Prediction of diabetic kidney disease risk using machine learning models: A population-based cohort study of Asian adults
Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD). We utilized longitudinal data from 1365 Chinese, Malay, and Indian particip...
Gespeichert in:
| Veröffentlicht in: | eLife Jg. 12 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
England
eLife Sciences Publications Ltd
14.09.2023
eLife Sciences Publications, Ltd |
| Schlagworte: | |
| ISSN: | 2050-084X, 2050-084X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD).
We utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40-80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004-2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m
with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC).
ML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847-0.856), which was 7.0% relatively higher than by LR 0.795 (0.790-0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies.
Our results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites.
This study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. |
|---|---|
| AbstractList | Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD).
We utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40-80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004-2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m
with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC).
ML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847-0.856), which was 7.0% relatively higher than by LR 0.795 (0.790-0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies.
Our results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites.
This study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Background:Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD).Methods:We utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40–80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004–2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC).Results:ML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847–0.856), which was 7.0% relatively higher than by LR 0.795 (0.790–0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies.Conclusions:Our results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites.Funding:This study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD).BackgroundMachine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD).We utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40-80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004-2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC).MethodsWe utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40-80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004-2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC).ML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847-0.856), which was 7.0% relatively higher than by LR 0.795 (0.790-0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies.ResultsML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847-0.856), which was 7.0% relatively higher than by LR 0.795 (0.790-0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies.Our results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites.ConclusionsOur results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites.This study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.FundingThis study was supported by the National Medical Research Council, NMRC/OFLCG/001/2017 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Background: Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML algorithms for predicting incident diabetic kidney disease (DKD). Methods: