Deep Learning Predicts Total Knee Replacement from Magnetic Resonance Images

Abstract

Knee Osteoarthritis (OA) is a common musculoskeletal disorder in the United States. When diagnosed at early stages, lifestyle interventions such as exercise and weight loss can slow OA progression, but at later stages, only an invasive option is available: total knee replacement (TKR). Though a generally successful procedure, only 2/3 of patients who undergo the procedure report their knees feeling "normal" post-operation, and complications can arise that require revision. This necessitates a model to identify a population at higher risk of TKR, particularly at less advanced stages of OA, such that appropriate treatments can be implemented that slow OA progression and delay TKR. Here, we present a deep learning pipeline that leverages MRI images and clinical and demographic information to predict TKR with AUC 0.834 ± 0.036 (p < 0.05). Most notably, the pipeline predicts TKR with AUC 0.943 ± 0.057 (p < 0.05) for patients without OA. Furthermore, we develop occlusion maps for case-control pairs in test data and compare regions used by the model in both, thereby identifying TKR imaging biomarkers. As such, this work takes strides towards a pipeline with clinical utility, and the biomarkers identified further our understanding of OA progression and eventual TKR onset. otherwise would, thereby reducing time spent pursuing nonsurgical alternatives with minimal probability of success while dealing with serious pain. Beyond this, if the model were to draw from medical images of the knee, it could identify anatomic regions most correlated with a TKR prediction. To this point, few studies have been conducted in this space, and those that have primarily investigate the importance of cartilage volume loss, subchondral bone defects, and bone marrow lesions [17][18][19] . An identification of more such biomarkers for TKR, however, could greatly improve understanding of both OA and TKR, and ultimately guide treatment strategies.Predictive modeling of TKR, however, has a limited history, particularly with models that use medical images. A few studies have leveraged random forest regression, Cochran-Armitage tests for trend, and t-tests to identify demographic, general health, and physical examination measurements that most strongly correlate with TKR or total joint arthroplasty (TJA) 20, 21 . Others have taken these efforts further, using techniques such as multiple regression and multivariate risk prediction models to predict TKR outright 22, 23 . To our knowledge, only one group has developed a predictive model of TKR that accepts image inputs, attaining performance that surpasses that of models using only clinical and demographic information 24 . Notably, past TKR predictive models largely measure performance by evaluating the area under the receiver operating characteristic (ROC) curve, which plots true positive rate against false positive rate 25 . However, in most datasets used in this space, the number of patients who eventually undergo TKR is dramatically higher among those who have advanced OA as opposed to those with n...

Artificial Learning and Machine Learning Decision Guidance Applications in Total Hip and Knee Arthroplasty: A Systematic Review

“…Hip and knee arthroplasty typically involve an older and highly comorbid patient population, and these tools can be especially helpful in identifying patient-specific needs and risks within this population. Examples of how these models can enable providers to create and optimize personalized treatment plans include accurate identification of an implant from a previous surgery for revision procedures and classifying total knee arthroplasty (TKA) surgical candidates based on patient-specific risk factors [29][30][31][33][34][35][37][38][39][40][41][42]44,62]. Hyer et al demonstrated an AI/ML model which classified TKA and total hip arthroplasty patients based on surgical complexity scores [19].…”

T2 analysis of the entire osteoarthritis initiative dataset

“…Our predictive models showed that T tuning the hyperparameter for the tree depths can be performed. 33 In reality, building highly accurate predictive and diagnostic models for OA requires rigorous feature engineering methods 34,35 work which is beyond the scope of this paper. We limited this initial study to the T 2 analysis of average values across compartments, however, previous studies reported that spatial assessment of the knee cartilage relaxation times using laminar and sub-compartmental analyses could lead to better and probably earlier identification of cartilage matrix abnormalities 36,37 Extraction of second-order statistical information or texture analysis 38,39 has been widely used to overcome the limitation of the average-based approaches.…”

Prognostic models for knee osteoarthritis: a protocol for systematic review, critical appraisal, and meta-analysis

“…Thus, it is preferable for KOA patients to delay TKA and to prolong the good health of their knees. Several models concerning TKA risk in KOA patients that conducted based on clinical information are reported, whose performance could be improved with the introduction of imaging data [14][15][16][17][18]. Chan et al [14] developed a formula reflecting the decision for TKA in patients with a painful KOA based on clinical and radiographic information, while Yu et al [15] automatically extracted patient data from electronic records to allow individuals TKA risk estimation.…”

“…Chan et al [14] developed a formula reflecting the decision for TKA in patients with a painful KOA based on clinical and radiographic information, while Yu et al [15] automatically extracted patient data from electronic records to allow individuals TKA risk estimation. Machine learning and deep learning methods were also used in building prediction models for identifying KOA patients at high risk of TKA [16][17][18]. Such models are necessitated for clinicians to pursue appropriate treatment options.…”