Development and Validation of a Diabetic Retinopathy Risk Stratification Algorithm

Although diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection, and treatment of disease. The study goal was to develop risk stratification algorithms for the onset of retinal complications of diabetes, incl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Diabetes care Jg. 46; H. 5; S. 1068
Hauptverfasser: Tarasewicz, Dariusz, Karter, Andrew J, Pimentel, Noel, Moffet, Howard H, Thai, Khanh K, Schlessinger, David, Sofrygin, Oleg, Melles, Ronald B
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.05.2023
Schlagworte:
ISSN:1935-5548, 1935-5548
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Although diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection, and treatment of disease. The study goal was to develop risk stratification algorithms for the onset of retinal complications of diabetes, including proliferative diabetic retinopathy, referable retinopathy, and macular edema. Retrospective cohort analysis of patients from the Kaiser Permanente Northern California Diabetes Registry who had no evidence of diabetic retinopathy at a baseline diabetic retinopathy screening during 2008-2020 was performed. Machine learning and logistic regression prediction models for onset of proliferative diabetic retinopathy, diabetic macular edema, and referable retinopathy detected through routine screening were trained and internally validated. Model performance was assessed using area under the curve (AUC) metrics. The study cohort (N = 276,794) was 51.9% male and 42.1% White. Mean (±SD) age at baseline was 60.0 (±13.1) years. A machine learning XGBoost algorithm was effective in identifying patients who developed proliferative diabetic retinopathy (AUC 0.86; 95% CI, 0.86-0.87), diabetic macular edema (AUC 0.76; 95% CI, 0.75-0.77), and referable retinopathy (AUC 0.78; 95% CI, 0.78-0.79). Similar results were found using a simpler nine-covariate logistic regression model: proliferative diabetic retinopathy (AUC 0.82; 95% CI, 0.80-0.83), diabetic macular edema (AUC 0.73; 95% CI, 0.72-0.74), and referable retinopathy (AUC 0.75; 95% CI, 0.75-0.76). Relatively simple logistic regression models using nine readily available clinical variables can be used to rank order patients for onset of diabetic eye disease and thereby more efficiently prioritize and target screening for at risk patients.
AbstractList Although diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection, and treatment of disease. The study goal was to develop risk stratification algorithms for the onset of retinal complications of diabetes, including proliferative diabetic retinopathy, referable retinopathy, and macular edema.OBJECTIVEAlthough diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection, and treatment of disease. The study goal was to develop risk stratification algorithms for the onset of retinal complications of diabetes, including proliferative diabetic retinopathy, referable retinopathy, and macular edema.Retrospective cohort analysis of patients from the Kaiser Permanente Northern California Diabetes Registry who had no evidence of diabetic retinopathy at a baseline diabetic retinopathy screening during 2008-2020 was performed. Machine learning and logistic regression prediction models for onset of proliferative diabetic retinopathy, diabetic macular edema, and referable retinopathy detected through routine screening were trained and internally validated. Model performance was assessed using area under the curve (AUC) metrics.RESEARCH DESIGN AND METHODSRetrospective cohort analysis of patients from the Kaiser Permanente Northern California Diabetes Registry who had no evidence of diabetic retinopathy at a baseline diabetic retinopathy screening during 2008-2020 was performed. Machine learning and logistic regression prediction models for onset of proliferative diabetic retinopathy, diabetic macular edema, and referable retinopathy detected through routine screening were trained and internally validated. Model performance was assessed using area under the curve (AUC) metrics.The study cohort (N = 276,794) was 51.9% male and 42.1% White. Mean (±SD) age at baseline was 60.0 (±13.1) years. A machine learning XGBoost algorithm was effective in identifying patients who developed proliferative diabetic retinopathy (AUC 0.86; 95% CI, 0.86-0.87), diabetic macular edema (AUC 0.76; 95% CI, 0.75-0.77), and referable retinopathy (AUC 0.78; 95% CI, 0.78-0.79). Similar results were found using a simpler nine-covariate logistic regression model: proliferative diabetic retinopathy (AUC 0.82; 95% CI, 0.80-0.83), diabetic macular edema (AUC 0.73; 95% CI, 0.72-0.74), and referable retinopathy (AUC 0.75; 95% CI, 0.75-0.76).RESULTSThe study cohort (N = 276,794) was 51.9% male and 42.1% White. Mean (±SD) age at baseline was 60.0 (±13.1) years. A machine learning XGBoost algorithm was effective in identifying patients who developed proliferative diabetic retinopathy (AUC 0.86; 95% CI, 0.86-0.87), diabetic macular edema (AUC 0.76; 95% CI, 0.75-0.77), and referable retinopathy (AUC 0.78; 95% CI, 0.78-0.79). Similar results were found using a simpler nine-covariate logistic regression model: proliferative diabetic retinopathy (AUC 0.82; 95% CI, 0.80-0.83), diabetic macular edema (AUC 0.73; 95% CI, 0.72-0.74), and referable retinopathy (AUC 0.75; 95% CI, 0.75-0.76).Relatively simple logistic regression models using nine readily available clinical variables can be used to rank order patients for onset of diabetic eye disease and thereby more efficiently prioritize and target screening for at risk patients.CONCLUSIONSRelatively simple logistic regression models using nine readily available clinical variables can be used to rank order patients for onset of diabetic eye disease and thereby more efficiently prioritize and target screening for at risk patients.