We utilized longitudinal data from 1365 Chinese, Malay, and Indian participants aged 40–80 y with diabetes but free of DKD who participated in the baseline and 6-year follow-up visit of the Singapore Epidemiology of Eye Diseases Study (2004–2017). Incident DKD (11.9%) was defined as an estimated glomerular filtration rate (eGFR) <60 mL/min/1.73 m2 with at least 25% decrease in eGFR at follow-up from baseline. A total of 339 features, including participant characteristics, retinal imaging, and genetic and blood metabolites, were used as predictors. Performances of several ML models were compared to each other and to logistic regression (LR) model based on established features of DKD (age, sex, ethnicity, duration of diabetes, systolic blood pressure, HbA1c, and body mass index) using area under the receiver operating characteristic curve (AUC). Results: ML model Elastic Net (EN) had the best AUC (95% CI) of 0.851 (0.847–0.856), which was 7.0% relatively higher than by LR 0.795 (0.790–0.801). Sensitivity and specificity of EN were 88.2 and 65.9% vs. 73.0 and 72.8% by LR. The top 15 predictors included age, ethnicity, antidiabetic medication, hypertension, diabetic retinopathy, systolic blood pressure, HbA1c, eGFR, and metabolites related to lipids, lipoproteins, fatty acids, and ketone bodies. Conclusions: Our results showed that ML, together with feature selection, improves prediction accuracy of DKD risk in an asymptomatic stable population and identifies novel risk factors, including metabolites. Funding: This study was supported by the Singapore Ministry of Health’s National Medical Research Council, NMRC/OFLCG/MOH-001327-03 and NMRC/HCSAINV/MOH-001019-00. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. |
| Author | Tan, Gavin Cheng, Ching Yu Lim, Cynthia Sabanayagam, Charumathi He, Feng Li, Jialiang Nusinovici, Simon |
| Author_xml | – sequence: 1 givenname: Charumathi orcidid: 0000-0002-4042-4719 surname: Sabanayagam fullname: Sabanayagam, Charumathi – sequence: 2 givenname: Feng orcidid: 0000-0002-4717-2243 surname: He fullname: He, Feng – sequence: 3 givenname: Simon surname: Nusinovici fullname: Nusinovici, Simon – sequence: 4 givenname: Jialiang surname: Li fullname: Li, Jialiang – sequence: 5 givenname: Cynthia surname: Lim fullname: Lim, Cynthia – sequence: 6 givenname: Gavin surname: Tan fullname: Tan, Gavin – sequence: 7 givenname: Ching Yu surname: Cheng fullname: Cheng, Ching Yu |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37706530$$D View this record in MEDLINE/PubMed |
| BookMark | eNptks9rHCEUx4eS0qRpTr0XoZdCmVRHHZ1ewhL6I7DQHlroTRx97rqZ1a3OFPa_rzubhiTUi_r8vC_v-X0vq5MQA1TVa4IvBefsAyy9g0tJpJDPqrMGc1xjyX6dPDifVhc5b3BZgklJuhfVKRUCt5zis2r_PYH1ZvQxoOiQ9bqH0Rt0622Afbln0BlQ8vkWTdmHFdpqs_YB0AA6hTkQLQz5I1qgXdxNgz5o1X3JssjEdUwjyuNk9wf5RfY6IG2nYcyvqudODxku7vbz6ufnTz-uv9bLb19urhfL2jDRjrU1jui-x22De82pZpoz12HmuAMBknXcaCowNoQDN6IVrjEWY6DOdQDc0vPq5qhro96oXfJbnfYqaq_mQEwrpVNpeQBFtDHGcUqxwAxa22tKOmok59ayhvGidXXU2k39FqyBMCY9PBJ9_BL8Wq3iH0Uwp4R2B4V3dwop_p4gj2rrs4Fh0AHilFUjW9ZhXHwq6Nsn6CZOKZS_KlTxTzLZdYV687Ck-1r-WVyA90fApJhzAnePEKwOM6TmGVLzDBWaPKGNH2dLSz9--G_OX4BPzJE |
| CitedBy_id | crossref_primary_10_1136_bmjopen_2024_086032 crossref_primary_10_1016_S2213_8587_24_00154_2 crossref_primary_10_1007_s12020_023_03637_8 crossref_primary_10_2337_dc25_0355 crossref_primary_10_1016_j_nefroe_2025_101330 crossref_primary_10_3390_jcm14062065 crossref_primary_10_1016_j_ijmedinf_2025_105975 crossref_primary_10_1016_j_nefro_2025_501403 crossref_primary_10_1080_03007995_2024_2423737 crossref_primary_10_1186_s13040_024_00369_x crossref_primary_10_1007_s00371_025_04045_x crossref_primary_10_1038_s41598_024_66548_2 crossref_primary_10_3389_fendo_2025_1495306 crossref_primary_10_1016_j_nefro_2025_03_001 crossref_primary_10_3390_jcm14134735 |
