A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease

Abstract Background Individuals with diabetic kidney disease (DKD) often suffer cardiac and kidney events. We sought to develop an accurate means by which to stratify risk in DKD. Methods Clinical variables and biomarkers were evaluated for their ability to predict the adjudicated primary composite...

Full description

Saved in:
Bibliographic Details
Main Authors: James L. Jr. Januzzi, Naveed Sattar, Muthiah Vaduganathan, Craig A. Magaret, Rhonda F. Rhyne, Yuxi Liu, Serge Masson, Javed Butler, Michael K. Hansen
Format: Article
Language:English
Published: BMC 2025-05-01
Series:Cardiovascular Diabetology
Subjects:
Online Access:https://doi.org/10.1186/s12933-025-02779-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726196231700480
author James L. Jr. Januzzi
Naveed Sattar
Muthiah Vaduganathan
Craig A. Magaret
Rhonda F. Rhyne
Yuxi Liu
Serge Masson
Javed Butler
Michael K. Hansen
author_facet James L. Jr. Januzzi
Naveed Sattar
Muthiah Vaduganathan
Craig A. Magaret
Rhonda F. Rhyne
Yuxi Liu
Serge Masson
Javed Butler
Michael K. Hansen
author_sort James L. Jr. Januzzi
collection DOAJ
description Abstract Background Individuals with diabetic kidney disease (DKD) often suffer cardiac and kidney events. We sought to develop an accurate means by which to stratify risk in DKD. Methods Clinical variables and biomarkers were evaluated for their ability to predict the adjudicated primary composite endpoint of CREDENCE (Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation) by 3 years. Using machine learning techniques, a parsimonious risk algorithm was developed. Results The final model included age, body-mass index, systolic blood pressure, and concentrations of N-terminal pro-B type natriuretic peptide, high sensitivity cardiac troponin T, insulin-like growth factor binding protein-7 and growth differentiation factor-15. The model had an in-sample C-statistic of 0.80 (95% CI = 0.77–0.83; P < 0.001). Dividing results into low, medium and high risk categories, for each increase in level the hazard ratio increased by 3.43 (95% CI = 2.72–4.32; P < 0.001). Low risk scores had negative predictive value of 94%, while high risk scores had positive predictive value of 58%. Higher values were associated with shorter time to event (log rank P < 0.001). Rising values at 1 year predicted higher risk for subsequent DKD events. Canagliflozin treatment reduced score results by 1 year with consistent event reduction across risk levels. Accuracy of the risk model was validated in separate cohorts from CREDENCE and the generally lower risk Canagliflozin Cardiovascular Assessment Study. Conclusions We describe a validated risk algorithm that accurately predicts cardio-kidney outcomes across a broad range of baseline risk. Trial registration CREDENCE (Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation; NCT02065791) and CANVAS (Canagliflozin Cardiovascular Assessment Study; NCT01032629/NCT01989754). Graphical abstract Persons with diabetic kidney disease (DKD) are at riskfor progressive kidney failure and cardiovascular (CV) events. Using datafrom the CREDENCE trial of patients with type 2 diabetes and DKD,machine learning techniques were applied to create a highly accuratealgorithm to predict progressive DKD and adverse CV outcomes. Thealgorithm was validated both within an internal CREDENCE cohort andexternally in the CANVAS trial.
format Article
id doaj-art-44d6b7602b7b4de7b68e7401e79883dc
institution DOAJ
issn 1475-2840
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series Cardiovascular Diabetology
spelling doaj-art-44d6b7602b7b4de7b68e7401e79883dc2025-08-20T03:10:16ZengBMCCardiovascular Diabetology1475-28402025-05-0124111310.1186/s12933-025-02779-5A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney diseaseJames L. Jr. Januzzi0Naveed Sattar1Muthiah Vaduganathan2Craig A. Magaret3Rhonda F. Rhyne4Yuxi Liu5Serge Masson6Javed Butler7Michael K. Hansen8Cardiology Division, Baim Institute for Clinical Research, Massachusetts General HospitalBHF Glasgow Cardiovascular Research Centre, University of GlasgowHarvard Medical School, Brigham and Women’s HospitalPrevencio, IncPrevencio, IncHarvard Medical School, Massachusetts General HospitalRoche Diagnostics IncBaylor Scott & White InstituteJanssen Research & Development, LLCAbstract Background Individuals with diabetic kidney disease (DKD) often suffer cardiac and kidney events. We sought to develop an accurate means by which to stratify risk in DKD. Methods Clinical