Although diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection, and treatment of disease. The study goal was to develop risk stratification algorithms for the onset of retinal complications of diabetes, including proliferative diabetic retinopathy, referable retinopathy, and macular edema. Retrospective cohort analysis of patients from the Kaiser Permanente Northern California Diabetes Registry who had no evidence of diabetic retinopathy at a baseline diabetic retinopathy screening during 2008-2020 was performed. Machine learning and logistic regression prediction models for onset of proliferative diabetic retinopathy, diabetic macular edema, and referable retinopathy detected through routine screening were trained and internally validated. Model performance was assessed using area under the curve (AUC) metrics. The study cohort (N = 276,794) was 51.9% male and 42.1% White. Mean (±SD) age at baseline was 60.0 (±13.1) years. A machine learning XGBoost algorithm was effective in identifying patients who developed proliferative diabetic retinopathy (AUC 0.86; 95% CI, 0.86-0.87), diabetic macular edema (AUC 0.76; 95% CI, 0.75-0.77), and referable retinopathy (AUC 0.78; 95% CI, 0.78-0.79). Similar results were found using a simpler nine-covariate logistic regression model: proliferative diabetic retinopathy (AUC 0.82; 95% CI, 0.80-0.83), diabetic macular edema (AUC 0.73; 95% CI, 0.72-0.74), and referable retinopathy (AUC 0.75; 95% CI, 0.75-0.76). Relatively simple logistic regression models using nine readily available clinical variables can be used to rank order patients for onset of diabetic eye disease and thereby more efficiently prioritize and target screening for at risk patients.
Author Karter, Andrew J
Tarasewicz, Dariusz
Sofrygin, Oleg
Thai, Khanh K
Pimentel, Noel
Schlessinger, David
Melles, Ronald B
Moffet, Howard H
Author_xml – sequence: 1
  givenname: Dariusz
  orcidid: 0000-0002-5573-3792
  surname: Tarasewicz
  fullname: Tarasewicz, Dariusz
  organization: 1Department of Ophthalmology, The Permanente Medical Group, Oakland, CA
– sequence: 2
  givenname: Andrew J
  orcidid: 0000-0001-5527-316X
  surname: Karter
  fullname: Karter, Andrew J
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 3
  givenname: Noel
  surname: Pimentel
  fullname: Pimentel, Noel
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 4
  givenname: Howard H
  surname: Moffet
  fullname: Moffet, Howard H
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 5
  givenname: Khanh K
  surname: Thai
  fullname: Thai, Khanh K
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 6
  givenname: David
  surname: Schlessinger
  fullname: Schlessinger, David
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 7
  givenname: Oleg
  surname: Sofrygin
  fullname: Sofrygin, Oleg
  organization: 2Division of Research, Kaiser Permanente, Oakland, CA
– sequence: 8
  givenname: Ronald B
  orcidid: 0000-0003-1027-4083
  surname: Melles
  fullname: Melles, Ronald B
  organization: 1Department of Ophthalmology, The Permanente Medical Group, Oakland, CA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36930723$$D View this record in MEDLINE/PubMed
BookMark eNpN0DtPwzAUBWALFdEHDPwB5JElYF87sT1WLS-pElJ5rNF14lBDEofEReq_p1KLxHLPGT6d4U7JqA2tI-SSsxsQQt2WBUDCeaZPyIQbkSZpKvXoXx-T6TB8Msak1PqMjEVmBFMgJmS9dD-uDl3j2kixLek71r7E6ENLQ0WRLj1aF31B1_vbhg7jZkfXfviiL7Hfu8oXBz2vP0Lv46Y5J6cV1oO7OOaMvN3fvS4ek9Xzw9NivkoKyWRMUrAVOlEVqgRrdYauMNygldZYpa0UgAaAa62sYSK1VZZhmSFnACrTGmBGrg-7XR--t26IeeOHwtU1ti5shxyU0YrLVJg9vTrSrW1cmXe9b7Df5X9_gF_Iu2Aq
CitedBy_id crossref_primary_10_1016_j_ajo_2024_07_039
crossref_primary_10_1016_j_apjo_2024_100109
crossref_primary_10_1136_bmjdrc_2023_003683
crossref_primary_10_1080_07391102_2024_2314269
crossref_primary_10_22399_ijcesen_1971
ContentType Journal Article
Copyright 2023 by the American Diabetes Association.
Copyright_xml – notice: 2023 by the American Diabetes Association.
