A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes

ABSTRACT Background and Aims To prevent end‐stage renal disease caused by diabetic kidney disease, we created a predictive model for high‐risk patients using machine learning. Methods and Results The reference point was the time at which each patient's estimated glomerular filtration rate (eGFR...

Full description

Saved in:
Bibliographic Details
Main Authors: Mari Watanabe, Shu Meguro, Kaiken Kimura, Michiaki Furukoshi, Tsuyoshi Masuda, Makoto Enomoto, Hiroshi Itoh
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Diabetes Investigation
Subjects:
Online Access:https://doi.org/10.1111/jdi.14309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846097194027843584
author Mari Watanabe
Shu Meguro
Kaiken Kimura
Michiaki Furukoshi
Tsuyoshi Masuda
Makoto Enomoto
Hiroshi Itoh
author_facet Mari Watanabe
Shu Meguro
Kaiken Kimura
Michiaki Furukoshi
Tsuyoshi Masuda
Makoto Enomoto
Hiroshi Itoh
author_sort Mari Watanabe
collection DOAJ
description ABSTRACT Background and Aims To prevent end‐stage renal disease caused by diabetic kidney disease, we created a predictive model for high‐risk patients using machine learning. Methods and Results The reference point was the time at which each patient's estimated glomerular filtration rate (eGFR) first fell below 60 mL/min/1.73 m2. The input period spanned the reference point to 1 year prior. The primary endpoint was a 50% decrease in eGFR from the mean of the input period over the 3 year evaluation period. We created predictive models for patients’ primary endpoints using time series data of various variables over the input period. Among 2,533 total patients, 1,409 had reference points, 31 had records for their input and evaluation periods and had reached their primary endpoints, and 317 patients had not. The area under the curve (AUC) of the predictive model peaked (0.81) when the minimum eGFR, the difference between maximum and minimum eGFR, and both maximum and minimum urinary protein values were included in the features. Conclusion The accuracy of prognosis prediction can be improved by considering the variable components of urinary protein and eGFR levels. This model will allow us to identify patients whose renal functions are relatively preserved with eGFR of more than 60 mL/min/1.73 m2 and are likely to benefit clinically from immediate treatment intensification.
format Article
id doaj-art-be8e764550124d70a3a94fa783be0c92
institution Kabale University
issn 2040-1116
2040-1124
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Diabetes Investigation
spelling doaj-art-be8e764550124d70a3a94fa783be0c922025-01-02T04:44:54ZengWileyJournal of Diabetes Investigation2040-11162040-11242025-01-01161939910.1111/jdi.14309A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetesMari Watanabe0Shu Meguro1Kaiken Kimura2Michiaki Furukoshi3Tsuyoshi Masuda4Makoto Enomoto5Hiroshi Itoh6Division of Nephrology, Endocrinology and Metabolism, Department of Internal Medicine Keio University School of Medicine Tokyo JapanDivision of Nephrology, Endocrinology and Metabolism, Department of Internal Medicine Keio University School of Medicine Tokyo JapanAsahi Kasei Corporation Tokyo JapanAsahi Kasei Corporation Tokyo JapanAsahi Kasei Corporation Tokyo JapanAsahi Kasei Corporation Tokyo JapanDivision of Nephrology, Endocrinology and Metabolism, Department of Internal Medicine Keio University School of Medicine Tokyo JapanABSTRACT Background and Aims To prevent end‐stage renal disease caused by diabetic kidney disease, we created a predictive model for high‐risk patients using machine learning. Methods and Results The reference point was the time at which each patient's estimated glomerular filtration rate (eGFR) first fell below 60 mL/min/1.73 m2. The input period spanned the reference point to 1 year prior. The primary endpoint was a 50% decrease in eGFR from the mean of the input period over the 3 year evaluation period. We created predictive models for patients’ primary endpoints using time series data of various variables over the input period. Among 2,533 total patients, 1,409 had reference points, 31 had records for their input and evaluation periods and had reached their primary endpoints, and 317 patients had not. The area under the curve (AUC) of the predictive model peaked (0.81) when the minimum eGFR, the difference between maximum and minimum eGFR, and both maximum and minimum urinary protein values were included in the features. Conclusion The accuracy of prognosis prediction can be improved by considering the variable components of urinary protein and eGFR levels. This model will allow us to identify patients whose renal functions are relatively preserved with eGFR of more than 60 mL/min/1.73 m2 and are likely to benefit clinically from immediate treatment intensification.https://doi.org/10.1111/jdi.14309Diabetic nephropathiesMachine learningPrognosis
spellingShingle Mari Watanabe
Shu Meguro
Kaiken Kimura
Michiaki Furukoshi
Tsuyoshi Masuda
Makoto Enomoto
Hiroshi Itoh
A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
Journal of Diabetes Investigation
Diabetic nephropathies
Machine learning
Prognosis
title A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
title_full A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
title_fullStr A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
title_full_unstemmed A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
title_short A machine learning model for predicting worsening renal function using one‐year time series data in patients with type 2 diabetes
title_sort machine learning model for predicting worsening renal function using one year time series data in patients with type 2 diabetes
topic Diabetic nephropathies
Machine learning
Prognosis
url https://doi.org/10.1111/jdi.14309
work_keys_str_mv AT mariwatanabe amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT shumeguro amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT kaikenkimura amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT michiakifurukoshi amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT tsuyoshimasuda amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT makotoenomoto amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT hiroshiitoh amachinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT mariwatanabe machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT shumeguro machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT kaikenkimura machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT michiakifurukoshi machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT tsuyoshimasuda machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT makotoenomoto machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes
AT hiroshiitoh machinelearningmodelforpredictingworseningrenalfunctionusingoneyeartimeseriesdatainpatientswithtype2diabetes