Utility of a Rule-Based Algorithm in the Assessment of Standardized Reporting in PI-RADS

Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostat...

Full description

Saved in:
Bibliographic Details
Published in:Academic radiology Vol. 30; no. 6; p. 1141
Main Authors: Zhang, Dylan, Neely, Ben, Lo, Joseph Y, Patel, Bhavik N, Hyslop, Terry, Gupta, Rajan T
Format: Journal Article
Language:English
Published: United States 01.06.2023
Subjects:
ISSN:1878-4046, 1878-4046
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement. All prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm. Compared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report. Rule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.
AbstractList Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement.RATIONALE AND OBJECTIVESAdoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement.All prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm.MATERIALS AND METHODSAll prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm.Compared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report.RESULTSCompared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report.Rule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.CONCLUSIONRule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.
Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement. All prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm. Compared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report. Rule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.
Author Lo, Joseph Y
Zhang, Dylan
Neely, Ben
Gupta, Rajan T
Hyslop, Terry
Patel, Bhavik N
Author_xml – sequence: 1
  givenname: Dylan
  surname: Zhang
  fullname: Zhang, Dylan
  organization: Department of Radiology, Duke University Medical Center, Durham, North Carolina, USA
– sequence: 2
  givenname: Ben
  surname: Neely
  fullname: Neely, Ben
  organization: Duke Clinical Research Institute, Duke University Medical Center, Durham, North Carolina, USA
– sequence: 3
  givenname: Joseph Y
  surname: Lo
  fullname: Lo, Joseph Y
  organization: Department of Radiology, Duke University Medical Center, Durham, North Carolina, USA
– sequence: 4
  givenname: Bhavik N
  surname: Patel
  fullname: Patel, Bhavik N
  organization: Department of Radiology, Mayo Clinic Arizona, Phoenix, Arizona, USA
– sequence: 5
  givenname: Terry
  surname: Hyslop
  fullname: Hyslop, Terry
  organization: Duke Clinical Research Institute, Duke University Medical Center, Durham, North Carolina, USA; Duke Cancer Institute, Durham, North Carolina, USA
– sequence: 6
  givenname: Rajan T
  surname: Gupta
  fullname: Gupta, Rajan T
  email: rajan.gupta@duke.edu
  organization: Department of Radiology, Duke University Medical Center, Durham, North Carolina, USA; Division of Urology, Duke University Medical Center, Durham, North Carolina, USA; Duke Cancer Institute Center for Prostate and Urologic Cancers, Durham, North Carolina, USA. Electronic address: rajan.gupta@duke.edu
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35909050$$D View this record in MEDLINE/PubMed
BookMark eNpN0DtPwzAUBWALFdEH_AEGlJEl4dpx7GQMLY9KlUAtldgix7ltXeVRYmcov55UFInpnOHTGc6YDOqmRkJuKQQUqHjYB0q3KmDAWAAiAMYvyIjGMvY5cDH414dkbO0egEYiDq_IMIwSSCCCEflcO1Mad_Sajae8ZVei_6gsFl5abpvWuF3lmdpzO_RSa9HaCmt3siun6kK1hfnu7RIPTetMvT3Z97m_TGera3K5UaXFm3NOyPr56WP66i_eXubTdOFrDtL5Ra5orLmQoi9Ui5yLgmKEKBKJSiqJGFIaJ7nQQigeMrFJOBYolVYagLMJuf_dPbTNV4fWZZWxGstS1dh0NmP9ECSRZKynd2fa5RUW2aE1lWqP2d8b7Ad-AGPU
CitedBy_id crossref_primary_10_1007_s11517_024_03131_x
crossref_primary_10_1200_CCI_25_00085
crossref_primary_10_1016_j_acra_2023_08_005
crossref_primary_10_1016_j_rpth_2025_102896
