Learning objectives
To describe the basic elements of deep learning in the diagnosis and patient specific prediction of knee osteoarthritis progression.
To review the primary literature for common research methodologies and outline the progress and limitations of machine learning in knee osteoarthritis progression.
Background
Knee osteoarthritis (KOA) is an extremely common musculoskeletal disease and the most common form of arthritis causing pain, mobility limitation, affecting independence and quality of life.1 In current practice, there remains an inability to systematically diagnose the disease at an early stage, whereby it may be possible to slow down its progression. KOA is a big data problem in terms of data complexity, heterogeneity and size as it has been commonly considered in the literature and one of the most important hurdles in KOA management...
Imaging findings OR Procedure details
The risk factors for knee OA can be categorised into: demographic data, anthropometric features, medical history, soluble biomarkers, genes, imaging features and clinical outcomes.1 In DL, a sample (e.g. a patient) is represented by a number of features, including patient's characteristics, risk factors, shape/texture characteristics in medical images (X-ray and quantitative MRI structure assessment) or clinical history data. To facilitate the learning process, these elements are typically linked, forming a multidimensional feature vector. We review the common computational research methodologies that aim to address this...
Conclusion
The use of data mining and deep learning techniques could lead to the establishment of optimised models for real-time decision making. Deep learning can investigate correlations and multiscale modelling can predict system dynamics to identify causality. Heterogeneity and transparency in deep learning study design is a current limitation, and a standardised approach would enable robust evaluation of differences in model performance. A more accurate diagnosis and earlier prediction of KOA progression may be possible using this technology, improving treatment planning, better targeting of individually tailored...
Personal information
J. Gajera:
Nothing to disclose
A. Ahluwalia:
Nothing to disclose
A. Howie:
Nothing to disclose
B. Lurie:
Nothing to disclose
M. Roberts:
Nothing to disclose
D. Hunter:
Nothing to disclose
References
Kokkotis C, Moustakidis S, Papageorgiou E, Giakas G, Tsaopoulos DE. Machine learning in knee osteoarthritis: A review. Osteoarthritis and Cartilage Open. 2020;2:100069.
Jamshidi A, Pelletier J-P, Martel-Pelletier J. Machine-learning-based patient-specific prediction models for knee osteoarthritis. Nature Reviews Rheumatology. 2019;15:49-60.
Leung K, Zhang B, Tan J, et al. Prediction of Total Knee Replacement and Diagnosis of Osteoarthritis by Using Deep Learning on Knee Radiographs: Data from the Osteoarthritis Initiative. Radiology. 2020;296:584-593.
Janvier T, Jennane R, Valery A, et al. Subchondral tibial bone texture analysis predicts knee...