Comparison Between Statistical Model and Machine Learning Methods for Predicting the Risk of Renal Function Decline Using Routine Clinical Data in Health Screening

Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the ri...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Risk management and healthcare policy Ročník 15; s. 817 - 826
Hlavní autori: Cao, Xia, Lin, Yanhui, Yang, Binfang, Li, Ying, Zhou, Jiansong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: England Dove Medical Press Limited 01.01.2022
Dove
Dove Medical Press
Predmet:
ISSN:1179-1594, 1179-1594
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data. This retrospective cohort study includes datasets from 2166 subjects, aged 35-74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered - random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable. A total of 2166 participants (mean age 49.2±11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant. Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.
AbstractList Purpose: Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data. Patients and Methods: This retrospective cohort study includes datasets from 2166 subjects, aged 35-74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered--random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree--and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable. Results: A total of 2166 participants (mean age 49.2[+ or -]11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant. Conclusion: Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors. Keywords: deep learning, chronic kidney disease, algorithm, health examination
Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data.PurposeUsing machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data.This retrospective cohort study includes datasets from 2166 subjects, aged 35-74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered - random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable.Patients and MethodsThis retrospective cohort study includes datasets from 2166 subjects, aged 35-74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered - random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable.A total of 2166 participants (mean age 49.2±11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant.ResultsA total of 2166 participants (mean age 49.2±11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant.Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.ConclusionOur results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.
Xia Cao,1– 3 Yanhui Lin,1– 3 Binfang Yang,1– 3 Ying Li,1– 3 Jiansong Zhou4 1Health Management Center, The Third Xiangya Hospital, Central South University, Changsha, Hunan, People’s Republic of China; 2Health Management Research Center, Central South University, Changsha, Hunan, People’s Republic of China; 3Hunan Chronic Disease Health Management Medical Research Center, Central South University, Changsha, Hunan, People’s Republic of China; 4National Clinical Research Center for Mental Disorders, and Department of Psychiatry, The Second Xiangya Hospital, Central South University, Changsha, Hunan, People’s Republic of ChinaCorrespondence: Jiansong Zhou, National Clinical Research Center for Mental Disorders, and Department of Psychiatry, The Second Xiangya Hospital, Central South University, Changsha, 410011, People’s Republic of China, Tel/Fax +86 073188618573, Email jasonzhou75@163.comPurpose: Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data.Patients and Methods: This retrospective cohort study includes datasets from 2166 subjects, aged 35– 74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered – random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable.Results: A total of 2166 participants (mean age 49.2± 11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant.Conclusion: Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.Keywords: deep learning, chronic kidney disease, algorithm, health examination
Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors. Therefore, we evaluate the performance of machine learning (ML) algorithms and to compare them with logistic regression for predicting the risk of renal function decline (RFD) using routine clinical data. This retrospective cohort study includes datasets from 2166 subjects, aged 35-74 years old, provided by an adult health screening follow-up program between 2010 and 2020. Seven different ML models were considered - random forest, gradient boosting, multilayer perceptron, support vector machine, K-nearest neighbors, adaptive boosting, and decision tree - and were compared with standard logistic regression. There were 24 independent variables, and the baseline estimate glomerular filtration rate (eGFR) was used as the predictive variable. A total of 2166 participants (mean age 49.2±11.2 years old, 63.3% males) were enrolled and randomly divided into a training set (n=1732) and a test set (n=434). The area under receiver operating characteristic curve (AUROC) for detecting RFD corresponding to the different models were above 0.85 during the training phase. The gradient boosting algorithms exhibited the best average prediction accuracy (AUROC: 0.914) among all algorithms validated in this study. Based on AUROC, the ML algorithms improved the RFD prediction performance, compared to logistic regression model (AUROC:0.882), except the K-nearest neighbors and decision tree algorithms (AUROC:0.854 and 0.824, respectively). However, the improvement differences with logistic regression were small (less than 4%) and nonsignificant. Our results indicate that the proposed health screening dataset-based RFD prediction model using ML algorithms is readily applicable, produces validated results. But logistic regression yields as good performance as ML models to predict the risk of RFD with simple clinical predictors.
