Unsupervised machine learning identifies two distinct posterior tibial slope clusters largely independent of Coronal Plane Alignment of the Knee in osteoarthritic knees
Unüberwachtes Machine-Learning identifiziert zwei distinkte Posterior-Tibial-Slope-Cluster weitgehend unabhängig von der Coronal Plane Alignment of the Knee bei arthrotischen Knien
Journal of Experimental Orthopaedics · 2026-10 · 13 (4)
DOI: 10.1002/jeo2.70945 ↗Auf einen Blick
Bei 3337 arthrotischen Knien identifizierte k-means zwei PTS-Cluster. Die PTS war weitgehend unabhängig von einzelnen CPAK-Phänotypen, zeigte aber einen Zusammenhang mit JLO.
Fragestellung
Lässt sich mit unüberwachtem Machine-Learning bei arthrotischen Knien natürliche PTS-Phänotypen identifizieren, und wie hängen sie mit CPAK und JLO zusammen?
Methode
Retrospektive radiologische Kohortenstudie mit 3337 arthrotischen Knien von 1746 Patient:innen; k-means-Clustering der PTS, Analyse von CPAK und JLO in 464 Knien.
Ergebnisse
Medianer PTS 5,6° (IQR 3,4°–7,7°). Zwei Cluster: flach 3,56° (55,91 %) und steil 8,52° (44,09 %). Kein CPAK-Phänotyp war in einem Cluster signifikant überrepräsentiert; JLO höher im flachen Cluster.
Schlussfolgerung der Autor:innen
Unüberwachtes k-means identifizierte zwei unterschiedliche sagittale PTS-Phänotypen bei arthrotischen Knien. Die PTS variierte weitgehend unabhängig von CPAK-Phänotypen, bei Zusammenhang mit JLO.
Kernaussagen
- Zwei PTS-Cluster: 3,56° und 8,52°
- Kein einzelner CPAK-Phänotyp war signifikant überrepräsentiert
- JLO war im flachen Cluster höher; PTS korrelierte invers mit JLO
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Journal of Experimental Orthopaedics, online erschienen am 13.10.2026. Verfasst von Dinko Vidović und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Traumatology Sestre Milosrdnice University Hospital Center Zagreb Croatia. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Purpose
Coronal‐plane classifications such as the Coronal Plane Alignment of the Knee (CPAK) classification support individualized total knee arthroplasty (TKA) planning but do not account for sagittal‐plane morphology, particularly the posterior tibial slope (PTS). This study aimed to determine whether unsupervised machine learning (k‐means clustering) could identify naturally occurring PTS phenotypes in osteoarthritic knees and to evaluate their association with CPAK classification and joint line obliquity (JLO).
Methods
This retrospective radiographic cohort study included 3337 osteoarthritic knees from 1746 patients. PTS was measured on lateral knee radiographs in all 3337 knees, using the posterior tibial cortex and the medial tibial plateau as reference lines. Full‐length standing radiographs were available for 464 knees; in these knees, the medial proximal tibial angle (MPTA) and the lateral distal femoral angle (LDFA) were measured to calculate the arithmetic hip–knee–ankle angle (aHKA) and JLO, and each knee was classified according to CPAK. K‐means clustering was used to identify PTS subgroups without predefined thresholds, and cluster validity was assessed using the elbow method and silhouette analysis. Associations between PTS clusters, CPAK phenotypes and radiographic parameters were analysed using the χ 2 test, adjusted standardized residuals, Fisher's exact test and correlation analysis.
Results
The median PTS was 5.6° (interquartile range 3.4°–7.7°). K‐means clustering identified two PTS clusters: a shallow‐slope cluster centred at 3.56°, comprising 55.91% of the knees and a steep‐slope cluster centred at 8.52°, comprising 44.09%. No individual CPAK phenotype was significantly overrepresented within either cluster. When phenotypes were grouped according to joint line orientation, however, apex‐distal phenotypes (I–III) were more frequently assigned to the steep‐slope cluster, whereas apex‐neutral phenotypes (IV–VI) were more frequently assigned to the shallow‐slope cluster. JLO was significantly higher in the shallow‐slope cluster and PTS showed a modest inverse correlation with JLO.
Conclusions
Unsupervised k‐means clustering identified two distinct sagittal PTS phenotypes in osteoarthritic knees. PTS varied largely independently of the individual CPAK phenotypes, although an association with JLO was observed. Sagittal morphology may therefore provide complementary information beyond coronal alignment classifications for the individualized planning of knee surgery. Level of Evidence Level IV.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Traumatology Sestre Milosrdnice University Hospital Center Zagreb Croatia.
- School of Medicine University of Zagreb Zagreb Croatia.
- School of Dental Medicine University of Zagreb Zagreb Croatia.
- School of Medicine Catholic University of Croatia Zagreb Croatia.
- Faculty of Health Studies University of Zagreb Zagreb Croatia.
- Department for Machine Learning Ruđer Bošković Institute Zagreb Croatia.
ORCID-Profile: Dejan Blažević, Borna Vojvodić, Anja Barešić, Tomislav Šmuc, David Glavaš Weinberger
Zitieren
APA
Vidović, D., Blažević, D., Baković, J., Čukelj, F., Karakaš, T., Vojvodić, B., Barešić, A., Šmuc, T., & Weinberger, D. G. (2026). Unsupervised machine learning identifies two distinct posterior tibial slope clusters largely independent of Coronal Plane Alignment of the Knee in osteoarthritic knees. Journal of Experimental Orthopaedics, 13(4). https://doi.org/10.1002/jeo2.70945
Vancouver
Vidović D, Blažević D, Baković J, Čukelj F, Karakaš T, Vojvodić B, et al. Unsupervised machine learning identifies two distinct posterior tibial slope clusters largely independent of Coronal Plane Alignment of the Knee in osteoarthritic knees. Journal of Experimental Orthopaedics. 2026;13(4). doi:10.1002/jeo2.70945
BibTeX
@article{Vidovi2026,
author = {Vidović, Dinko and Blažević, Dejan and Baković, Josip and Čukelj, Fabijan and Karakaš, Tin and Vojvodić, Borna and Barešić, Anja and Šmuc, Tomislav and Weinberger, David Glavaš},
title = {Unsupervised machine learning identifies two distinct posterior tibial slope clusters largely independent of Coronal Plane Alignment of the Knee in osteoarthritic knees},
journal = {Journal of Experimental Orthopaedics},
year = {2026},
volume = {13},
number = {4},
doi = {10.1002/jeo2.70945}
}
EUVIMED