We started a multi-year project to collect discharge summaries from multiple hospitals and create a big text database to build a common document vector space, and develop various applications such as the autoselection of the disease. As the first step, we extracted discharge summary from two hospitals. Using a text mining method, we carried out a DPC selection. There was a difference in term structure and number of terms between the discharge summaries from both hospitals. Nevertheless, the selection rate of the disease is resembled closely.
Medical records contain enormous amounts of data. It is important to extract useful evidence from such data and feedback to clinical medicine. Evidence-based medicine (EBM) was introduced in the 1990s and has been widely used for more than 20 years, however, hospital information system environments that take advantage of the ideas of EBM have not yet been established. Recently, the numbers of medical institutions with multilateral search systems for the medical records stored in data warehouses (DWHs) have been increasing, but these institutions systems cannot deal fully with issues such as data reliability and high-dimensional, high-speed searches. DWHs can control long time-series data. Although, the measurement methods and analytical equipment used have been modified and improved with advances in testing techniques, this may have induced shifting and/or fragmentation of these types of data. Furthermore, database design has to be flexible to satisfy the various demands of information retrieval; systems must therefore have the structures to deal with such demands. We report here our new system infrastructure, which exchanges data in order to absorb the data shifting associated with changes in the testing methods. The system enables the preparation of DWH environments that can be used to seamlessly analyze long time-series data, record in knowledge databases the results of comprehensive analyses of institutions characteristics of laboratory diagnoses, and use the data in education, research and clinical practice.
Related JoVE Video
Journal of Visualized Experiments
What is Visualize?
JoVE Visualize is a tool created to match the last 5 years of PubMed publications to methods in JoVE's video library.
How does it work?
We use abstracts found on PubMed and match them to JoVE videos to create a list of 10 to 30 related methods videos.
Video X seems to be unrelated to Abstract Y...
In developing our video relationships, we compare around 5 million PubMed articles to our library of over 4,500 methods videos. In some cases the language used in the PubMed abstracts makes matching that content to a JoVE video difficult. In other cases, there happens not to be any content in our video library that is relevant to the topic of a given abstract. In these cases, our algorithms are trying their best to display videos with relevant content, which can sometimes result in matched videos with only a slight relation.