Promises and limitations of deep learning for predicting knee osteoarthritis progression from medical imaging: A systematic review
Knee Surgery, Sports Traumatology, Arthroscopy · 2026-11 · 34 (11) · 4219-4234
DOI: 10.1002/ksa.70555 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, online erschienen am 03.08.2026. Verfasst von Amna Gillani und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedics and Sports Orthopaedics, School of Medicine and Health, TUM University Hospital, Technical University of Munich, Munich, G…. Hauptthemen laut MEDLINE: Osteoarthritis, Knee, Disease Progression, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Purpose
To systematically evaluate the performance, methodological quality, and translational barriers of deep learning (DL) models for predicting knee osteoarthritis (KOA) progression from medical imaging.
Methods
Following PRISMA guidelines, we searched PubMed, Scopus, and Web of Science (inception to June 2026) for peer‐reviewed studies applying DL to predict KOA progression from medical imaging. Two reviewers independently screened studies, extracted data, and assessed risk of bias using PROBAST‐AI. The primary outcome was area under the receiver operating characteristic curve (AUC). Narrative synthesis was performed due to heterogeneity in imaging modalities, outcome definitions, and prediction horizons.
Results
From 1116 records, 33 studies (2019–2026) met the inclusion criteria, encompassing 50 predictive models. Sample sizes ranged from 340 to 52,981 knees (median: 4298). Nine progression definitions were identified and categorised as structural deterioration ( n = 14), symptomatic worsening ( n = 2), surgical endpoints ( n = 8) or combined outcomes ( n = 9). Nearly all studies (97%) used the Osteoarthritis Initiative dataset for training, and only 27% performed external validation. Surgery prediction models showed the highest descriptive median AUC (0.87), compared with structural (0.78) and symptomatic (0.79) progression models, but reflect non‐disease factors including access to care. MRI‐based models showed higher internal median AUCs (0.85) than radiograph‐based models (0.81), but none underwent external validation. Externally validated models showed performance degradation (median AUC: 0.75 vs. 0.81 internal). Combining imaging modalities did not consistently improve predictions. However, studies leveraging longitudinal trajectories reported higher internal performance. Most studies showed low risk of bias in participant selection and outcome assessment, but 76% had unclear or high risk in the analysis domain.
Conclusions
DL models demonstrate proof‐of‐concept for predicting KOA progression but require substantial improvements before clinical deployment. Overcoming translational barriers requires standardised progression definitions integrating structural and symptomatic outcomes, rigorous multi‐site validation, and models that effectively leverage multimodal and longitudinal data. Level of Evidence N/A.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Orthopaedics and Sports Orthopaedics, School of Medicine and Health, TUM University Hospital, Technical University of Munich, Munich, Germany.
- Chair for AI in Healthcare and Medicine, TUM University Hospital, Technical University of Munich, Munich, Germany.
- Musculoskeletal Radiology Section, TUM University Hospital, Technical University of Munich, Munich, Germany.
- University Department of Orthopedic Surgery and Traumatology, Kantonsspital Baselland, Bruderholz, Switzerland.
- Department of Clinical Research, Research Group Michael T. Hirschmann, Regenerative Medicine & Biomechanics, University of Basel, Basel, Switzerland.
- Department of Computing, Imperial College London, London, UK.
ORCID-Profile: Amna Gillani, Rüdiger von Eisenhart-Rothe, Klaus Woertler, Michael T Hirschmann, Daniel Rueckert, Florian Hinterwimmer
Zitieren
APA
Gillani, A., von Eisenhart-Rothe, R., Woertler, K., Hirschmann, M. T., Rueckert, D., & Hinterwimmer, F. (2026). Promises and limitations of deep learning for predicting knee osteoarthritis progression from medical imaging: A systematic review. Knee Surgery, Sports Traumatology, Arthroscopy, 34(11), 4219-4234. https://doi.org/10.1002/ksa.70555
Vancouver
Gillani A, von Eisenhart-Rothe R, Woertler K, Hirschmann MT, Rueckert D, Hinterwimmer F. Promises and limitations of deep learning for predicting knee osteoarthritis progression from medical imaging: A systematic review. Knee Surgery, Sports Traumatology, Arthroscopy. 2026;34(11):4219-4234. doi:10.1002/ksa.70555
BibTeX
@article{Gillani2026,
author = {Gillani, Amna and von Eisenhart-Rothe, Rüdiger and Woertler, Klaus and Hirschmann, Michael T and Rueckert, Daniel and Hinterwimmer, Florian},
title = {Promises and limitations of deep learning for predicting knee osteoarthritis progression from medical imaging: A systematic review},
journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
year = {2026},
volume = {34},
number = {11},
pages = {4219--4234},
doi = {10.1002/ksa.70555}
}
EUVIMED