Electronic data validation systems will ensure that data sets conform to the agreed data models and the quality and adequacy of the submitted data will be regularly reviewed from a clinical perspective.
There exist enormous historical data for the typical products in large batch production; while for small-batch customized products, the lack of sufficient historical data may prevent successful application of traditional data-based process modeling and quality prediction methods.
In order to understand what factors drive the maintainability of conceptual data models and to improve conceptual modelling processes, we need to be able to assess conceptual data model properties and qualities in an objective and cost-efficient manner.
The scope of agile enterprise data warehousing (EDW) presents a challenge in terminology because the separate software disciplines involved requirements management, data modeling, quality assurance, and application coding each utilize a different vocabulary.
Finally, we describe some initial efforts towards developing a common standard for data model quality, which may provide a model for future standardisation efforts.
It also opens a wide area for various interesting research questions such as data provenance tracking, data and model quality measurements and the capture of object relationships.
However, the effect of data on model quality and model performance, and the appropriate structure of models have not been previously investigated.
Data availability and quality for model input are critically important.
In the context of whole-genome prediction, the pipeline that we have developed can automate all steps involved in the computing and decision making for whole-genome prediction, which includes and is not limited to data input and quality control, model feature selection (FS) if applicable, post-FS statistical inference and cross-validation (CV), and output and documentations.
The authors believe that applying data governance in building information warehouses will provide a good start for data and model quality control.