| Cites_doi | 10.1016/j.jval.2019.02.012 10.3399/bjgp20X708245 10.2337/db20-0586 10.1007/978-0-387-84858-7 10.3109/09286580903144738 10.2196/15510 10.1371/journal.pone.0158765 10.1038/s41591-018-0239-8 10.2215/CJN.11491116 10.1161/HYPERTENSIONAHA.120.13516 10.7326/0003-4819-150-9-200905050-00006 10.1038/s41581-020-0278-5 10.1080/09286580600878844 10.1038/s41598-017-09204-2 10.1007/s00125-018-4567-5 10.2337/dc19-1897 10.7326/0003-4819-158-11-201306040-00007 10.1016/j.ophtha.2016.11.016 10.1155/2020/4074832 10.1016/S0140-6736(16)32064-5 10.1038/ki.2011.368 10.1136/bmjdrc-2021-002364 10.1001/jama.2019.17379 10.3390/metabo11090614 10.2215/CJN.10321014 10.1053/j.ajkd.2011.02.382 10.1071/PY17156 10.5694/j.1326-5377.2008.tb01585.x 10.1016/j.jclinepi.2020.03.002 10.1093/ndt/gfq084 10.1093/aje/kwz189 10.1093/ije/dyab114 10.3390/ijerph16081443 10.1016/j.diabres.2017.03.024 10.1038/s41581-020-0286-5 10.1371/journal.pone.0162909 10.1001/jamanetworkopen.2019.1540 |
| ContentType | Journal Article |
| Copyright | 2023, Sabanayagam et al. 2023, Sabanayagam et al. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023, Sabanayagam et al 2023 Sabanayagam et al |
| Copyright_xml | – notice: 2023, Sabanayagam et al. – notice: 2023, Sabanayagam et al. This work is published under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023, Sabanayagam et al 2023 Sabanayagam et al |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88E 88I 8FE 8FH 8FI 8FJ 8FK ABUWG AFKRA AZQEC BBNVY BENPR BHPHI CCPQU DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. LK8 M0S M1P M2P M7P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS Q9U 7X8 5PM DOA |
| DOI | 10.7554/eLife.81878 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) ProQuest Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials Biological Science Collection (subscription) ProQuest Central Natural Science Collection ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Premium Collection ProQuest Health & Medical Complete (Alumni) Biological Sciences Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) Science Database (subscription) Biological Science Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest Central Student ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Health & Medical Research Collection Biological Science Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Science Journals (Alumni Edition) ProQuest Biological Science Collection ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE Publicly Available Content Database MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 2050-084X |
| ExternalDocumentID | oai_doaj_org_article_1acccf5330704e6dba3193c855dd4245 PMC10531395 37706530 10_7554_eLife_81878 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GeographicLocations | Singapore |
| GeographicLocations_xml | – name: Singapore |
| GrantInformation_xml | – fundername: ; grantid: NMRC/OFLCG/001/2017 – fundername: ; grantid: NMRC/HCSAINV/MOH-001019-00 |
| GroupedDBID | 53G 5VS 7X7 88E 88I 8FE 8FH 8FI 8FJ AAFWJ AAKDD AAYXX ABUWG ACGFO ACGOD ACPRK ADBBV ADRAZ AENEX AFFHD AFKRA AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS AZQEC BAWUL BBNVY BCNDV BENPR BHPHI BPHCQ BVXVI CCPQU CITATION DIK DWQXO EMOBN FYUFA GNUQQ GROUPED_DOAJ GX1 HCIFZ HMCUK HYE IAO IEA IHR INH INR ISR ITC KQ8 LK8 M1P M2P M48 M7P M~E NQS OK1 PGMZT PHGZM PHGZT PIMPY PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO RHI RNS RPM UKHRP ALIPV CGR CUY CVF ECM EIF NPM 3V. 7XB 8FK K9. PKEHL PQEST PQUKI PRINS Q9U 7X8 5PM |
