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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |