File:Fig4 Ye JofPathInformatics2016 7.jpg

Figure 4. (a) Microsoft Word table rendition of portion of R data frame showing the four columns of retrieved data and one column of generated element. The first four columns such as "accession_no," "patient_id," "created_date," and "finding_text" are data retrieved from PowerPath database. The 5th column "cannotupdate" is used subsequently to determine if updated staging information will be obtained from the subsequent reports. The content of "finding_text" contains large chunks of text data including the synoptic reports; only the first few words are displayed in the table. (b) Microsoft Word table rendition showing portion of an R data frame containing two columns of extracted elements and one column of tidy data (BreslowDepth[mm]) derived from the first two columns.

Ye, J.J. (2016). "Pathology report data extraction from relational database using R, with extraction from reports on melanoma of skin as an example". Journal of Pathology Informatics 7: 44. doi:10.4103/2153-3539.192822. 

2016

Ye, J.J.

Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported