A data cleaning algorithm to reject chronic or congenital conditions flagged as present on admission and exclude them from programs monitoring patient safety would reduce the problem of over-counting of events that has previously been noted in automated surveillance systems [ 31].
For the present study, the data-cleaning algorithm checked and cleaned the biologic dose per dispensing field based on the plan paid amount, biologic dose, injection frequency, and wholesale acquisition cost (WAC; AnalySource, First DataBank Inc., South San Francisco, CA, USA).
A number of the factors identified can be modified through data cleaning, data restoration and algorithm updates and modification.
Data quality check and data cleaning were also performed.
Before applying the sentence detection algorithm, some data cleaning was needed: white spaces (space, tabs, carriage return, etc).
The data were processed through Illumina Genome Studio signal filtration and cleaning algorithms.
Specifically, Appendix A provides the descriptions of the datasets, data cleaning and combining process, and key variables used in the algorithm.
As the majority of the effort was spent on data cleaning, one of the next steps would be to incorporate natural language processing algorithms to help automate more of the cleaning as well as the encoding.
Therefore we have evaluated the two-phase filtering stage of the algorithm in order to find the best combination of filters as means of data cleaning.