Audience Academic
Author Cao, Xia
Lin, Yanhui
Yang, Binfang
Li, Ying
Zhou, Jiansong
Author_xml – sequence: 1
  givenname: Xia
  surname: Cao
  fullname: Cao, Xia
– sequence: 2
  givenname: Yanhui
  surname: Lin
  fullname: Lin, Yanhui
– sequence: 3
  givenname: Binfang
  surname: Yang
  fullname: Yang, Binfang
– sequence: 4
  givenname: Ying
  surname: Li
  fullname: Li, Ying
– sequence: 5
  givenname: Jiansong
  surname: Zhou
  fullname: Zhou, Jiansong
BackLink https://www.ncbi.nlm.nih.gov/pubmed/35502445$$D View this record in MEDLINE/PubMed
BookMark eNptkl1v0zAUhiM0xMbYHdfIEhLighbHcRL7ZtLoGJ3Uiqll15brHLceqV1sB8Tv4Y_itGVq0RIpH8fPeY-Pz_syO7HOQpa9zvGQ5LT-OJuO74bzglasrJ5lZ3le80Fecnpy8H2aXYTwgNNFOatZ_SI7LcoSE0rLs-zPyK030pvgLPoE8ReARfMoownRKNmiqWugRdI2aCrVylhAE5DeGrtEU4gr1wSknUd3HhqjYh-OK0AzE74jp9EMbNK46WxaSgWuQbW9xH3owZnrYv83SrFtrWsZJTIWjUG2cYXmyqfdJPJV9lzLNsDF_n2e3d98_jYaDyZfv9yOriYDVVIWB4QRzbQuFk1DcL3IeYEJaM4oUTXWlBdcNZrkuiqbvFIyPQmXKidYE8V5SYrz7Han2zj5IDberKX_LZw0YhtwfimkT8fSgiCpEOMVqxSvKasK3kilJeiqYguicZG0Lndam26xhkaBjV62R6LHK9asxNL9FByXFa5xEni_F_DuRwchirUJCtpWWnBdEKQqOSF1nbOEvt2hS5m2Zqx2SVH1uLhKSmnOlPbdDZ-g0t3A2qhkK21S_Cjh3UHCajuU4NquH2U4Bt8c9vrY5D-XJeDDDlDeheBBPyI5Fr2PRe9jsfdxwsl_uDK9JV1_UqZ9Oukvd471Vg
CitedBy_id crossref_primary_10_1371_journal_pone_0317558
crossref_primary_10_1016_j_zemedi_2023_08_001
crossref_primary_10_1007_s42452_025_06980_9
crossref_primary_10_3390_s25030916
Cites_doi 10.1038/s41419-017-0003-x
10.1007/s11255-017-1732-6
10.1186/1475-2891-12-12
10.2215/CJN.07900812
10.1210/jc.2011-2658
10.1016/S0140-6736(16)32064-5
10.1038/ctg.2013.19
10.1186/s12967-019-1860-0
10.3390/jcm9020403
10.1016/j.amjmed.2011.09.009
10.1097/CCM.0000000000003123
10.3390/ijerph17144973
10.1186/s12882-016-0335-2
10.1016/j.jclinepi.2020.03.002
10.1016/j.wneu.2017.09.149
10.1016/S0140-6736(12)60033-6
10.1038/s41598-021-95019-1
10.1053/j.ajkd.2017.09.013
10.1136/bmjopen-2015-008188
10.1371/journal.pone.0174944
10.2307/2531595
10.1136/bmjgh-2019-001644
10.1016/S0140-6736(19)32977-0
10.7326/0003-4819-150-9-200905050-00006
10.1056/NEJMp1606181
10.1093/eurheartj/ehw302
10.1016/j.pec.2012.11.001
10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
10.1053/j.ajkd.2019.05.032
10.1161/JAHA.113.000157
10.1001/jama.2019.17379
10.1186/s12882-017-0758-4
10.1016/S0140-6736(17)30788-2
10.2196/15510
10.1371/journal.pmed.1001809
10.1093/ndt/gfl227
10.1186/s12882-015-0009-5
10.1136/bmjopen-2019-035308
10.1186/s12882-017-0781-5
10.1016/j.artmed.2010.05.002
ContentType Journal Article
Copyright 2022 Cao et al.