| ID | FETCH-LOGICAL-c476t-dcf1abb0620ba53a4a54f904f5fe7e8495ca3700c15e5c767f2cd00e3ff9ee5d3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 15 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001076921800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2050-084X |
| IngestDate | Fri Oct 03 12:50:30 EDT 2025 Tue Nov 04 02:06:27 EST 2025 Sun Nov 09 12:39:17 EST 2025 Tue Oct 07 07:04:58 EDT 2025 Mon Jul 21 05:34:39 EDT 2025 Sat Nov 29 06:59:14 EST 2025 Tue Nov 18 21:26:00 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | global health predictors epidemiology GBDT none DKD elastic net incidence metabolites |
| Language | English |
| License | 2023, Sabanayagam et al. This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c476t-dcf1abb0620ba53a4a54f904f5fe7e8495ca3700c15e5c767f2cd00e3ff9ee5d3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-4042-4719 0000-0002-4717-2243 |
| OpenAccessLink | https://doaj.org/article/1acccf5330704e6dba3193c855dd4245 |
| PMID | 37706530 |
| PQID | 2870684899 |
| PQPubID | 2045579 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_1acccf5330704e6dba3193c855dd4245 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10531395 proquest_miscellaneous_2864900881 proquest_journals_2870684899 pubmed_primary_37706530 crossref_primary_10_7554_eLife_81878 crossref_citationtrail_10_7554_eLife_81878 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-09-14 |
| PublicationDateYYYYMMDD | 2023-09-14 |
| PublicationDate_xml | – month: 09 year: 2023 text: 2023-09-14 day: 14 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England – name: Cambridge |
| PublicationTitle | eLife |
| PublicationTitleAlternate | Elife |
| PublicationYear | 2023 |
| Publisher | eLife Sciences Publications Ltd eLife Sciences Publications, Ltd |
| Publisher_xml | – name: eLife Sciences Publications Ltd – name: eLife Sciences Publications, Ltd |
| References | Nusinovici (bib26) 2020; 122 Nelson (bib25) 2019; 322 Jiang (bib17) 2020; 43 National Registry of Diseases Office (bib24) 2020 Song (bib32) 2020; 8 Bi (bib2) 2019; 188 Yau (bib37) 2011; 58 Quek (bib28) 2021; 11 Colhoun (bib5) 2018; 61 Hastie (bib11) 2009 Alicic (bib1) 2017; 12 Chong (bib3) 2017; 124 Cole (bib4) 2020; 16 Lavanya (bib18) 2009; 16 Stevens (bib33) 2013; 158 Foong (bib10) 2007; 14 Levey (bib19) 2009; 150 Mathi Thumilan (bib23) 2016; 11 Ravizza (bib29) 2019; 25 Ogurtsova (bib27) 2017; 128 Sabanayagam (bib31) 2019; 2 Dunkler (bib8) 2015; 10 Eddy (bib9) 2020; 16 Sabanayagam (bib30) 2010; 25 Webster (bib35) 2017; 389 Doupe (bib7) 2019; 22 Huang (bib14) 2020; 69 Majithia (bib21) 2021; 50 Yip (bib38) 2017; 7 Manski-Nankervis (bib22) 2018; 24 Lim (bib20) 2021; 9 Hussain (bib16) 2019; 16 Hirst (bib13) 2020; 70 Huang (bib15) 2020; 2020 Couser (bib6) 2011; 80 White (bib36) 2008; 188 Hill (bib12) 2016; 11 Sundström (bib34) 2020; 75 |
| References_xml | – volume: 22 start-page: 808 year: 2019 ident: bib7 article-title: Machine learning for health services researchers publication-title: Value in Health doi: 10.1016/j.jval.2019.02.012 – volume: 70 start-page: e285 year: 2020 ident: bib13 article-title: Prevalence of chronic kidney disease in the community using data from OxRen: a UK population-based cohort study publication-title: The British Journal of General Practice doi: 10.3399/bjgp20X708245 – volume: 69 start-page: 2756 year: 2020 ident: bib14 article-title: Machine learning approaches reveal metabolic signatures of incident chronic kidney disease in individuals with prediabetes and type 2 diabetes publication-title: Diabetes doi: 10.2337/db20-0586 – volume-title: The