Search

5.9% of the Austrian population is affected by diabetes mellitus. Disease Management is a structured treatment approach that is suitable for application to the diabetes mellitus area and often is supported by information technology. This article describes the information systems developed and implemented in the Austrian disease management programme for type 2 diabetes. Several workflows for administration as well as for clinical documentation have been implemented utilizing the Austrian e-Health infrastructure. De-identified clinical data is available for creating feedback reports for providers and programme evaluation. [ABSTRACT FROM AUTHOR]

The amount of narrative clinical text documents stored in Electronic Patient Records (EPR) of Hospital Information Systems is increasing. Physicians spend a lot of time finding relevant patient-related information for medical decision making in these clinical text documents. Thus, efficient and topical retrieval of relevant patient-related information is an important task in an EPR system. This paper describes the prototype of a medical information retrieval system (MIRS) for clinical text documents. The open-source information retrieval framework Apache Lucene has been used to implement the prototype of the MIRS. Additionally, a multi-label classification system based on the open-source data mining framework WEKA generates metadata from the clinical text document set. The metadata is used for influencing the rank order of documents retrieved by physicians. Combining information retrieval and automated document classification offers an enhanced approach to let physicians and in the near future patients define their information needs for information stored in an EPR. The system has been designed as a J2EE Web-application. First findings are based on a sample of 18,000 unstructured, clinical text documents written in German. [ABSTRACT FROM AUTHOR]

In this paper we describe the approach to build a web-based clinical data management infrastructure on top of an entity-attribute-value (EAV) database which provides for flexible definition and extension of clinical data sets as well as efficient data handling and high performance query execution. A “mixed” EAV implementation provides a flexible and configurable data repository and at the same time utilizes the performance advantages of conventional database tables for rarely changing data structures. A dynamically configurable data dictionary contains further information for data validation. The online user interface can also be assembled dynamically. A data transfer object which encapsulates data together with all required metadata is populated by the backend and directly used to dynamically render frontend forms and handle incoming data. The “mixed” EAV model enables flexible definition and modification of clinical data sets while reducing performance drawbacks of pure EAV implementations to a minimum. The system currently is in use in an electronic patient record with focus on flexibility and a quality management application (www.healthgate.at) with high performance requirements. [ABSTRACT FROM AUTHOR]

At nearly every patient visit, medical documents are produced and stored in a medical record, often in an unstructured form as free text. The growing amount of stored documents increases the need for effective and timely retrieval of information. We developed a multi-label text classification system to categorize free text medical documents (e.g. discharge letters, clinical findings, reports) written in German into predefined classes. A random sample of 1,500 free text medical documents was retrieved from a general hospital information system and was manually assigned to 1 to 8 categories by a domain expert. This sample was used to train and evaluate the performance of 4 classification schemes: Naïve Bayes, k-NN, SVM, and J48. Additional tests of the effect of text preprocessing were done. In our study, preprocessing improved the performance, and best results were obtained by J48 classification. [ABSTRACT FROM AUTHOR]

Hospitals are major providers of health services and analysis of hospital activity data is of great interest for both policy makers and public health researchers. The WHO Regional Office for Europe disseminates the hospital discharge data from European countries through the European Hospital Morbidity Database, available on http://data.euro.who.int/hmdb. In order to ensure that reliable high quality data on hospital activities can be published in a timely manner, a program for validation of hospital discharge data has been developed using the R language for statistical computing. This program has been in use since the October 2012 version of the European Hospital Morbidity Database and its use has contributed to improved quality and comparability of data on hospital activities across Europe. [ABSTRACT FROM AUTHOR]

5.9% of the Austrian population is affected by diabetes mellitus. Disease Management is a structured treatment approach that is suitable for application to the diabetes mellitus area and often is supported by information technology. This article describes the information systems developed and implemented in the Austrian disease management programme for type 2 diabetes. Several workflows for administration as well as for clinical documentation have been implemented utilizing the Austrian e-Health infrastructure. De-identified clinical data is available for creating feedback reports for providers and programme evaluation.

The amount of narrative clinical text documents stored in Electronic Patient Records (EPR) of Hospital Information Systems is increasing. Physicians spend a lot of time finding relevant patient-related information for medical decision making in these clinical text documents. Thus, efficient and topical retrieval of relevant patient-related information is an important task in an EPR system. This paper describes the prototype of a medical information retrieval system (MIRS) for clinical text documents. The open-source information retrieval framework Apache Lucene has been used to implement the prototype of the MIRS. Additionally, a multi-label classification system based on the open-source data mining framework WEKA generates metadata from the clinical text document set. The metadata is used for influencing the rank order of documents retrieved by physicians. Combining information retrieval and automated document classification offers an enhanced approach to let physicians and in the near future patients define their information needs for information stored in an EPR. The system has been designed as a J2EE Web-application. First findings are based on a sample of 18,000 unstructured, clinical text documents written in German.

In this paper we describe the approach to build a web-based clinical data management infrastructure on top of an entity-attribute-value (EAV) database which provides for flexible definition and extension of clinical data sets as well as efficient data handling and high performance query execution. A "mixed" EAV implementation provides a flexible and configurable data repository and at the same time utilizes the performance advantages of conventional database tables for rarely changing data structures. A dynamically configurable data dictionary contains further information for data validation. The online user interface can also be assembled dynamically. A data transfer object which encapsulates data together with all required metadata is populated by the backend and directly used to dynamically render frontend forms and handle incoming data. The "mixed" EAV model enables flexible definition and modification of clinical data sets while reducing performance drawbacks of pure EAV implementations to a minimum. The system currently is in use in an electronic patient record with focus on flexibility and a quality management application (www.healthgate.at) with high performance requirements.