COPYRIGHT 2022 Dove Medical Press Limited
2022 Cao et al. 2022 Cao et al.
Copyright_xml – notice: 2022 Cao et al.
– notice: COPYRIGHT 2022 Dove Medical Press Limited
– notice: 2022 Cao et al. 2022 Cao et al.
DBID AAYXX
CITATION
NPM
7X8
5PM
DOA
DOI 10.2147/RMHP.S346856
DatabaseName CrossRef
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic


PubMed
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Open Access Full Text
  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: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Business
DocumentTitleAlternate Cao et al
EISSN 1179-1594
EndPage 826
ExternalDocumentID oai_doaj_org_article_28ff89686c9748639dacfaef668b2f03
PMC9056070
A703445442
35502445
10_2147_RMHP_S346856
Genre Journal Article
GeographicLocations China
GeographicLocations_xml – name: China
GroupedDBID ---
0YH
29P
2WC
44B
53G
5VS
7RV
8C1
8FI
8FJ
8G5
AAYXX
ABUWG
ADBBV
ADRAZ
AEUYN
AFFHD
AFKRA
ALMA_UNASSIGNED_HOLDINGS
AOIJS
AQTUD
AQUVI
AZQEC
BAWUL
BCNDV
BENPR
BKEYQ
BPHCQ
BVXVI
CCPQU
CITATION
DIK
DWQXO
E3Z
EBD
EBS
EJD
FYUFA
GNUQQ
GROUPED_DOAJ
GUQSH
GX1
HYE
IAO
IHR
IHW
IPNFZ
ITC
KQ8
M0T
M2O
M48
M~E
NAPCQ
OK1
P2P
PGMZT
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQQKQ
PROAC
RIG
RPM
TDBHL
UKHRP
VDV
NPM
ALIPV
7X8
5PM
ID FETCH-LOGICAL-c548t-282f8ff3bdd207b19302ef9842c70f4939cdf21f65d16ca5d129ac120f2c99523
IEDL.DBID DOA
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000797147300006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1179-1594
IngestDate Fri Oct 03 12:53:31 EDT 2025
Tue Nov 04 01:59:05 EST 2025
Sun Oct 12 02:49:18 EDT 2025
Tue Nov 11 10:48:54 EST 2025
Tue Nov 04 18:12:31 EST 2025
Tue May 06 02:10:43 EDT 2025
Sun Oct 05 09:13:47 EDT 2025
Sat Nov 29 03:07:42 EST 2025
Tue Nov 18 22:31:00 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords deep learning
chronic kidney disease
health examination
algorithm
Language English
License http://creativecommons.org/licenses/by-nc/3.0
2022 Cao et al.
This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and incorporate the Creative Commons Attribution – Non Commercial (unported, v3.0) License (http://creativecommons.org/licenses/by-nc/3.0/). By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms (https://www.dovepress.com/terms.php).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c548t-282f8ff3bdd207b19302ef9842c70f4939cdf21f65d16ca5d129ac120f2c99523
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://doaj.org/article/28ff89686c9748639dacfaef668b2f03
PMID 35502445
PQID 2659227718
PQPubID 23479
PageCount 10
ParticipantIDs doaj_primary_oai_doaj_org_article_28ff89686c9748639dacfaef668b2f03
pubmedcentral_primary_oai_pubmedcentral_nih_gov_9056070
proquest_miscellaneous_2659227718
gale_infotracmisc_A703445442
gale_infotracacademiconefile_A703445442
gale_healthsolutions_A703445442
pubmed_primary_35502445
crossref_primary_10_2147_RMHP_S346856
crossref_citationtrail_10_2147_RMHP_S346856
PublicationCentury 2000
PublicationDate 2022-01-01
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-01-01
  day: 01
PublicationDecade 2020
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Risk management and healthcare policy
PublicationTitleAlternate Risk Manag Healthc Policy
PublicationYear 2022
Publisher Dove Medical Press Limited