Elements of Statistical Learning: Data Mining, Inference, and Prediction year: 2009 ident: bib11 doi: 10.1007/978-0-387-84858-7 – volume: 16 start-page: 325 year: 2009 ident: bib18 article-title: Methodology of the Singapore Indian Chinese Cohort (SICC) eye study: quantifying ethnic variations in the epidemiology of eye diseases in Asians publication-title: Ophthalmic Epidemiology doi: 10.3109/09286580903144738 – volume: 8 year: 2020 ident: bib32 article-title: Longitudinal risk prediction of chronic kidney disease in diabetic patients using a temporal-enhanced gradient boosting machine: retrospective cohort study publication-title: JMIR Medical Informatics doi: 10.2196/15510 – volume: 11 year: 2016 ident: bib12 article-title: Global Prevalence of Chronic Kidney Disease - a systematic review and meta-analysis publication-title: PLOS ONE doi: 10.1371/journal.pone.0158765 – volume: 25 start-page: 57 year: 2019 ident: bib29 article-title: Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data publication-title: Nature Medicine doi: 10.1038/s41591-018-0239-8 – volume: 12 start-page: 2032 year: 2017 ident: bib1 article-title: Diabetic Kidney Disease: challenges, progress, and possibilities publication-title: Clinical Journal of the American Society of Nephrology doi: 10.2215/CJN.11491116 – volume: 75 start-page: 1165 year: 2020 ident: bib34 article-title: Machine learning in risk prediction publication-title: Hypertension doi: 10.1161/HYPERTENSIONAHA.120.13516 – volume: 150 start-page: 604 year: 2009 ident: bib19 article-title: A new equation to estimate glomerular filtration rate publication-title: Annals of Internal Medicine doi: 10.7326/0003-4819-150-9-200905050-00006 – volume: 16 start-page: 377 year: 2020 ident: bib4 article-title: Genetics of diabetes mellitus and diabetes complications publication-title: Nature Reviews. Nephrology doi: 10.1038/s41581-020-0278-5 – volume: 14 start-page: 25 year: 2007 ident: bib10 article-title: Rationale and methodology for a population-based study of eye diseases in Malay people: The Singapore Malay eye study (SiMES) publication-title: Ophthalmic Epidemiology doi: 10.1080/09286580600878844 – volume: 7 year: 2017 ident: bib38 article-title: Retinal vascular imaging markers and incident chronic kidney disease: a prospective cohort study publication-title: Scientific Reports doi: 10.1038/s41598-017-09204-2 – volume: 61 start-page: 996 year: 2018 ident: bib5 article-title: Biomarkers of diabetic kidney disease publication-title: Diabetologia doi: 10.1007/s00125-018-4567-5 – volume: 43 start-page: 925 year: 2020 ident: bib17 article-title: Establishment and validation of a risk prediction model for early diabetic kidney disease based on a systematic review and meta-analysis of 20 cohorts publication-title: Diabetes Care doi: 10.2337/dc19-1897 – volume: 158 start-page: 825 year: 2013 ident: bib33 article-title: Evaluation and management of chronic kidney disease: synopsis of the kidney disease: improving global outcomes 2012 clinical practice guideline publication-title: Annals of Internal Medicine doi: 10.7326/0003-4819-158-11-201306040-00007 – volume: 124 start-page: 336 year: 2017 ident: bib3 article-title: Type 2 diabetes genetic variants and risk of diabetic retinopathy publication-title: Ophthalmology doi: 10.1016/j.ophtha.2016.11.016 – volume: 2020 year: 2020 ident: bib15 article-title: Short-Chain Fatty Acids Ameliorate Diabetic Nephropathy via GPR43-Mediated inhibition of Oxidative Stress and NF-κB Signaling publication-title: Oxidative Medicine and Cellular Longevity doi: 10.1155/2020/4074832 – volume: 389 start-page: 1238 year: 2017 ident: