A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis

Paola Rucci, Marcora Mandreoli, Dino Gibertoni, Alessandro Zuccalà, Maria Pia Fantini, Jacopo Lenzi, Antonio Santoro, Roberto Scarpioni, Sara De Amicis, Carlo Buzio, Salvatore David, Sonia Pasquali, Mattia Corradini, Gianni Cappelli, Fabio Olmeda, Alberto Baraldi, Francesco Caruso, Sergio Stefoni, Claudio Orsi, Cecilia CannarilePierpaolo Di Nicolò, Alda Storari, Giorgia Russo, Andrea Buscaroli, Mattia Monti, Giovanni Mosconi, Stefania Cristino, Carlo Feletti, Leopoldo Baldrati, Angelo Rigotti, Marta Flachi

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

BackgroundRegistry-based studies have identified risk factors for chronic kidney disease (CKD) and for progression to end-stage renal disease. However, usually, these studies do not incorporate sequential measurements of kidney function and provide little information on the prognosis of individual patients. The aim of this study is to identify which combinations of demographic and clinical characteristics are useful to discriminate patients with a differential annual decline in glomerular filtration rate (GFR).MethodsThis observational retrospective study includes patients enlisted in the registry of the Prevention of Progressive Renal Insufficiency Project of Emilia-Romagna region (Italy) from July 2004 to June 2010, with at least four serum creatinine measurements. Classification tree analysis (CTA) was used to identify subgroups of patients with a different annual GFR decline using demographic and laboratory data collected at study entry.ResultsThe CTA procedure generated seven mutually exclusive groups. Among patients with proteinuria, those with a baseline estimated GFR (eGFR) of >33 mL/min/1.73 m2 exhibited the fastest illness progression in the study population (-3.655 mL/min/1.73 m2), followed by patients with a baseline eGFR of 2 and a baseline serum phosphorus of >4.3 mg/dL (-2.833 mL/min/1.73 m 2). Among patients without proteinuria, those aged 67 years, females had on average a stable eGFR over time, with a large variability.ConclusionsIt is possible to rely on a few variables typically accessible in routine clinical practice to stratify patients with a different CKD progression rate. Stratification can be used to guide decisions about the follow-up schedule, treatments to slow progression of kidney disease, prevent its complications and to begin planning for dialysis and transplantation.

Original languageEnglish
Pages (from-to)603-610
Number of pages8
JournalNephrology Dialysis Transplantation
Volume29
Issue number3
DOIs
Publication statusPublished - 2014

Fingerprint

Chronic Renal Insufficiency
Disease Progression
Glomerular Filtration Rate
Proteinuria
Demography
Kidney Diseases
Serum
Phosphorus
Italy
Chronic Kidney Failure
Observational Studies
Renal Insufficiency
Registries
Dialysis
Creatinine
Appointments and Schedules
Retrospective Studies
Transplantation
Kidney
Population

Keywords

  • CKD progression
  • Decision tree
  • Prediction models

ASJC Scopus subject areas

  • Nephrology
  • Transplantation
  • Medicine(all)

Cite this

Rucci, P., Mandreoli, M., Gibertoni, D., Zuccalà, A., Fantini, M. P., Lenzi, J., ... Flachi, M. (2014). A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis. Nephrology Dialysis Transplantation, 29(3), 603-610. https://doi.org/10.1093/ndt/gft444

A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis. / Rucci, Paola; Mandreoli, Marcora; Gibertoni, Dino; Zuccalà, Alessandro; Fantini, Maria Pia; Lenzi, Jacopo; Santoro, Antonio; Scarpioni, Roberto; De Amicis, Sara; Buzio, Carlo; David, Salvatore; Pasquali, Sonia; Corradini, Mattia; Cappelli, Gianni; Olmeda, Fabio; Baraldi, Alberto; Caruso, Francesco; Stefoni, Sergio; Orsi, Claudio; Cannarile, Cecilia; Di Nicolò, Pierpaolo; Storari, Alda; Russo, Giorgia; Buscaroli, Andrea; Monti, Mattia; Mosconi, Giovanni; Cristino, Stefania; Feletti, Carlo; Baldrati, Leopoldo; Rigotti, Angelo; Flachi, Marta.

In: Nephrology Dialysis Transplantation, Vol. 29, No. 3, 2014, p. 603-610.