Dove
Dove Medical Press
Publisher_xml – name: Dove Medical Press Limited
– name: Dove
– name: Dove Medical Press
References Cao (ref15) 2018; 50
Mocroft (ref7) 2015; 12
Jerez (ref22) 2010; 50
Xiao (ref31) 2019; 17
DeLong (ref24) 1988; 44
ref1
O’Seaghdha (ref6) 2012; 125
Madero (ref17) 2013; 8
Yu (ref33) 2020; 9
Waljee (ref26) 2014; 5
Nelson (ref4) 2019; 322
Nusinovici (ref10) 2020; 122
Yang (ref3) 2020; 76
Levey (ref18) 2009; 150
Krishnan (ref19) 2014; 3
Umesawa (ref36) 2018; 71
Zhang (ref2) 2012; 379
Qin (ref21) 2013; 12
Goldstein (ref11) 2017; 38
Webster (ref20) 2017; 389
Dienemann (ref38) 2016; 17
Carrillo-Larco (ref5) 2017; 18
Song (ref30) 2020; 8
Senders (ref12) 2018; 109
Obermeyer (ref8) 2016; 375
Shih (ref29) 2020; 17
Cao (ref14) 2015; 16
Sederholm Lawesson (ref39) 2015; 5
Berglund (ref13) 2013; 91
Mahmood (ref32) 2017; 18
Bradshaw (ref34) 2019; 4
Lee (ref27) 2021; 11
Cheng (ref16) 2012; 97
Weng (ref9) 2017; 12
Koyner (ref28) 2018; 46
Youden (ref23) 1950; 3
Berg (ref40) 2006; 21
Yang (ref35) 2020; 10
Levin (ref37) 2017; 390
Chen (ref25) 2018; 9
References_xml – volume: 9
  start-page: 3
  year: 2018
  ident: ref25
  publication-title: Cell Death Dis
  doi: 10.1038/s41419-017-0003-x
– volume: 50
  start-page: 517
  year: 2018
  ident: ref15
  publication-title: Int Urol Nephrol
  doi: 10.1007/s11255-017-1732-6
– volume: 12
  start-page: 12
  year: 2013
  ident: ref21
  publication-title: Nutr J
  doi: 10.1186/1475-2891-12-12
– volume: 8
  start-page: 424
  year: 2013
  ident: ref17
  publication-title: Clin J Am Soc Nephrol
  doi: 10.2215/CJN.07900812
– volume: 97
  start-page: 1268
  year: 2012
  ident: ref16
  publication-title: J Clin Endocr Metab
  doi: 10.1210/jc.2011-2658
– volume: 389
  start-page: 1238
  year: 2017
  ident: ref20
  publication-title: Lancet
  doi: 10.1016/S0140-6736(16)32064-5
– volume: 5
  start-page: e44
  year: 2014
  ident: ref26
  publication-title: Clin Transl Gastroenterol
  doi: 10.1038/ctg.2013.19
– volume: 17
  start-page: 119
  year: 2019
  ident: ref31
  publication-title: J Transl Med
  doi: 10.1186/s12967-019-1860-0
– volume: 9
  start-page: 403
  year: 2020
  ident: ref33
  publication-title: J Clin Med
  doi: 10.3390/jcm9020403
– volume: 125
  start-page: 270
  year: 2012
  ident: ref6
  publication-title: Am J Med
  doi: 10.1016/j.amjmed.2011.09.009
– volume: 46
  start-page: 1070
  year: 2018
  ident: ref28
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0000000000003123
– volume: 17
  start-page: 4973
  year: 2020
  ident: ref29
  publication-title: Int J Environ Res Public Health
  doi: 10.3390/ijerph17144973
– volume: 17
  start-page: 121
  year: 2016
  ident: ref38
  publication-title: BMC Nephrol
  doi: 10.1186/s12882-016-0335-2
– volume: 122
  start-page: 56
  year: 2020
  ident: ref10
  publication-title: J Clin Epidemiol
  doi: 10.1016/j.jclinepi.2020.03.002
– volume: 109
  start-page: 476
  year: 2018
  ident: ref12
  publication-title: World Neurosurg
  doi: 10.1016/j.wneu.2017.09.149
– volume: 379
  start-page: 815
  year: 2012
  ident: ref2
  publication-title: Lancet
  doi: 10.1016/S0140-6736(12)60033-6
– volume: 11
  start-page: 15704
  year: 2021
  ident: ref27
  publication-title: Sci Rep
  doi: 10.1038/s41598-021-95019-1
– volume: 71