bib35 article-title: Chronic Kidney Disease publication-title: Lancet doi: 10.1016/S0140-6736(16)32064-5 – year: 2020 ident: bib24 article-title: Singapore Renal Registry Annual Report 2020 – volume: 80 start-page: 1258 year: 2011 ident: bib6 article-title: The contribution of chronic kidney disease to the global burden of major noncommunicable diseases publication-title: Kidney International doi: 10.1038/ki.2011.368 – volume: 9 year: 2021 ident: bib20 article-title: Application of machine learning techniques to understand ethnic differences and risk factors for incident chronic kidney disease in Asians publication-title: BMJ Open Diabetes Research & Care doi: 10.1136/bmjdrc-2021-002364 – volume: 322 start-page: 2104 year: 2019 ident: bib25 article-title: Development of risk prediction equations for incident chronic kidney disease publication-title: JAMA doi: 10.1001/jama.2019.17379 – volume: 11 year: 2021 ident: bib28 article-title: Novel serum and urinary metabolites associated with diabetic retinopathy in three asian cohorts publication-title: Metabolites doi: 10.3390/metabo11090614 – volume: 10 start-page: 1371 year: 2015 ident: bib8 article-title: Risk Prediction for Early CKD in Type 2 Diabetes publication-title: Clinical Journal of the American Society of Nephrology doi: 10.2215/CJN.10321014 – volume: 58 start-page: 39 year: 2011 ident: bib37 article-title: Retinal arteriolar narrowing and subsequent development of CKD Stage 3: the Multi-Ethnic Study of Atherosclerosis (MESA) publication-title: American Journal of Kidney Diseases doi: 10.1053/j.ajkd.2011.02.382 – volume: 24 start-page: 280 year: 2018 ident: bib22 article-title: Screening and diagnosis of chronic kidney disease in people with type 2 diabetes attending Australian general practice publication-title: Australian Journal of Primary Health doi: 10.1071/PY17156 – volume: 188 start-page: 204 year: 2008 ident: bib36 article-title: Limited knowledge of kidney disease in a survey of AusDiab study participants publication-title: The Medical Journal of Australia doi: 10.5694/j.1326-5377.2008.tb01585.x – volume: 122 start-page: 56 year: 2020 ident: bib26 article-title: Logistic regression was as good as machine learning for predicting major chronic diseases publication-title: Journal of Clinical Epidemiology doi: 10.1016/j.jclinepi.2020.03.002 – volume: 25 start-page: 2564 year: 2010 ident: bib30 article-title: Ethnic disparities in prevalence and impact of risk factors of chronic kidney disease publication-title: Nephrology, Dialysis, Transplantation doi: 10.1093/ndt/gfq084 – volume: 188 start-page: 2222 year: 2019 ident: bib2 article-title: What is machine learning? A primer for the epidemiologist publication-title: American Journal of Epidemiology doi: 10.1093/aje/kwz189 – volume: 50 year: 2021 ident: bib21 article-title: Corrigendum to: Cohort profile: the Singapore Epidemiology of Eye Diseases Study (SEED) publication-title: International Journal of Epidemiology doi: 10.1093/ije/dyab114 – volume: 16 year: 2019 ident: bib16 article-title: Limited knowledge of Chronic Kidney Disease among Type 2 Diabetes Mellitus Patients in India publication-title: International Journal of Environmental Research and Public Health doi: 10.3390/ijerph16081443 – volume: 128 start-page: 40 year: 2017 ident: bib27 article-title: IDF Diabetes Atlas: Global estimates for the prevalence of diabetes for 2015 and 2040 publication-title: Diabetes Research and Clinical Practice doi: 10.1016/j.diabres.2017.03.024 – volume: 16 start-page: 657 year: 2020 ident: bib9 article-title: Integrated multi-omics approaches to improve classification of chronic