Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements

Hip displacement is a significant concern in children with cerebral palsy (CP), necessitating accurate and timely assessment to prevent long-term complications. This study developed a support vector machine (SVM) model to classify hip conditions using migration percentage (MP) measurements obtained...

Full description

Saved in:
Bibliographic Details
Main Authors: Sema Ertan Birsel, Ekrem Demirci, Ali Seker, Kadriye Yasemin Usta Ayanoğlu, Emir Oncu, Fatih Ciftci
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Bone Reports
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352187225000294
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335731090096128
author Sema Ertan Birsel
Ekrem Demirci
Ali Seker
Kadriye Yasemin Usta Ayanoğlu
Emir Oncu
Fatih Ciftci
author_facet Sema Ertan Birsel
Ekrem Demirci
Ali Seker
Kadriye Yasemin Usta Ayanoğlu
Emir Oncu
Fatih Ciftci
author_sort Sema Ertan Birsel
collection DOAJ
description Hip displacement is a significant concern in children with cerebral palsy (CP), necessitating accurate and timely assessment to prevent long-term complications. This study developed a support vector machine (SVM) model to classify hip conditions using migration percentage (MP) measurements obtained from 176 hips across 88 anteroposterior pelvic radiographs. MP values were categorized into three groups: normal (MP ≤ 30 %), risky (30 % < MP ≤ 60 %), and dislocated (MP > 60 %). The SVM model was evaluated using stratified k-fold cross-validation, with accuracy, precision, recall, and F1-scores as key metrics. Its classifications were compared to manual evaluations performed by an orthopedic resident and a pediatric orthopedic surgeon. The model achieved an overall accuracy of 92.898 %, surpassing the consistency and reliability of manual assessments, particularly in identifying dislocated hips. Statistical analysis showed no significant differences between the model's MP measurements and those of the clinicians, validating its effectiveness. This study highlights the potential of SVM models to enhance diagnostic accuracy, reduce variability in evaluations, and support clinical decision-making. Future research should expand the dataset and incorporate advanced machine learning models to further improve diagnostic precision.
format Article
id doaj-art-c780e25a79b140c6a6a025d8644f90d9
institution Kabale University
issn 2352-1872
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Bone Reports
spelling doaj-art-c780e25a79b140c6a6a025d8644f90d92025-08-20T03:45:11ZengElsevierBone Reports2352-18722025-06-012510185210.1016/j.bonr.2025.101852Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurementsSema Ertan Birsel0Ekrem Demirci1Ali Seker2Kadriye Yasemin Usta Ayanoğlu3Emir Oncu4Fatih Ciftci5Ortopediatri Pediatric Orthopedics Academy, Istanbul, TurkeyIstanbul University-Cerrahpasa, Cerrahpasa Faculty of Medicine, Department of Orthopedics and Traumatology, Istanbul, TurkeyIstanbul University-Cerrahpasa, Cerrahpasa Faculty of Medicine, Department of Orthopedics and Traumatology, Istanbul, TurkeyDepartment of Tropiko Software and Consultancy, Istanbul, TurkeyDepartment of Bioengineering, Faculty of Chemical and Metallurgical Engineering, Yıldız Technical University, İstanbul 34210, Turkey; BioriginAI Research Group, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul, 34015, Turkey; Correspondence to: E. Oncu, BioriginAI Research Group, Department of Bioengineering, Faculty of Chemical and Metallurgical Engineering, Yıldız Technical University, Istanbul, 34210, Turkey.BioriginAI Research Group, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul, 34015, Turkey; Faculty of Engineering, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul 34015, Turkey; Department of Technology Transfer Office, Fatih Sultan Mehmet Vakıf University, Istanbul, 34015, Turkey; Correspondence to: F. Ciftci, BioriginAI Research Group, Department of Biomedical Engineering, Fatih Sultan Mehmet Vakıf University, Istanbul 34015, Turkey.Hip displacement is a significant concern in children with cerebral palsy (CP), necessitating accurate and timely assessment to prevent long-term complications. This study developed a support vector machine (SVM) model to classify hip conditions using migration percentage (MP) measurements obtained from 176 hips across 88 anteroposterior pelvic radiographs. MP values were categorized into three groups: normal (MP ≤ 30 %), risky (30 % < MP ≤ 60 %), and dislocated (MP > 60 %). The SVM model was evaluated using stratified k-fold cross-validation, with accuracy, precision, recall, and F1-scores as key metrics. Its classifications were compared to manual evaluations performed by an orthopedic resident and a pediatric orthopedic surgeon. The model achieved an overall accuracy of 92.898 %, surpassing the consistency and reliability of manual assessments, particularly in identifying dislocated hips. Statistical analysis showed no significant differences between the model's MP measurements and those of the clinicians, validating its effectiveness. This study highlights the potential of SVM models to enhance diagnostic accuracy, reduce variability in evaluations, and support clinical decision-making. Future research should expand the dataset and incorporate advanced machine learning models to further improve diagnostic precision.http://www.sciencedirect.com/science/article/pii/S2352187225000294Artificial intelligenceBone diseasesCase studyCerebral palsyMachine learning
spellingShingle Sema Ertan Birsel
Ekrem Demirci
Ali Seker
Kadriye Yasemin Usta Ayanoğlu
Emir Oncu
Fatih Ciftci
Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
Bone Reports
Artificial intelligence
Bone diseases
Case study
Cerebral palsy
Machine learning
title Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
title_full Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
title_fullStr Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
title_full_unstemmed Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
title_short Machine learning-assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
title_sort machine learning assisted classification of hip conditions in pediatric cerebral palsy patients using migration percentage measurements
topic Artificial intelligence
Bone diseases
Case study
Cerebral palsy
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2352187225000294
work_keys_str_mv AT semaertanbirsel machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements
AT ekremdemirci machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements
AT aliseker machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements
AT kadriyeyaseminustaayanoglu machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements
AT emironcu machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements
AT fatihciftci machinelearningassistedclassificationofhipconditionsinpediatriccerebralpalsypatientsusingmigrationpercentagemeasurements