start-ver=1.4 cd-journal=joma no-vol=29 cd-vols= no-issue=5 article-no= start-page=650 end-page=661 dt-received= dt-revised= dt-accepted= dt-pub-year=2025 dt-pub=20250106 dt-online= en-article= kn-article= en-subject= kn-subject= en-title= kn-title=Development and validation of an algorithm for identifying patients undergoing dialysis from patients with advanced chronic kidney disease en-subtitle= kn-subtitle= en-abstract= kn-abstract=Background Identifying patients on dialysis among those with an estimated glomerular filtration rate (eGFR) < 15 mL/min/1.73 m2 remains challenging. To facilitate clinical research in advanced chronic kidney disease (CKD) using electronic health records, we aimed to develop algorithms to identify dialysis patients using laboratory data obtained in routine practice.
Methods We collected clinical data of patients with an eGFR < 15 mL/min/1.73 m2 from six clinical research core hospitals across Japan: four hospitals for the derivation cohort and two for the validation cohort. The candidate factors for the classification models were identified using logistic regression with stepwise backward selection. To ensure transplant patients were not included in the non-dialysis population, we excluded individuals with the disease code Z94.0.
Results We collected data from 1142 patients, with 640 (56%) currently undergoing hemodialysis or peritoneal dialysis (PD), including 426 of 763 patients in the derivation cohort and 214 of 379 patients in the validation cohort. The prescription of PD solutions perfectly identified patients undergoing dialysis. After excluding patients prescribed PD solutions, seven laboratory parameters were included in the algorithm. The areas under the receiver operation characteristic curve were 0.95 and 0.98 and the positive and negative predictive values were 90.9% and 91.4% in the derivation cohort and 96.2% and 94.6% in the validation cohort, respectively. The calibrations were almost linear.
Conclusions We identified patients on dialysis among those with an eGFR < 15 ml/min/1.73 m2. This study paves the way for database research in nephrology, especially for patients with non-dialysis-dependent advanced CKD. en-copyright= kn-copyright= en-aut-name=ImaizumiTakahiro en-aut-sei=Imaizumi en-aut-mei=Takahiro kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=1 ORCID= en-aut-name=YokotaTakashi en-aut-sei=Yokota en-aut-mei=Takashi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=2 ORCID= en-aut-name=FunakoshiKouta en-aut-sei=Funakoshi en-aut-mei=Kouta kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=3 ORCID= en-aut-name=YasudaKazushi en-aut-sei=Yasuda en-aut-mei=Kazushi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=4 ORCID= en-aut-name=HattoriAkiko en-aut-sei=Hattori en-aut-mei=Akiko kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=5 ORCID= en-aut-name=MorohashiAkemi en-aut-sei=Morohashi en-aut-mei=Akemi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=6 ORCID= en-aut-name=KusakabeTatsumi en-aut-sei=Kusakabe en-aut-mei=Tatsumi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=7 ORCID= en-aut-name=ShojimaMasumi en-aut-sei=Shojima en-aut-mei=Masumi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=8 ORCID= en-aut-name=NagamineSayoko en-aut-sei=Nagamine en-aut-mei=Sayoko kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=9 ORCID= en-aut-name=NakanoToshiaki en-aut-sei=Nakano en-aut-mei=Toshiaki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=10 ORCID= en-aut-name=HuangYong en-aut-sei=Huang en-aut-mei=Yong kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=11 ORCID= en-aut-name=MorinagaHiroshi en-aut-sei=Morinaga en-aut-mei=Hiroshi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=12 ORCID= en-aut-name=OhtaMiki en-aut-sei=Ohta en-aut-mei=Miki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=13 ORCID= en-aut-name=NagashimaSatomi en-aut-sei=Nagashima en-aut-mei=Satomi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=14 ORCID= en-aut-name=InoueRyusuke en-aut-sei=Inoue en-aut-mei=Ryusuke kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=15 ORCID= en-aut-name=NakamuraNaoki en-aut-sei=Nakamura en-aut-mei=Naoki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=16 ORCID= en-aut-name=OtaHideki en-aut-sei=Ota en-aut-mei=Hideki kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=17 ORCID= en-aut-name=MaruyamaTatsuya en-aut-sei=Maruyama en-aut-mei=Tatsuya kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=18 ORCID= en-aut-name=GobaraHideo en-aut-sei=Gobara en-aut-mei=Hideo kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=19 ORCID= en-aut-name=EndohAkira en-aut-sei=Endoh en-aut-mei=Akira kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=20 ORCID= en-aut-name=AndoMasahiko en-aut-sei=Ando en-aut-mei=Masahiko kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=21 ORCID= en-aut-name=ShiratoriYoshimune en-aut-sei=Shiratori en-aut-mei=Yoshimune kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=22 ORCID= en-aut-name=MaruyamaShoichi en-aut-sei=Maruyama en-aut-mei=Shoichi kn-aut-name= kn-aut-sei= kn-aut-mei= aut-affil-num=23 ORCID= affil-num=1 en-affil=Department of Nephrology, Nagoya University Graduate School of Medicine kn-affil= affil-num=2 en-affil=Institute of Health Science Innovation for Medical Care, Hokkaido University Hospital kn-affil= affil-num=3 en-affil=Kyusyu University Hospital kn-affil= affil-num=4 en-affil=Department of Nephrology, Nagoya University Graduate School of Medicine kn-affil= affil-num=5 en-affil=Department of Nephrology, Nagoya University Graduate School of Medicine kn-affil= affil-num=6 en-affil=Department of Advanced Medicine, Nagoya University Hospital kn-affil= affil-num=7 en-affil=Institute of Health Science Innovation for Medical Care, Hokkaido University Hospital kn-affil= affil-num=8 en-affil=Department of Medicine and Clinical Science, Graduate School of Medical Sciences, Kyushu University kn-affil= affil-num=9 en-affil=Department of Medicine and Clinical Science, Graduate School of Medical Sciences, Kyushu University kn-affil= affil-num=10 en-affil=Department of Medicine and Clinical Science, Graduate School of Medical Sciences, Kyushu University kn-affil= affil-num=11 en-affil=Division of Medical Informatics, Okayama University Hospital kn-affil= affil-num=12 en-affil=Department of Comprehensive Therapy for Chronic Kidney Disease, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University kn-affil= affil-num=13 en-affil=Clinical Research Promotion Center, The University of Tokyo Hospital kn-affil= affil-num=14 en-affil=Department of Healthcare Information Management, The University of Tokyo Hospital kn-affil= affil-num=15 en-affil=Medical Information Technology Center, Tohoku University Hospital kn-affil= affil-num=16 en-affil=Medical Information Technology Center, Tohoku University Hospital kn-affil= affil-num=17 en-affil=Medical Information Technology Center, Tohoku University Hospital kn-affil= affil-num=18 en-affil=Clinical Research Promotion Center, The University of Tokyo Hospital kn-affil= affil-num=19 en-affil=Division of Medical Informatics, Okayama University Hospital kn-affil= affil-num=20 en-affil=Department of Medical Informatics, Hokkaido University Hospital kn-affil= affil-num=21 en-affil=Department of Nephrology, Nagoya University Graduate School of Medicine kn-affil= affil-num=22 en-affil=Medical IT Center, Nagoya University Hospital kn-affil= affil-num=23 en-affil=Department of Nephrology, Nagoya University Graduate School of Medicine kn-affil= en-keyword=Chronic kidney disease kn-keyword=Chronic kidney disease en-keyword=Algorithm kn-keyword=Algorithm en-keyword=Classification kn-keyword=Classification en-keyword=Dialysis kn-keyword=Dialysis END