Research output: Contribution to journalArticle

Rucci, P, Mandreoli, M, Gibertoni, D, Zuccalà, A, Fantini, MP, Lenzi, J, Santoro, A, Scarpioni, R, De Amicis, S, Buzio, C, David, S, Pasquali, S, Corradini, M, Cappelli, G, Olmeda, F, Baraldi, A, Caruso, F, Stefoni, S, Orsi, C, Cannarile, C, Di Nicolò, P, Storari, A, Russo, G, Buscaroli, A, Monti, M, Mosconi, G, Cristino, S, Feletti, C, Baldrati, L, Rigotti, A & Flachi, M 2014, 'A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis', Nephrology Dialysis Transplantation, vol. 29, no. 3, pp. 603-610. https://doi.org/10.1093/ndt/gft444
Rucci, Paola ; Mandreoli, Marcora ; Gibertoni, Dino ; Zuccalà, Alessandro ; Fantini, Maria Pia ; Lenzi, Jacopo ; Santoro, Antonio ; Scarpioni, Roberto ; De Amicis, Sara ; Buzio, Carlo ; David, Salvatore ; Pasquali, Sonia ; Corradini, Mattia ; Cappelli, Gianni ; Olmeda, Fabio ; Baraldi, Alberto ; Caruso, Francesco ; Stefoni, Sergio ; Orsi, Claudio ; Cannarile, Cecilia ; Di Nicolò, Pierpaolo ; Storari, Alda ; Russo, Giorgia ; Buscaroli, Andrea ; Monti, Mattia ; Mosconi, Giovanni ; Cristino, Stefania ; Feletti, Carlo ; Baldrati, Leopoldo ; Rigotti, Angelo ; Flachi, Marta. / A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis. In: Nephrology Dialysis Transplantation. 2014 ; Vol. 29, No. 3. pp. 603-610.
@article{02d8e9d9d636408984cb6a624c9eaa69,
title = "A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis",
abstract = "BackgroundRegistry-based studies have identified risk factors for chronic kidney disease (CKD) and for progression to end-stage renal disease. However, usually, these studies do not incorporate sequential measurements of kidney function and provide little information on the prognosis of individual patients. The aim of this study is to identify which combinations of demographic and clinical characteristics are useful to discriminate patients with a differential annual decline in glomerular filtration rate (GFR).MethodsThis observational retrospective study includes patients enlisted in the registry of the Prevention of Progressive Renal Insufficiency Project of Emilia-Romagna region (Italy) from July 2004 to June 2010, with at least four serum creatinine measurements. Classification tree analysis (CTA) was used to identify subgroups of patients with a different annual GFR decline using demographic and laboratory data collected at study entry.ResultsThe CTA procedure generated seven mutually exclusive groups. Among patients with proteinuria, those with a baseline estimated GFR (eGFR) of >33 mL/min/1.73 m2 exhibited the fastest illness progression in the study population (-3.655 mL/min/1.73 m2), followed by patients with a baseline eGFR of 2 and a baseline serum phosphorus of >4.3 mg/dL (-2.833 mL/min/1.73 m 2). Among patients without proteinuria, those aged 67 years, females had on average a stable eGFR over time, with a large variability.ConclusionsIt is possible to rely on a few variables typically accessible in routine clinical practice to stratify patients with a different CKD progression rate. Stratification can be used to guide decisions about the follow-up schedule, treatments to slow progression of kidney disease, prevent its complications and to begin planning for dialysis and transplantation.",
keywords = "CKD progression, Decision tree, Prediction models",
author = "Paola Rucci and Marcora Mandreoli and Dino Gibertoni and Alessandro Zuccal{\`a} and Fantini, {Maria Pia} and Jacopo Lenzi and Antonio Santoro and Roberto Scarpioni and {De Amicis}, Sara and Carlo Buzio and Salvatore David and Sonia Pasquali and Mattia Corradini and Gianni Cappelli and Fabio Olmeda and Alberto Baraldi and Francesco Caruso and Sergio Stefoni and Claudio Orsi and Cecilia Cannarile and {Di Nicol{\`o}}, Pierpaolo and Alda Storari and Giorgia Russo and Andrea Buscaroli and Mattia Monti and Giovanni Mosconi and Stefania Cristino and Carlo Feletti and Leopoldo Baldrati and Angelo Rigotti and Marta Flachi",
year = "2014",
doi = "10.1093/ndt/gft444",
language = "English",
volume = "29",
pages = "603--610",
journal = "Nephrology Dialysis Transplantation",
issn = "0931-0509",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - A clinical stratification tool for chronic kidney disease progression rate based on classification tree analysis