crossref_primary_10_1016_j_imu_2023_101309
ContentType Journal Article
Copyright Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1016/j.acra.2022.06.024
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Medicine
EISSN 1878-4046
ExternalDocumentID 35909050
Genre Journal Article
GroupedDBID ---
--K
.1-
.FO
.GJ
0R~
1B1
1P~
23M
4.4
457
53G
5GY
5RE
5VS
AAEDT
AAEDW
AALRI
AAQFI
AAQXK
AAWTL
AAXUO
ABJNI
ABMAC
ABWVN
ACGFS
ACRPL
ADBBV
ADMUD
ADNMO
AENEX
AEVXI
AFCTW
AFFNX
AFJKZ
AFRHN
AFTJW
AITUG
AJUYK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ASPBG
AVWKF
AZFZN
BELOY
C5W
CGR
CS3
CUY
CVF
EBS
ECM
EFJIC
EIF
EJD
F5P
FDB
FEDTE
FGOYB
G-Q
HVGLF
HZ~
IHE
J1W
KOM
M41
MO0
NPM
NQ-
O9-
OI~
OU0
P2P
R2-
ROL
RPZ
SEL
SES
SEW
SJN
SSZ
UHS
XH2
Z5R
ZGI
ZXP
7X8
APXCP
EFKBS
ID FETCH-LOGICAL-c407t-dba18c4676ba11c6b46d1e5ee697ea7a7ee31189b6c66a4326f94ede7acac0042
IEDL.DBID 7X8
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001001884800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1878-4046
IngestDate Sun Sep 28 07:23:14 EDT 2025
Thu Apr 03 07:01:17 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Keywords prostate cancer
standardized reporting
MRI
quality improvement
imaging informatics
Language English
License Copyright © 2022 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c407t-dba18c4676ba11c6b46d1e5ee697ea7a7ee31189b6c66a4326f94ede7acac0042
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 35909050
PQID 2697095722
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2697095722
pubmed_primary_35909050
PublicationCentury 2000
PublicationDate 2023-06-00
20230601
PublicationDateYYYYMMDD 2023-06-01
PublicationDate_xml – month: 06
  year: 2023
  text: 2023-06-00
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Academic radiology
PublicationTitleAlternate Acad Radiol
PublicationYear 2023
SSID ssj0015683
Score 2.3956387
Snippet Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 1141
SubjectTerms Algorithms
Humans
Image-Guided Biopsy - methods
Magnetic Resonance Imaging - methods
Male
Multiparametric Magnetic Resonance Imaging
Prostate - pathology
Prostatic Neoplasms - diagnostic imaging
Prostatic Neoplasms - pathology
Retrospective Studies
Title Utility of a Rule-Based Algorithm in the Assessment of Standardized Reporting in PI-RADS
URI https://www.ncbi.nlm.nih.gov/pubmed/35909050
https://www.proquest.com/docview/2697095722
Volume 30
WOSCitedRecordID wos001001884800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ZS8NAEF7UivjifdSLFXwN5tzNPkk8ioItpbWSt7DZ3WihJrVNBf31ziZb-yQIvoQEJksyzM58s3MhdOF41HVtyiw_DDLLV54PelDCYypTBp4c41VV2vMj7XTCOGZdc-A2NWmVc51YKWpZCH1GfukSRgEOwMpX43dLT43S0VUzQmMZNTyAMjqli8aLKEJAqjacTgiekg-OoCmaqfO7uJjovkOuW_Xv1BXvv0HMytS0Nv_7kVtow4BMHNVSsY2WVL6D1tomjL6L4kGpU2I_cZFhjnuzkbKuwZpJHI1eYLny9Q0PcwzQEEc_jTs1bd-cOwy_gLaG7mD5NG33wepFt_09NGjdPd3cW2bEgiXAkystmXInFKAsCdw4gqQ-kY4KlIIfUZxyqpQHLghLiSCE-4D1MuYrqSgXXOgNv49W8iJXhwgrKbKUuzINXQbMVswRzM4kZUGYURLIJjqf8ywBEdZxCZ6rYjZNFlxrooOa8cm47rWReAGzmR3YR394-xit62HwdSLXCWpksIHVKVoVH-VwOjmrZAOunW77G843wvQ
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Utility+of+a+Rule-Based+Algorithm+in+the+Assessment+of+Standardized+Reporting+in+PI-RADS&rft.jtitle=Academic+radiology&rft.au=Zhang%2C+Dylan&rft.au=Neely%2C+Ben&rft.au=Lo%2C+Joseph+Y&rft.au=Patel%2C+Bhavik+N&rft.date=2023-06-01&rft.eissn=1878-4046&rft.volume=30&rft.issue=6&rft.spage=1141&rft_id=info:doi/10.1016%2Fj.acra.2022.06.024&rft_id=info%3Apmid%2F35909050&rft_id=info%3Apmid%2F35909050&rft.externalDocID=35909050
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1878-4046&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1878-4046&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1878-4046&client=summon