EUVIMEDEUVIMED entdecken
Crossref

Unveiling knee morphology with SHAP: shaping personalized medicine through explainable AI

Berke Cansiz, Serdar Arslan, Muhammet Zeki Gültekin, Gorkem Serbes

The Knee · 2025-10 · 56 · 415-430

DOI: 10.1016/j.knee.2025.06.012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Knee, 2025-10. Verfasst von Berke Cansiz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Yildiz Technical University, Esenler, Istanbul 34220, Turkey. Hauptthemen laut MEDLINE: Precision Medicine, Knee Joint, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: This study aims to enhance personalized medical assessments and the early detection of knee-related pathologies by examining the relationship between knee morphology and demographic factors such as age, gender, and body mass index. Additionally, gender-specific reference values for knee morphological features will be determined using explainable artificial intelligence (XAI). METHODS: A retrospective analysis was conducted on the MRI data of 500 healthy knees aged 20-40 years. The study included various knee morphological features such as Distal Femoral Width (DFW), Lateral Femoral Condyler Width (LFCW), Intercondylar Femoral Width (IFW), Anterior Cruciate Ligament Width (ACLW), and Anterior Cruciate Ligament Length (ACLL). Machine learning models, including Decision Trees, Random Forests, Light Gradient Boosting, Multilayer Perceptron, and Support Vector Machines, were employed to predict gender based on these features. The SHapley Additive exPlanation was used to analyze feature importance. RESULTS: The learning models demonstrated high classification performance, with 83.2% (±5.15) for classification of clusters based on morphological feature and 88.06% (±4.8) for gender classification. These results validated that the strong correlation between knee morphology and gender. CONCLUSION: The study found that DFW is the most significant feature for gender prediction, with values below 78-79 mm range indicating females and values above this range indicating males. LFCW, IFW, ACLW, and ACLL also showed significant gender-based differences. The findings establish gender-specific reference values for knee morphological features, highlighting the impact of gender on knee morphology. These reference values can improve the accuracy of diagnoses and treatment plans tailored to each gender, enhancing personalized medical care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Precision MedicineKnee JointArtificial IntelligenceHumansFemaleMaleAdultRetrospective StudiesYoung AdultMagnetic Resonance ImagingMachine LearningSex FactorsReference ValuesFemurAnterior Cruciate Ligament

Stichwörter der Autor:innen

Artificial intelligenceDistal Femoral WidthKnee morphologySHapley Additive exPlanationsTurkish population

Autor:innen und Institutionen

  • Department of Biomedical Engineering, Yildiz Technical University, Esenler, Istanbul 34220, Turkey.
  • Department of Physiotherapy and Rehabilitation, Faculty of Nezehat Keleşoğlu Health Science, Necmettin Erbakan University, Konya, Turkey.
  • Department of Orthopedics and Traumatology, Konya City Hospital, Konya, Turkey.
  • Department of Biomedical Engineering, Yildiz Technical University, Esenler, Istanbul 34220, Turkey. Electronic address: gserbes@yildiz.edu.tr.

Zitieren

APA

Cansiz, B., Arslan, S., Gültekin, M. Z., & Serbes, G. (2025). Unveiling knee morphology with SHAP: shaping personalized medicine through explainable AI. The Knee, 56, 415-430. https://doi.org/10.1016/j.knee.2025.06.012

Vancouver

Cansiz B, Arslan S, Gültekin MZ, Serbes G. Unveiling knee morphology with SHAP: shaping personalized medicine through explainable AI. The Knee. 2025;56:415-430. doi:10.1016/j.knee.2025.06.012

BibTeX
@article{Cansiz2025,
  author = {Cansiz, Berke and Arslan, Serdar and Gültekin, Muhammet Zeki and Serbes, Gorkem},
  title = {Unveiling knee morphology with SHAP: shaping personalized medicine through explainable AI},
  journal = {The Knee},
  year = {2025},
  volume = {56},
  pages = {415--430},
  doi = {10.1016/j.knee.2025.06.012}
}
Kostenlos starten →