  start-page: 842
  year: 2018
  ident: ref36
  publication-title: Am J Kidney Dis
  doi: 10.1053/j.ajkd.2017.09.013
– volume: 5
  start-page: e008188
  year: 2015
  ident: ref39
  publication-title: BMJ Open
  doi: 10.1136/bmjopen-2015-008188
– volume: 12
  start-page: e0174944
  year: 2017
  ident: ref9
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0174944
– volume: 44
  start-page: 837
  year: 1988
  ident: ref24
  publication-title: Biometrics
  doi: 10.2307/2531595
– volume: 4
  start-page: e001644
  year: 2019
  ident: ref34
  publication-title: BMJ Glob Health
  doi: 10.1136/bmjgh-2019-001644
– ident: ref1
  doi: 10.1016/S0140-6736(19)32977-0
– volume: 150
  start-page: 604
  year: 2009
  ident: ref18
  publication-title: Ann Intern Med
  doi: 10.7326/0003-4819-150-9-200905050-00006
– volume: 375
  start-page: 1216
  year: 2016
  ident: ref8
  publication-title: N Engl J Med
  doi: 10.1056/NEJMp1606181
– volume: 38
  start-page: 1805
  year: 2017
  ident: ref11
  publication-title: Eur Heart J
  doi: 10.1093/eurheartj/ehw302
– volume: 91
  start-page: 105
  year: 2013
  ident: ref13
  publication-title: Patient Educ Couns
  doi: 10.1016/j.pec.2012.11.001
– volume: 3
  start-page: 32
  year: 1950
  ident: ref23
  publication-title: Cancer
  doi: 10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
– volume: 76
  start-page: 258
  year: 2020
  ident: ref3
  publication-title: Am J Kidney Dis
  doi: 10.1053/j.ajkd.2019.05.032
– volume: 3
  year: 2014
  ident: ref19
  publication-title: J Am Heart Assoc
  doi: 10.1161/JAHA.113.000157
– volume: 322
  start-page: 2104
  year: 2019
  ident: ref4
  publication-title: JAMA
  doi: 10.1001/jama.2019.17379
– volume: 18
  start-page: 343
  year: 2017
  ident: ref5
  publication-title: BMC Nephrol
  doi: 10.1186/s12882-017-0758-4
– volume: 390
  start-page: 1888
  year: 2017
  ident: ref37
  publication-title: Lancet
  doi: 10.1016/S0140-6736(17)30788-2
– volume: 8
  start-page: e15510
  year: 2020
  ident: ref30
  publication-title: JMIR Med Inform
  doi: 10.2196/15510
– volume: 12
  start-page: e1001809
  year: 2015
  ident: ref7
  publication-title: PLoS Med
  doi: 10.1371/journal.pmed.1001809
– volume: 21
  start-page: 2577
  year: 2006
  ident: ref40
  publication-title: Nephrol Dial Transplant
  doi: 10.1093/ndt/gfl227
– volume: 16
  start-page: 16
  year: 2015
  ident: ref14
  publication-title: BMC Nephrol
  doi: 10.1186/s12882-015-0009-5
– volume: 10
  start-page: e035308
  year: 2020
  ident: ref35
  publication-title: BMJ Open
  doi: 10.1136/bmjopen-2019-035308
– volume: 18
  start-page: 372
  year: 2017
  ident: ref32
  publication-title: BMC Nephrol
  doi: 10.1186/s12882-017-0781-5
– volume: 50
  start-page: 105
  year: 2010
  ident: ref22
  publication-title: Artif Intell Med
  doi: 10.1016/j.artmed.2010.05.002
SSID ssj0000498787
Score 2.2237084
Snippet Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk factors....
Purpose: Using machine learning method to predict and judge unknown data offers opportunity to improve accuracy by exploring complex interactions between risk...
Xia Cao,1– 3 Yanhui Lin,1– 3 Binfang Yang,1– 3 Ying Li,1– 3 Jiansong Zhou4 1Health Management Center, The Third Xiangya Hospital, Central South University,...