kidney disease publication-title: Nature Reviews. Nephrology doi: 10.1038/s41581-020-0286-5 – volume: 11 year: 2016 ident: bib23 article-title: Development and characterization of genic SSR markers from Indian Mulberry transcriptome and their transferability to related Species of Moraceae publication-title: PLOS ONE doi: 10.1371/journal.pone.0162909 – volume: 2 year: 2019 ident: bib31 article-title: Association of diabetic retinopathy and diabetic kidney disease with all-cause and cardiovascular mortality in a Multiethnic Asian Population publication-title: JAMA Network Open doi: 10.1001/jamanetworkopen.2019.1540 |
| SSID | ssj0000748819 |
| Score | 2.458006 |
| Snippet | Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the accuracy of ML... Background:Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the... Background: Machine learning (ML) techniques improve disease prediction by identifying the most relevant features in multidimensional data. We compared the... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| SubjectTerms | Adult Antidiabetics Biomarkers Blood pressure Body mass index Cholesterol Cohort analysis Cohort Studies Creatinine Data collection Diabetes Diabetes Mellitus Diabetic Nephropathies - diagnosis Diabetic Nephropathies - epidemiology Diabetic nephropathy Diabetic retinopathy DKD elastic net Epidemiology Epidemiology and Global Health Epidermal growth factor receptors Eye diseases Fatty acids GBDT Glomerular filtration rate Glucose Glycated Hemoglobin High density lipoprotein Humans incidence Ketones Kidney diseases Learning algorithms Lipid metabolism Lipids Lipoproteins Machine Learning Medical research Metabolism Metabolites Minority & ethnic groups Performance evaluation Population Population studies Population-based studies Predictions predictors Research Design Retinopathy Risk factors |
| SummonAdditionalLinks | – databaseName: ProQuest Health & Medical Collection dbid: 7X7 link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELaggNQLb0qgICNxQjJ1YjuOuaAFUXGoqh5A2lvk-NFGQLIkW6T993gcb-iiigvXeBSNNE_PjOdD6LUp4DmkskTonBFecE20LThpFCyvMpYJHh8Kn8jT02q5VGep4DamscqtT4yO2vYGauRHsSFX8XA9eL_6SQA1CrqrCULjJroFsNmg53Ip5xpLCI9ViHjTszwZAueRO2m9exuCFMCqXQlEcV__dUnm37OSV4LP8b3_Zfs-upvSTryY9OQBuuG6h-jOBES5eYQ2ZwM0bEBIuPd4Ksi2Bn9rbec2OHVxMMyhY5iUP8c_4hCmwwl1InwASJ3xHV7g1YwJRiBGWgwgvMMax0228PsFPNzEcfPH-Bh9Pf705eNnkkAZiOGyXBNrfK6bhpYFbbRgmmvBvaLcC--kq8J9y2gmKTW5cMLIUvrCWEod8145Jyx7gva6vnNPEbalUrLx1pvChrzIa9-EVN9KZx0X2jYZerOVUG3SxnIAzvheh5sLiLOO4qyjOLOgd1vi1bSo43qyDyDqmQS2a8cP_XBeJ2Otc22M8TB3Kyl3pW10cFTMVEJYC53iDB1uhV0nkx_rP5LO0Kv5OBgrdGB05_pLoCm5CllXlWfoYNKrmRMmoePMaIaqHY3bYXX3pGsv4kLwHDwpU-LZv_l6jvaLkKLBtEvOD9Heerh0L9Bt82vdjsPLaDq_AWfqKNg priority: 102 providerName: ProQuest |
| Title | Prediction of diabetic kidney disease risk using machine learning models: A population-based cohort study of Asian adults |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37706530 https://www.proquest.com/docview/2870684899 https://www.proquest.com/docview/2864900881 https://pubmed.ncbi.nlm.nih.gov/PMC10531395 https://doaj.org/article/1acccf5330704e6dba3193c855dd4245 |
| Volume | 12 |
