information retrieval

Medical information is often stored in a narrative way, which makes the automated processing a difficult and time-consuming task.

Persons responsible for the authoring of medical documents do not take care of a further processing with automated systems. So, information stored in medical writings is not directly usable for the processing with computers. Due to this, efforts have been made to transfer these narrative documents in a format easier processable with computers. This matter of fact also applies to clinical practice guidelines (CPGs). As many medical documents, CPGs are written in a narrative speech as well, without regards to a computer-assisted processing. For the implementation of CPGs in medical facilities an automated processing is therefore desirable. An important fact is that a lot of information in CPGs is provided in a negated form, expressing that certain circumstances in patients or treatments are not available, existing or applicable. Although negated, this information is nevertheless very useful, since it can express the absence of certain conditions or diseases in patients. Moreover, negations can describe which treatment options should not be taken into account for a given patient, helping a practising physician or nurse in his/her decision process for the assortment of a proper treatment. Thus, a proper Negation Detection in CPGs is an important task for the automated processing of this type of medical documents. It helps to accelerate the decision making process and can support medical staff in their care for patients. We developed algorithms capable of Negation Detection in CPGs. We use syntactical methods provided by the English language to achieve a precise detection of occuring negations. According to our results we are convinced that the involvement of syntactical methods can improve Negation Detection, not only in medical writings but also in arbitrary narrative texts.

A Neonatal Care Unit (NICU) is a data-rich environment. An information overload can be observed at point-of-care and hospital enterprise level. Errors may occur just because of the sheer volume of data. The implementation of healthcare information technologies (HIT) can help to enhance the safety, quality and patient-centeredness of care.

Patient data management systems (PDMS) are especially designed software and hardware products for the documentation of patient's condition and treatment at intensive care. These routinely used systems must capture and store the abundance of information generated during the critical care process. Additional, a growing number of quality management systems (QMS) are implemented to provide clinical decision support, computerized physician order entry, rule-based infection monitoring, external quality control, and others. QMS applications and linkages in and among HIT systems can improve patient safety substantial. Communication tasks and asynchronous data exchange between HIT systems are important. Most HIT systems used at the introduced NICU provide rudimentary data exchange functions, but their data structures are optimized to applications requirements. The data stored at the PDMS database should be used for the QMS application to prevent multiple documentations. Frequent changes of the patient documentation process, subsequent data corrections, and missing essential patient information cause severe problems for data retrieval. A concept of data export - from actual used PDMS databases - is presented to handle such problems. The solution concept provides calculations, aggregation rules, and export adaptation functionalities. Patient data must be transformed to clearly defined information records for the QMS. The concept evaluation describes success, development process, operating time, customizations, and user satisfaction for implemented projects. It shows the importance of communication mechanisms between PDMS and QMS users. The integration of QMS applications into medical workflow is complex and elaborate methods for data and information exchange are required.