 

Continue 

Data Files

The International Classification of Diseases (ICD) is a nomenclature of the disease occurring in humans, with each listed disease assigned a unique identifying code. In this chapter, we will explore scripts which create ICD dictionaries. ICD will also play a role in future chapters. 

Continue 

Data Files

PubMed is the U.S. National Library of Medicine’s public search engine for millions of citations from the medical literature. In addition, PubMed can serve as an excellent data source for savvy informaticists. In this chapter, we will be exploring scripts which interact with PubMed. 

Continue

Data Files 

Creating an accurate and complete nomenclature is important since misuse of medical terminology can lead to medical errors. Nomenclatures are often large and detailed thanks to electronic storage. In this chapter we will be exploring one such nomenclature system, the Developmental Lineage Classification adn Taxonomy of Neoplasms. 

Continue 

Data Files

In the field of biomedical informatics, it is often necessary to extract medical terms from text and attach a nomenclature concept code to the extracted term. This can often be done automatically using software. This chapter will explore software automated medical coding. 

Continue 

Data Files

Medical records contain confidential and sensitive information. Often, medical data must be deidentified before being used. This chapter will explore how medical text can be deidentified with the aid of software. 

Continue 

There are many network protocols for exchanging information over the Internet, and for using remotely located applications. This chapter will explore a script for grabbing information from the internet utilizing one such protocol. 

Continue 

XML is a method for marking up files so that every piece of data is surrounded by bracketed text that describe the piece of data. markup allows us to convey any message as XML. This chapter will explore XML and script that can parse XML files. 

Continue 

Data Files