SourceID doaj
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 817
SubjectTerms algorithm
Algorithms
chronic kidney disease
Chronic kidney failure
deep learning
Evidence-based medicine
health examination
Machine learning
Medical screening
Methods
Original Research
Type 2 diabetes
Title Comparison Between Statistical Model and Machine Learning Methods for Predicting the Risk of Renal Function Decline Using Routine Clinical Data in Health Screening
URI https://www.ncbi.nlm.nih.gov/pubmed/35502445
https://www.proquest.com/docview/2659227718
https://pubmed.ncbi.nlm.nih.gov/PMC9056070
https://doaj.org/article/28ff89686c9748639dacfaef668b2f03
Volume 15
WOSCitedRecordID wos000797147300006&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: DOAJ Open Access Full Text
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: DOA
  dateStart: 20080101
  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: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: M~E
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Healthcare Administration Database
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: M0T
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthmanagement
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Nursing & Allied Health Database
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: 7RV
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/nahs
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: BENPR
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: PIMPY
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Public Health Database
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: 8C1
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/publichealth
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Research Library
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: M2O
  dateStart: 20080101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/pqrl
  providerName: ProQuest
– providerCode: PRVAWR
  databaseName: Taylor & Francis Open Access
  customDbUrl:
  eissn: 1179-1594
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000498787
  issn: 1179-1594
  databaseCode: 0YH
  dateStart: 20081201
  isFulltext: true
  titleUrlDefault: https://www.tandfonline.com
  providerName: Taylor & Francis
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwELVgQWgviO8NLGWQQBxQ2MR1E_u47W61HFqi7oLKKXIdGwpVitouf4g_yoydVo0Q4sLFUuqJGmcmnudk_B5jr9IqM0IZHRs307EwpAaYk4ZGKm0-SyuRdJ0Xm8jHYzmdqmJP6otqwgI9cLhxJ1w6J1UmM4PIV2I-rbRx2roskzPuAs8nop69xdS3gHtlLhtlFRVjzhah6p1keU4mo4vi3WVXZJJ0q_fykaft_3Ny3stO7crJvVQ0vMfuNhgSTsO132c3bP2A3dmWsD9kvwY7cUHohzosIFDpOZnxRNI_W4CuKxj5UkoLDcvqFxh5Qek1IJSFYkUfcagsGhAlwmS-_g5LBxNLfz7EfEg-hTNLmyst-NoDoAIjOmroRhdwpjca5jWE7U5waajOBy0fsY_D86vBRdyIMcQGFzWbGJdmDl3RnVUVT9CLqptw65QU3OSJE6qrTOV46rJelWZGY8uVNilPHDdK4XL3MTuol7U9YmB6WuiZSByCL4EpVHGTGcSFhphhXJJG7O3WJaVpmMpJMGNR4oqFHFiSA8vGgRF7vbP-ERg6_mLXJ-_ubIhX2_-A0VY20Vb-K9oi9oJiowybVHezQ3maE3ViTwgesTfeguYHvGijm20OOHRi2mpZHrcs8bk2re6X2_grqYuK4Wq7vF6XnD6F8xxRRcSehHjcjQrhI6Iu0YtY3orU1rDbPfX8q6cVV-gOTABP_8d9esYOOe0T8e-qjtnBZnVtn7Pb5ieG-qrDbuaTT9ROJbZykHbYrf75uJh0_FOM7Si5opZ_wJ7i_aj4_BvPVEr2
linkProvider Directory of Open Access Journals
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=Comparison+Between+Statistical+Model+and+Machine+Learning+Methods+for+Predicting+the+Risk+of+Renal+Function+Decline+Using+Routine+Clinical+Data+in+Health+Screening&rft.jtitle=Risk+management+and+healthcare+policy&rft.au=Cao+X&rft.au=Lin+Y&rft.au=Yang+B&rft.au=Li+Y&rft.date=2022-01-01&rft.pub=Dove+Medical+Press&rft.issn=1179-1594&rft.eissn=1179-1594&rft.volume=15&rft.spage=817&rft.epage=826&rft_id=info:doi/10.2147%2FRMHP.S346856&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_28ff89686c9748639dacfaef668b2f03
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1179-1594&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1179-1594&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1179-1594&client=summon