Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study

Abstract Machine learning algorithms that integrate multiple biomarkers are increasingly used in disease detection, yet economic considerations are often overlooked. Medial vascular calcification (mVC), a pathology associated with elevated cardiovascular risk in chronic kidney disease (CKD), require...

Full description

Saved in:
Bibliographic Details
Main Authors: Urszula Bialonczyk, Malgorzata Debowska, Lu Dai, Abdul Rashid Qureshi, Leon Bobrowski, Magnus Soderberg, Bengt Lindholm, Peter Stenvinkel, Tomasz Lukaszuk, Jan Poleszczuk
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02457-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850268753600708608
author Urszula Bialonczyk
Malgorzata Debowska
Lu Dai
Abdul Rashid Qureshi
Leon Bobrowski
Magnus Soderberg
Bengt Lindholm
Peter Stenvinkel
Tomasz Lukaszuk
Jan Poleszczuk
author_facet Urszula Bialonczyk
Malgorzata Debowska
Lu Dai
Abdul Rashid Qureshi
Leon Bobrowski
Magnus Soderberg
Bengt Lindholm
Peter Stenvinkel
Tomasz Lukaszuk
Jan Poleszczuk
author_sort Urszula Bialonczyk
collection DOAJ
description Abstract Machine learning algorithms that integrate multiple biomarkers are increasingly used in disease detection, yet economic considerations are often overlooked. Medial vascular calcification (mVC), a pathology associated with elevated cardiovascular risk in chronic kidney disease (CKD), requires cost-effective diagnostic approaches. This pilot study evaluated the cost-effectiveness of machine learning models for mVC detection using traditional risk markers and circulating biomarkers in 152 CKD patients undergoing living donor kidney transplantation. Patients were classified as having no/minimal (n = 93) or moderate/extensive (n = 59) mVC. Five classification frameworks with automatic variable selection identified predictors of mVC. Age and copeptin were selected by all algorithms, while diabetes, male sex, choline, and osteoprotegerin were chosen by four methods. The number of features selected ranged from 5 to 21. Although accuracy differences among classifiers were limited to 3%, models using more features nearly tripled the procedure’s cost. By incorporating the incremental cost-effectiveness ratio, the study highlighted significant disparities in performance versus cost among classifiers. The present findings suggest that machine learning has the potential to complement imaging techniques for mVC detection and uncover novel biomarkers. However, modest performance improvements may not justify higher costs, underscoring the importance of considering cost-effectiveness when selecting classification models.
format Article
id doaj-art-74809b6118b747c3b0b746028fa5b80d
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-74809b6118b747c3b0b746028fa5b80d2025-08-20T01:53:22ZengNature PortfolioScientific Reports2045-23222025-05-0115111010.1038/s41598-025-02457-2Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot studyUrszula Bialonczyk0Malgorzata Debowska1Lu Dai2Abdul Rashid Qureshi3Leon Bobrowski4Magnus Soderberg5Bengt Lindholm6Peter Stenvinkel7Tomasz Lukaszuk8Jan Poleszczuk9Nalecz Institute of Biocybernetics and Biomedical Engineering, Polish Academy of SciencesNalecz Institute of Biocybernetics and Biomedical Engineering, Polish Academy of SciencesAging Research Center, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet and Stockholm UniversityRenal Medicine and Baxter Novum, Department of Clinical Science, Intervention and Technology, Karolinska InstitutetNalecz Institute of Biocybernetics and Biomedical Engineering, Polish Academy of SciencesPathology, Clinical Pharmacology and Safety Sciences, AstraZeneca R&DRenal Medicine and Baxter Novum, Department of Clinical Science, Intervention and Technology, Karolinska InstitutetRenal Medicine and Baxter Novum, Department of Clinical Science, Intervention and Technology, Karolinska InstitutetFaculty of Computer Science, Bialystok University of TechnologyNalecz Institute of Biocybernetics and Biomedical Engineering, Polish Academy of SciencesAbstract Machine learning algorithms that integrate multiple biomarkers are increasingly used in disease detection, yet economic considerations are often overlooked. Medial vascular calcification (mVC), a pathology associated with elevated cardiovascular risk in chronic kidney disease (CKD), requires cost-effective diagnostic approaches. This pilot study evaluated the cost-effectiveness of machine learning models for mVC detection using traditional risk markers and circulating biomarkers in 152 CKD patients undergoing living donor kidney transplantation. Patients were classified as having no/minimal (n = 93) or moderate/extensive (n = 59) mVC. Five classification frameworks with automatic variable selection identified predictors of mVC. Age and copeptin were selected by all algorithms, while diabetes, male sex, choline, and osteoprotegerin were chosen by four methods. The number of features selected ranged from 5 to 21. Although accuracy differences among classifiers were limited to 3%, models using more features nearly tripled the procedure’s cost. By incorporating the incremental cost-effectiveness ratio, the study highlighted significant disparities in performance versus cost among classifiers. The present findings suggest that machine learning has the potential to complement imaging techniques for mVC detection and uncover novel biomarkers. However, modest performance improvements may not justify higher costs, underscoring the importance of considering cost-effectiveness when selecting classification models.https://doi.org/10.1038/s41598-025-02457-2ClassificationFeature selectionMedial vascular calcificationChronic kidney diseaseIncremental cost-effectiveness ratio
spellingShingle Urszula Bialonczyk
Malgorzata Debowska
Lu Dai
Abdul Rashid Qureshi
Leon Bobrowski
Magnus Soderberg
Bengt Lindholm
Peter Stenvinkel
Tomasz Lukaszuk
Jan Poleszczuk
Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
Scientific Reports
Classification
Feature selection
Medial vascular calcification
Chronic kidney disease
Incremental cost-effectiveness ratio
title Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
title_full Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
title_fullStr Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
title_full_unstemmed Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
title_short Balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease: a pilot study
title_sort balancing accuracy and cost in machine learning models for detecting medial vascular calcification in chronic kidney disease a pilot study
topic Classification
Feature selection
Medial vascular calcification
Chronic kidney disease
Incremental cost-effectiveness ratio
url https://doi.org/10.1038/s41598-025-02457-2
work_keys_str_mv AT urszulabialonczyk balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT malgorzatadebowska balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT ludai balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT abdulrashidqureshi balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT leonbobrowski balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT magnussoderberg balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT bengtlindholm balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT peterstenvinkel balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT tomaszlukaszuk balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy
AT janpoleszczuk balancingaccuracyandcostinmachinelearningmodelsfordetectingmedialvascularcalcificationinchronickidneydiseaseapilotstudy