Refine
Document Type
- Book (4)
- Conference Proceeding (3)
Is part of the Bibliography
- yes (7)
Institute
- Fakultät WiSo (7)
Characteristics of German Hospitals Adopting Health IT Systems : Results from an Empirical Study
(2011)
Hospital characteristics that facilitate IT adoption have been described by the literature extensively, however with controversial results. The aim of this study therefore is to draw a set of the most important variables from previous studies and include them in a combined analysis for testing their contribution as single factors and their interactions. Total number of IT systems installed and number of clinical IT systems in the hospital were used as criterion variables. Data from a national survey of German hospitals served as basis. Based on a stepwise multiple regression analysis four variables were identified to significantly explain the degree of IT adoption (60% explained variance): 1) hospital size, 2) IT department, 3) reference customer and 4) ownership (private vs. public). Our results replicate previous findings with regard to hospital size and ownership. In addition our study emphasizes the importance of a reliable internal structure for IT projects (existence of an IT department) and the culture of testing and installing most recent IT products (being a reference customer). None of the interactions between factors was significant.
Charakteristika innovativer Krankenhäuser in Deutschland : Ergebnisse einer empirischen Untersuchung
(2011)
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.