Submitted to the Health Informatics Graduate Program Faculty, Indiana University, in partial fulfillment of the requirements for the degree of Master of Science in Health Informatics.May 2006 / The purpose of this study is to examine the current use of natural language processing for extracting meaningful data from free text in medical reports. The use of natural language processing has been used to process information from various genres. To evaluate the use of natural language processing, a synthesized review of primary research papers specific to natural language processing and extracting data from medical reports. A three phased approach is used to describe the process of gathering the final metrics for validating the use of natural language processing. The main purpose of any NLP is to extract or understand human language and to process it into meaning for a specified area of interest or end-user. There are three types of approaches: symbolic, statistical, and connectionist. There are identified problems with natural language processing and the different approaches. Problems noted about natural language processing in the research are: acquisition, coverage, robustness, and extensibility. Metrics were gathered from primary research papers to evaluate the success of the natural language processors. Recall average of the four papers was 85%. Precision average of five papers was 87.7%. Accuracy average was 97%. Sensitivity average was 84%, while specificity was 97.4%. Based on the results of the primary research there was no definitive way to validate one NLP approach as an industry standard The research reviewed it is clear that there has been at least limited success with information extraction from free text with use of natural language processing. It is important to understand the continuum of data, information, and knowledge in the previous and future research of natural language processing. In the industry of health informatics this is a technology necessary for improving healthcare and research.

In medicine, reliable data are available only in a few areas and necessary information on prognostic implications is generally missing. In spite of the fact that a great amount of money has been invested to ease the process, an effective solution has yet to be found. Unfortunately, existing data collection approaches in medicine seem inadequate to provide accurate and high quality data, which is a prerequisite for building a robust and effective DDSS. In this thesis, many different medical reporting methodologies and systems which have been used up to now are evaluated / their strengths and deficiencies are revealed to shed light on how to set up an ideal medical reporting type. This thesis presents a new medical reporting method, namely &ldquo / Structured, Interactive, Standardized and Decision Supporting Method&rdquo / (SISDS) that encompasses most of the favorable features of the existing medical reporting methods while removing most of their deficiencies such as inefficiency and cognitive overload as well as introducing and promising new advantages. The method enables professionals to produce multilingual medical reports much more efficiently than the existing approaches in a novel way by allowing free-text-like data entry in a structured form. The proposed method in this study is proved to be more effective in many perspectives, such as facilitating the complete and the accurate data collection process and providing opportunities to build DDSS without tedious pre-processing and data preparation steps, mainly helping health care professionals practice better medicine.