Package: EndoMineR 2.0.1.9000

Sebastian Zeki

EndoMineR: Functions to mine endoscopic and associated pathology datasets

This script comprises the functions that are used to clean up endoscopic reports and pathology reports as well as many of the scripts used for analysis. The scripts assume the endoscopy and histopathology data set is merged already but it can also be used of course with the unmerged datasets.

Authors:Sebastian Zeki [aut, cre]

EndoMineR_2.0.1.9000.tar.gz
EndoMineR_2.0.1.9000.zip(r-4.7)EndoMineR_2.0.1.9000.zip(r-4.6)EndoMineR_2.0.1.9000.zip(r-4.5)
EndoMineR_2.0.1.9000.tgz(r-4.6-any)EndoMineR_2.0.1.9000.tgz(r-4.5-any)
EndoMineR_2.0.1.9000.tar.gz(r-4.7-any)EndoMineR_2.0.1.9000.tar.gz(r-4.6-any)
EndoMineR_2.0.1.9000.tgz(r-4.6-emscripten)
 |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
EndoMineR/json (API)

# Install 'EndoMineR' in R:
install.packages('EndoMineR', repos = c('https://ropensci.r-universe.dev', 'https://cloud.r-project.org'))

Reviews:rOpenSci Software Review #153

Bug tracker:https://github.com/ropensci/endominer/issues

Pkgdown/docs site:https://docs.ropensci.org

Datasets:

On CRAN:

Conda:

endoscopygastroenterologypeer-reviewedsemi-structured-datatext-mining

5.58 score 13 stars 39 scripts 55 exports 128 dependencies

Last updated from:2b3603a276 (on master). Checks:7 NOTE, 2 OK, 1 ERROR. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64NOTE415
pkgdown docsOK389
source / vignettesERROR2222
linux-release-x86_64NOTE434
macos-release-arm64NOTE328
macos-oldrel-arm64NOTE204
windows-develNOTE379
windows-releaseNOTE367
windows-oldrelNOTE398
wasm-releaseOK202

Exports:Barretts_FUTypeBarretts_PathStageBarretts_PragueScoreBarrettsAllBarrettsBxQualBarrettsParisEMRBiopsyIndexCategoricalByEndoscopistColumnCleanUpdev_ExtrapolateOPCS4PrepDictionaryInPlaceReplaceEndoBasicGraphEndomerge2EndoPasteEndoscEndoscopistEndoscInstrumentEndoscMedsEndoscopyEventEntityPairs_OneSentenceEntityPairs_TwoSentenceEosinophilicsEventListExtractorExtrapolatefromDictionaryGISymptomsListGRS_Type_Assess_By_UnitHistolBxSizeHistolNumbOfBxHistolTypeHistolTypeAndSiteHowManyOverTimeIBD_ScoresListLookupLocationListLocationListLowerLocationListUniversalLocationListUpperMetricByEndoscopistMyImgLibraryNegativeRemoveNegativeRemoveWrapperPatientFlow_CircosPlotsPatientFlowIndividualRFACathsanityscale_colour_Publicationscale_fill_PublicationSurveilFirstTestSurveilLastTestSurveilTimeByRowSurveySankeytextPreptheme_PublicationTimeToStatusWordsToNumbers

Dependencies:askpassbackportsbase64encBHbitbit64blobbroombslibcachemcallrcellrangercheckmateclicliprclustercolorspaceconflictedcpp11crayoncurldata.tableDBIdbplyrDiagrammeRdigestdplyrdtplyrevaluatefarverfastmapfontawesomeforcatsforeignFormulafsfuzzyjoingarglegenericsgeosphereggplot2ggthemesgluegoogledrivegooglesheets4gridExtragtablehavenherehighrHmischmshtmlTablehtmltoolshtmlwidgetshttridsigraphisobandjquerylibjsonliteknitrlabelinglatticelifecyclelubridatemagrittrMatrixmemoisemimemodelrNLPnnetopensslotelpanderpillarpkgconfigprettyunitsprocessxprogresspspurrrR6raggrappdirsRColorBrewerRcppreadrreadxlrematchrematch2reprexrlangrmarkdownrpartrprojrootrstudioapirvestS7sassscalesselectrslamstringdiststringistringrsyssystemfontstextshapingtibbletidyrtidyselecttidyversetimechangetinytextmtzdbutf8uuidvctrsviridisLitevisNetworkvroomwithrxfunxml2yaml

EndoMineR
Aims of EndoMineR | 1. Extraction and cleaning | i. Dusting the data | ii. Spell checking | iii.Negative phrase removal | iv. Term mapping | Sv. egregating the data | What if my data is already in columns? | Can I have an example please? | 2. Data linkage | 3. Deriving new data from what you have | i) Medication | ii) Endosccopy Event extraction | iii) Histology biopsy number extraction | iv) Histology biopsy size extraction | v) Histology type and site extraction
Rendered fromEndoMineR.Rmdusingknitr::rmarkdown