| WOSCitedRecordID | wos001076921800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: Directory of Open Access Journals customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: M~E dateStart: 20120101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Biological Science Database customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: M7P dateStart: 20120101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central (NC Live) customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: BENPR dateStart: 20120101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Health & Medical Collection customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: 7X7 dateStart: 20120101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: PIMPY dateStart: 20120101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (subscription) customDbUrl: eissn: 2050-084X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000748819 issn: 2050-084X databaseCode: M2P dateStart: 20120101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3da9swED-2doO9jH3PWxs02NPAq2xJltW3dLRs0AYzNsiejKyPzmxzSpIO8t9XJzshGYW-7EUP8mFk3Ul38p1-P4D3JsfrkMqmQmcs5TnXqbY5TxuF4FXGMsHjReFzOZmU06mqtqi-sCashwfuJ-4o08YYjzWQknJX2EYHo2GmFMJazNrh7kul2jpMxT1YBsPMVH8hTwaXeeTOW-8-BveEhGpbLigi9d8WXv5bJbnlds6ewOMhXiTjfpxP4Z7rnsHDnkFy9RxW1RwzLTi7ZOZJ_ye1NeRXazu3IkP6hWABOcES90vyJ1ZPOjLQRYQO5MJZHJMxudqQeaXo3CxB9tz5kkQIWnz9GG9ckgjZsXgB389Ov336nA5sCqnhslim1vhMNw0tctpowTTXgntFuRfeSVeGg5LRTFJqMuGEkYX0ubGUOua9ck5Y9hL2ulnnXgOxhVKy8dab3IaAxmvfhBjdSmcdF9o2CXxYT3BtBqhxZLz4XYcjB2qjjtqoozaSYDBr4aseYeN2sRPU1EYEYbFjRzCWejCW-i5jSeBgred6WKuLOqZ6Sx4Ongm82zwOqwxTJ7pzs2uUKbgK4VKZJfCqN4vNSJjEVDGjCZQ7BrMz1N0nXfszInlnuAUyJd78j497C4_yEIFhMUvGD2BvOb92h_DA_F22i_kI7supjG05gv2T00n1dRTXTGgv8gpbGdr96stF9eMGTichoA |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Jb9QwFH4qUxBc2CmBAkaCC1JoFjtOkBAalqqjTkdzKFI5BcdLOwIyQzIFzZ_iN-LnLHRQxa0HrrFlOcnnt_gtH8AzGWE5ZKZ8JsLYpxEVvlAR9YsMm1dJFTPqCoXHfDJJj46y6Qb86mphMK2yk4lOUKu5xDvyHReQS6l1D94svvvIGoXR1Y5Co4HFvl79tC5b_Xr03v7f51G0--Hw3Z7fsgr4kvJk6StpQlEUQRIFhWCxoIJRkwXUMKO5Tq3DIEXMg0CGTDPJE24iqYJAx8ZkWjMV23UvwSa1YA8GsDkdHUw_9bc6ViGnVsc2hYDcquodPZ4Z_dKqRSRyO6P6HEPAeWbt39mZZ9Td7o3_7UPdhOutYU2GzUm4BRu6vA1XGqrN1R1YTSsMSSEMydyQ5sp5JsmXmSr1irRxKoKZ9gRrAY7JN5dmqknLq2EfIGlQ_YoMyaJnPfPRClAEaYarJXG9enH5IZamEtfbpL4LHy_kve_BoJyX-j4QlWQZL4wyMlLW8jPCFNaZUVwrTZlQhQcvOkTksu3JjtQgX3PrmyF8cgef3MHHsyerm7xoWpGcP-0tQqufgv3D3YN5dZy34igPhZTSYGYxD6hOVCGsKI5lyphSGAv3YLsDV94KtTr_gywPnvbDVhxhjEmUen6KcxKaWbsyDT3YanDc7yTmGFOPAw_SNYSvbXV9pJyduJbnIeqKOGMP_r2vJ3B17_BgnI9Hk_2HcC2yBinm9oR0GwbL6lQ_gsvyx3JWV4_bg0vg80Ufgd9pwInD |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1bb9MwFD4aHSBeuF8CA4wEL0ihSWzHCRJCHVvFtKqqEEh7yxxfRgSkpe1A_Wv8OnycpKxo4m0PvMaW5SSfz8Xn8gE8VwmWQ-Y65DKmIUuYDKVOWFjm2LxKacqZLxQeifE4OzrKJ1vwq6uFwbTKTiZ6Qa2nCu_I-z4glzHnHvRtmxYx2Ru-nX0PkUEKI60dnUYDkUOz-unct8Wbgz33r18kyXD_47v3YcswECom0mWolY1lWUZpEpWSU8kkZzaPmOXWCJM550FJKqJIxdxwJVJhE6WjyFBrc2O4pm7dS7AtqHN6erC9uz-efFjf8DjlnDl92xQFCqe2-2ZUWfPKqUgkdTujBj1bwHkm7t-ZmmdU3_DG__zRbsL11uAmg-aE3IItU9-GKw0F5-oOrCZzDFUhPMnUkuYqulLkS6VrsyJt_IpgBj7BGoET8s2nnxrS8m24B0gmtHhNBmS2ZkML0TrQBOmH50vie_ji8gMsWSW-58niLny6kPe-B716WpsHQHSa56K02qpEO4vQSls6J0cLow3jUpcBvOzQUai2VztShnwtnM-GUCo8lAoPpcCduG7yrGlRcv60XYTZegr2FfcPpvOTohVTRSyVUhYzjkXETKpL6UQ0VRnnWmOMPICdDmhFK-wWxR-UBfBsPezEFMaeZG2mpzgnZbmzN7M4gPsNptc7oQJj7TQKINtA-8ZWN0fq6rNvhR6jDqE5f_jvfT2Fqw73xehgfPgIriXOTsWUn5jtQG85PzWP4bL6sawW8yftGSZwfNEn4DfkdJJd |
| 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=Prediction+of+diabetic+kidney+disease+risk+using+machine+learning+models%3A+A+population-based+cohort+study+of+Asian+adults&rft.jtitle=eLife&rft.au=Charumathi+Sabanayagam&rft.au=Feng+He&rft.au=Simon+Nusinovici&rft.au=Jialiang+Li&rft.date=2023-09-14&rft.pub=eLife+Sciences+Publications+Ltd&rft.eissn=2050-084X&rft.volume=12&rft_id=info:doi/10.7554%2FeLife.81878&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_1acccf5330704e6dba3193c855dd4245 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2050-084X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2050-084X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2050-084X&client=summon |