AU - Rucci, Paola

AU - Mandreoli, Marcora

AU - Gibertoni, Dino

AU - Zuccalà, Alessandro

AU - Fantini, Maria Pia

AU - Lenzi, Jacopo

AU - Santoro, Antonio

AU - Scarpioni, Roberto

AU - De Amicis, Sara

AU - Buzio, Carlo

AU - David, Salvatore

AU - Pasquali, Sonia

AU - Corradini, Mattia

AU - Cappelli, Gianni

AU - Olmeda, Fabio

AU - Baraldi, Alberto

AU - Caruso, Francesco

AU - Stefoni, Sergio

AU - Orsi, Claudio

AU - Cannarile, Cecilia

AU - Di Nicolò, Pierpaolo

AU - Storari, Alda

AU - Russo, Giorgia

AU - Buscaroli, Andrea

AU - Monti, Mattia

AU - Mosconi, Giovanni

AU - Cristino, Stefania

AU - Feletti, Carlo

AU - Baldrati, Leopoldo

AU - Rigotti, Angelo

AU - Flachi, Marta

PY - 2014

Y1 - 2014

N2 - BackgroundRegistry-based studies have identified risk factors for chronic kidney disease (CKD) and for progression to end-stage renal disease. However, usually, these studies do not incorporate sequential measurements of kidney function and provide little information on the prognosis of individual patients. The aim of this study is to identify which combinations of demographic and clinical characteristics are useful to discriminate patients with a differential annual decline in glomerular filtration rate (GFR).MethodsThis observational retrospective study includes patients enlisted in the registry of the Prevention of Progressive Renal Insufficiency Project of Emilia-Romagna region (Italy) from July 2004 to June 2010, with at least four serum creatinine measurements. Classification tree analysis (CTA) was used to identify subgroups of patients with a different annual GFR decline using demographic and laboratory data collected at study entry.ResultsThe CTA procedure generated seven mutually exclusive groups. Among patients with proteinuria, those with a baseline estimated GFR (eGFR) of >33 mL/min/1.73 m2 exhibited the fastest illness progression in the study population (-3.655 mL/min/1.73 m2), followed by patients with a baseline eGFR of 2 and a baseline serum phosphorus of >4.3 mg/dL (-2.833 mL/min/1.73 m 2). Among patients without proteinuria, those aged 67 years, females had on average a stable eGFR over time, with a large variability.ConclusionsIt is possible to rely on a few variables typically accessible in routine clinical practice to stratify patients with a different CKD progression rate. Stratification can be used to guide decisions about the follow-up schedule, treatments to slow progression of kidney disease, prevent its complications and to begin planning for dialysis and transplantation.

AB - BackgroundRegistry-based studies have identified risk factors for chronic kidney disease (CKD) and for progression to end-stage renal disease. However, usually, these studies do not incorporate sequential measurements of kidney function and provide little information on the prognosis of individual patients. The aim of this study is to identify which combinations of demographic and clinical characteristics are useful to discriminate patients with a differential annual decline in glomerular filtration rate (GFR).MethodsThis observational retrospective study includes patients enlisted in the registry of the Prevention of Progressive Renal Insufficiency Project of Emilia-Romagna region (Italy) from July 2004 to June 2010, with at least four serum creatinine measurements. Classification tree analysis (CTA) was used to identify subgroups of patients with a different annual GFR decline using demographic and laboratory data collected at study entry.ResultsThe CTA procedure generated seven mutually exclusive groups. Among patients with proteinuria, those with a baseline estimated GFR (eGFR) of >33 mL/min/1.73 m2 exhibited the fastest illness progression in the study population (-3.655 mL/min/1.73 m2), followed by patients with a baseline eGFR of 2 and a baseline serum phosphorus of >4.3 mg/dL (-2.833 mL/min/1.73 m 2). Among patients without proteinuria, those aged 67 years, females had on average a stable eGFR over time, with a large variability.ConclusionsIt is possible to rely on a few variables typically accessible in routine clinical practice to stratify patients with a different CKD progression rate. Stratification can be used to guide decisions about the follow-up schedule, treatments to slow progression of kidney disease, prevent its complications and to begin planning for dialysis and transplantation.

KW - CKD progression

KW - Decision tree

KW - Prediction models

UR - http://www.scopus.com/inward/record.url?scp=84895757986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895757986&partnerID=8YFLogxK

U2 - 10.1093/ndt/gft444

DO - 10.1093/ndt/gft444

M3 - Article

C2 - 24286974

AN - SCOPUS:84895757986

VL - 29

SP - 603

EP - 610

JO - Nephrology Dialysis Transplantation

JF - Nephrology Dialysis Transplantation

SN - 0931-0509

IS - 3

ER -