Last update: 2021-01-30
Started: 2017-09-08

Analysis
2. Assessment of quality functions | a) Documentation Quality | b) Endoscopic Quality | Sedation Usage | 4.Patient flow functions | Sankey plots | Circos plots
Rendered fromAnalysis.Rmdusingknitr::rmarkdown

Last update: 2019-10-03
Started: 2017-12-22

Barrett's Oesophagus
Specific diseases - Barrett's oesophagus | 1. Pre-processing Barrett's samples | a) Prague score | b) Worst pathological stage | c)Follow-up groups | 2.Quality assessment in Barrett's surveillance | Quality of perfomance of Barrett's surveillance endoscopies as just by tissue sampling
Rendered fromBarretts.Rmdusingknitr::rmarkdown

Last update: 2019-10-03
Started: 2017-12-22

Data
Gastroscopy | Raw datasets:
Rendered fromData.Rmdusingknitr::rmarkdown

Last update: 2019-10-03
Started: 2018-03-01

Polyps
Rendered fromPolyps.Rmdusingknitr::rmarkdown

Last update: 2019-10-03
Started: 2019-04-26

Readme and manuals

Help Manual

Help pageTopics
Determine the Follow up groupBarretts_FUType
Get the worst pathological stage for Barrett'sBarretts_PathStage
Extract the Prague scoreBarretts_PragueScore
Run all the basic Barrett's functionsBarrettsAll
Get the number of Barrett's biopsies takenBarrettsBxQual
Run the Paris classification versus worst histopath grade for Barrett'sBarrettsParisEMR
Index biopsy locationsBiopsyIndex
Group anything by Endoscopist and returns the tableCategoricalByEndoscopist
Fake Lower GI Endoscopy SetColonFinal
Tidy up messy columnsColumnCleanUp
OPCS-4 Codingdev_ExtrapolateOPCS4Prep
Dictionary In Place ReplaceDictionaryInPlaceReplace
Basic graph creation using the template specified in theme_Publication.EndoBasicGraph
Merge endoscopy and histology data.Endomerge2
EndoMineR: A package for analysis of endoscopic and related pathologyEndoMineR
Paste endoscopy and histology results into oneEndoPaste
Clean endoscopist columnEndoscEndoscopist
Clean instrument columnEndoscInstrument
Clean medication columnEndoscMeds
Extract the endoscopic event.EndoscopyEvent
See if words from two lists co-exist within a sentenceEntityPairs_OneSentence
Look for relationships between site and eventEntityPairs_TwoSentence
Extract the Prague scoreEosinophilics
Use list of endoscopic events and proceduresEventList
Extract columns from the raw textExtractor
Extrapolate from DictionaryExtrapolatefromDictionary
Index of GI symptomsGISymptomsList
Create GRS metrics by endoscopist (X-ref with pathology)GRS_Type_Assess_By_Unit
Determine the largest biopsy size from the histology reportHistolBxSize
Extract the number of biopsies taken from the histology reportHistolNumbOfBx
Use list of pathology typesHistolType
Extract the site a specimen was removed from as well as the typeHistolTypeAndSite
Number of tests done per month and year by indicationHowManyOverTime
Cleans medication column if presentIBD_Scores
Extract from report, using words from a listListLookup
Use list of upper and lower GI standard locationsLocationList
Use list of standard locations for lower GI endoscopyLocationListLower
Use list of standard locations for upper GI endoscopyLocationListUniversal
Use list of standard locations for upper GI endoscopyLocationListUpper
Plot a metric by endoscopistMetricByEndoscopist
Fake EndoscopiesMyendo
Clean html endoscopic imagesMyImgLibrary
Fake Pathology reportMypath
Remove negative and normal sentencesNegativeRemove
Wrapper for Negative RemoveNegativeRemoveWrapper
Fake Upper GI Pathology SetPathDataFrameFinal
Fake Lower GI Pathology SetPathDataFrameFinalColon
Create a Circos plot for patient flowPatientFlow_CircosPlots
Create a plot over time of patient categorical findings as a line chartPatientFlowIndividual
Use list of catheters used in radiofrequency ablationRFACath
Create a basic consort diagram from dataframessanity
Set the colour theme for all the ggplotsscale_colour_Publication
Set the fills for all the ggplotsscale_fill_Publication
Find and ReplacespellCheck
Extracts the first test only per patientSurveilFirstTest
Extract the last test done by a patient onlySurveilLastTest
Extract the time difference between each test in daysSurveilTimeByRow
Create a Sankey plot for patient flowSurveySankey
Combine all the text cleaning and extraction functions into onetextPrep
Set the publication theme for all the ggplotstheme_Publication
Fake Upper GI Endoscopy SetTheOGDReportFinal
Extract the time to an eventTimeToStatus
Fake Lower GI Endoscopy Set including PathologyvColon
Convetr words to numbers especially for the histopathology textWordsToNumbers