variables and biomarkers were evaluated for their ability to predict the adjudicated primary composite endpoint of CREDENCE (Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation) by 3 years. Using machine learning techniques, a parsimonious risk algorithm was developed. Results The final model included age, body-mass index, systolic blood pressure, and concentrations of N-terminal pro-B type natriuretic peptide, high sensitivity cardiac troponin T, insulin-like growth factor binding protein-7 and growth differentiation factor-15. The model had an in-sample C-statistic of 0.80 (95% CI = 0.77–0.83; P < 0.001). Dividing results into low, medium and high risk categories, for each increase in level the hazard ratio increased by 3.43 (95% CI = 2.72–4.32; P < 0.001). Low risk scores had negative predictive value of 94%, while high risk scores had positive predictive value of 58%. Higher values were associated with shorter time to event (log rank P < 0.001). Rising values at 1 year predicted higher risk for subsequent DKD events. Canagliflozin treatment reduced score results by 1 year with consistent event reduction across risk levels. Accuracy of the risk model was validated in separate cohorts from CREDENCE and the generally lower risk Canagliflozin Cardiovascular Assessment Study. Conclusions We describe a validated risk algorithm that accurately predicts cardio-kidney outcomes across a broad range of baseline risk. Trial registration CREDENCE (Canagliflozin and Renal Events in Diabetes with Established Nephropathy Clinical Evaluation; NCT02065791) and CANVAS (Canagliflozin Cardiovascular Assessment Study; NCT01032629/NCT01989754). Graphical abstract Persons with diabetic kidney disease (DKD) are at riskfor progressive kidney failure and cardiovascular (CV) events. Using datafrom the CREDENCE trial of patients with type 2 diabetes and DKD,machine learning techniques were applied to create a highly accuratealgorithm to predict progressive DKD and adverse CV outcomes. Thealgorithm was validated both within an internal CREDENCE cohort andexternally in the CANVAS trial.https://doi.org/10.1186/s12933-025-02779-5Diabetic kidney diseaseCanagliflozinDiabetes mellitusRisk predictionPrognosis
spellingShingle James L. Jr. Januzzi
Naveed Sattar
Muthiah Vaduganathan
Craig A. Magaret
Rhonda F. Rhyne
Yuxi Liu
Serge Masson
Javed Butler
Michael K. Hansen
A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
Cardiovascular Diabetology
Diabetic kidney disease
Canagliflozin
Diabetes mellitus
Risk prediction
Prognosis
title A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
title_full A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
title_fullStr A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
title_full_unstemmed A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
title_short A validated multivariable machine learning model to predict cardio-kidney risk in diabetic kidney disease
title_sort validated multivariable machine learning model to predict cardio kidney risk in diabetic kidney disease
topic Diabetic kidney disease
Canagliflozin
Diabetes mellitus
Risk prediction
Prognosis
url https://doi.org/10.1186/s12933-025-02779-5
work_keys_str_mv AT jamesljrjanuzzi avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT naveedsattar avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT muthiahvaduganathan avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT craigamagaret avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT rhondafrhyne avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT yuxiliu avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT sergemasson avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT javedbutler avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT michaelkhansen avalidatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT jamesljrjanuzzi validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT naveedsattar validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT muthiahvaduganathan validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT craigamagaret validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT rhondafrhyne validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT yuxiliu validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT sergemasson validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT javedbutler validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease
AT michaelkhansen validatedmultivariablemachinelearningmodeltopredictcardiokidneyriskindiabetickidneydisease