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.2337/dc22-1168
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 1935-5548
ExternalDocumentID 36930723
Genre Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NIDDK NIH HHS
  grantid: P30 DK092924
GroupedDBID ---
-ET
..I
.XZ
08P
0R~
18M
29F
2WC
4.4
53G
5GY
5RE
5RS
5VS
6PF
8R4
8R5
AAIKC
AAMNW
AAWTL
AAYEP
ABOCM
ABPPZ
ACGFO
ACGOD
ADBBV
AEGXH
AENEX
AERZD
AFOSN
AFRAH
AHMBA
AIAGR
ALIPV
ALMA_UNASSIGNED_HOLDINGS
BAWUL
BENPR
BTFSW
CGR
CS3
CUY
CVF
DIK
DU5
E3Z
EBS
ECM
EDB
EIF
EMOBN
EX3
F5P
GX1
H13
HZ~
IAO
IEA
IHR
INH
INR
IOF
IPO
KQ8
L7B
M0K
M5~
NPM
O5R
O5S
O9-
OK1
OVD
P2P
PCD
Q2X
RHI
SV3
TDI
TEORI
TR2
TWZ
VVN
W8F
WH7
WOQ
WOW
YHG
YOC
ZCG
~KM
7X8
AAFWJ
ID FETCH-LOGICAL-c404t-52bfae3fc7d2bb86aec919ab4b9b78b432a9221887b9035bf66ad6a1022768822
IEDL.DBID 7X8
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001017248100042&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1935-5548
IngestDate Sun Nov 09 09:34:53 EST 2025
Thu Apr 03 06:57:07 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
License 2023 by the American Diabetes Association.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c404t-52bfae3fc7d2bb86aec919ab4b9b78b432a9221887b9035bf66ad6a1022768822
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-1027-4083
0000-0002-5573-3792
0000-0001-5527-316X
OpenAccessLink https://pmc.ncbi.nlm.nih.gov/articles/PMC10257789/pdf/dc221168.pdf
PMID 36930723
PQID 2798714539
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2798714539
pubmed_primary_36930723
PublicationCentury 2000
PublicationDate 2023-05-01
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 05
  year: 2023
  text: 2023-05-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Diabetes care
PublicationTitleAlternate Diabetes Care
PublicationYear 2023
SSID ssj0004488
Score 2.4652812
Snippet Although diabetic retinopathy is a leading cause of blindness worldwide, diabetes-related blindness can be prevented through effective screening, detection,...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 1068
SubjectTerms Aged
Algorithms
Blindness
Diabetes Mellitus
Diabetic Retinopathy - diagnosis
Diabetic Retinopathy - epidemiology
Female
Humans
Macular Edema - diagnosis
Macular Edema - epidemiology
Macular Edema - etiology
Male
Middle Aged
Retrospective Studies
Risk Assessment
Title Development and Validation of a Diabetic Retinopathy Risk Stratification Algorithm
URI https://www.ncbi.nlm.nih.gov/pubmed/36930723
https://www.proquest.com/docview/2798714539
Volume 46
WOSCitedRecordID wos001017248100042&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/eLvHCXMwpV1LS8NAEF7Uinjx_agvVvAa2mQ3-zhJEcVLSykqvYV9ZLWoSTVV8N87m02xF0HwktOGLMNk5_tmZudD6AJAcpflVkUpU9qnbkwkcq4jToRTVjIIiUFsgg8GYjyWwybhVjVtlfMzsT6obWl8jryTcGDHMU2JvJy-RV41yldXGwmNZdQiAGW8V_PxwrRwWutOAkZJIwibIkwWSgjhHWuAhMUxE78jyzrC3Gz-d29baKPBlrgXnGEbLeXFDlrrN9XzXTRa6BDCqrD4AUB40FTCpcMKh_aYicEjfxG69GrFX3g0qZ5xPcTWdxWF1b2XR_j-7Ol1D93fXN9d3UaNpkJkaJfOgHdqp3LiDLeJ1oKp3MhYKk211FxoShIlEwj7gmvZJal2jCnLlOeFQEwATeyjlaIs8kOEuZNcx4QD4VNUUSeklalzsfZTxJgSbXQ-t1YGPusLEarIy48q-7FXGx0Ek2fTMFwjI16bkSfk6A9vH6N1r_4e-g9PUMvBH5ufolXzOZtU72e1M8BzMOx_A6gDvwU
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=Development+and+Validation+of+a+Diabetic+Retinopathy+Risk+Stratification+Algorithm&rft.jtitle=Diabetes+care&rft.au=Tarasewicz%2C+Dariusz&rft.au=Karter%2C+Andrew+J&rft.au=Pimentel%2C+Noel&rft.au=Moffet%2C+Howard+H&rft.date=2023-05-01&rft.eissn=1935-5548&rft.volume=46&rft.issue=5&rft.spage=1068&rft_id=info:doi/10.2337%2Fdc22-1168&rft_id=info%3Apmid%2F36930723&rft_id=info%3Apmid%2F36930723&rft.externalDocID=36930723
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1935-5548&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1935-5548&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1935-5548&client=summon