Refine
Year of publication
- 2015 (9) (remove)
Document Type
- Conference Proceeding (9) (remove)
Is part of the Bibliography
- yes (9)
Institute
- Fakultät WiSo (9)
Restricted Versus Unrestricted Search Space : Experience from Mining a Large Japanese Database
(2015)
The aim of this study was to investigate whether standard Big Data mining methods lead to clinically useful results. An association analysis was performed using the apriori algorithm to discover associations among co-morbidities of diabetes patients. Selected data were further analyzed by using k-means clustering with age, long-term blood sugar and cholesterol values. The association analysis led to a multitude of trivial rules. Cluster analysis detected clusters of well and badly managed diabetes patients both belonging to different age groups. The study suggests the usage of cluster analysis on a restricted space to come to meaningful results.
Although national eHealth strategies have existed now for more than a decade in many countries, they have been implemented with varying success. In Germany, the eHealth strategy so far has resulted in a roll out of electronic health cards for all citizens in the statutory health insurance, but in no clinically meaningful IT-applications. The aim of this study was to test the technical and organisation feasibility, usability, and utility of an eDischarge application embedded into a laboratory Health Telematics Infrastructure (TI). The tests embraced the exchange of eDischarge summaries based on the multiprofessional HL7 eNursing Summary standard between a municipal hospital and a nursing home. All in all, 36 transmissions of electronic discharge documents took place. They demonstrated the technical-organisation feasibility and resulted in moderate usability ratings. A comparison between eDischarge and paper-based summaries hinted at higher ratings of utility and information completeness for eDischarges. Despite problems with handling the electronic health card, the proof-of-concept for the first clinically meaningful IT-application in the German Health TI could be regarded as successful.