Sustainable Data Preparation with Focus on Applications in Health Care
The project DataPrepHealth is a dissertation funded by the FFG. Its aim is to develop a process for sustainable data preparation with special attention on applications in the health care sector. The aim of the preparation is a usage of the data in different models. The process itself parts into different steps:
- Definition of Data
- Data cleaning (inconsistencies, duplicates, …)
- Merging of different data sources
- Preparation and aggregration of data for utilization in various models
For every step there will be methods defined, which either already exist or have to be created. These methods will then be combined into a standardized process with the focus on reproducibility, transparency, and the documentation of the process.
To have the process as application-oriented as possible it will be developed in the course of various (real world) projects in the realm of health care. As part of this the necessary requirements for the process will be defined and the different methods will be tested.
The result will be a standardized process, which can be readily applied. The benefit will be a massive saving of time as the data preparation does not have to be started from scratch for each and every project. Nevertheless, the high transparency and continuous documentation of the process will assure traceability and thus increase trustfulness of the project.
Funding information:
This is a research-project funded by FFG.