An Algorithmic Approach to Understanding Osteoarthritic Knee Pain.

Background: Osteoarthritic knee pain is a complex phenomenon, and multiple factors, both within the knee and external to it, can contribute to how the patient perceives pain. We sought to determine how well a deep neural network could predict osteoarthritic knee pain and other symptoms solely from a single radiograph view. Methods: We used data from the Osteoarthritis Initiative, a 10-year observational study of patients with knee osteoarthritis. We paired >50,000 weight-bearing, posteroanterior knee radiographs with corresponding Knee Injury and Osteoarthritis Outcome Score (KOOS) pain, symptoms, and activities of daily living subscores and used them to train a series of deep learning models to predict those scores solely from raw radiographic input. We created regression models for specific score predictions and classification models to predict whether the modeled KOOS subscore exceeded a range of thresholds. Results: The root-mean-square errors were 15.7 for KOOS pain, 13.1 for KOOS symptoms, and 14.2 for KOOS activities of daily living. Modeling was performed to predict whether pain was above or below given pain thresholds, and was able to predict extreme pain (KOOS pain < 40) with an area under the curve (AUC) of 0.78. Notably, the system was also able to correctly predict numerous cases where the Kellgren-Lawrence (KL) grade assigned by the radiologist was 0 but patient pain was high, and cases where the KL grade was 4 but patient pain was low. Conclusions: A deep neural network can be trained to predict the osteoarthritic knee pain that a patient experienced and other symptoms with reasonable accuracy from a single posteroanterior view of the knee, even using low-resolution images. The system can predict pain and dysfunction that the traditional KL grade does not capture. Deep learning applied to raw imaging inputs holds promise for disentangling sources of pain within the knee from aggravating factors external to the knee. Level of Evidence: Diagnostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Do Patient-Reported Outcomes Reflect Objective Measures of Function? Implications for Total Knee Arthroplasty.

BACKGROUND: Patient-reported outcomes (PROs) are used in research, clinical practice, and by federal reimbursement models to assess outcomes for patients who have knee osteoarthritis (OA) and total knee arthroplasty (TKA). We examined a large cohort of patients to determine if commonly used PROs reflect observed evaluation as measured by standardized functional tests (SFTs). METHODS: We used data from the Osteoarthritis Initiative, a 10-year observational study of knee osteoarthritis patients. Two cohorts were examined: 1) participants who received TKA (n = 281) and 2) participants who have native OA (n = 4,687). The PROs included Western Ontario and McMaster Osteoarthritis Index (WOMAC), Knee Injury and Osteoarthritis Outcome Score (KOOS), 12-Item Short Form Health Survey (SF-12), and Intermittent and Constant Pain Score (ICOAP). The SFTs included 20 m and 400 meter (m) walks and chair stand pace. Repeated measures correlation coefficients were used to determine the relationship between PROs and SFTs. RESULTS: The PROs and SFTs were not strongly correlated in either cohort. The magnitude of the repeated measures correlation (rrm) between KOOS, WOMAC, SF-12, and ICOAP scores and SFT measurements in native knee OA patients ranged as follows: 400 m walk pace (0.08 to 0.20), chair stand pace (0.05 to 0.12), and 20 m pace (0.02 to 0.21), all with P < .05. In the TKA cohort, values ranged as follows: 400 M walk pace (0.00 to 0.29), chair stand time (0.02 to 0.23), and 20 M pace (0.03 to 0.30). Due to the smaller cohort size, the majority, but not all had P values < .05. CONCLUSION: There is not a strong association between PROs and SFTs among patients who have knee OA or among patients who received a TKA. Therefore, PROs should not be used as a simple proxy for observed evaluation of physical function. Rather, PROs and SFTs are complementary and should be used in combination for a more nuanced and complete characterization of outcome.

Deep Learning and Imaging for the Orthopaedic Surgeon: How Machines "Read" Radiographs.

➤: In the not-so-distant future, orthopaedic surgeons will be exposed to machines that begin to automatically "read" medical imaging studies using a technology called deep learning. ➤: Deep learning has demonstrated remarkable progress in the analysis of medical imaging across a range of modalities that are commonly used in orthopaedics, including radiographs, computed tomographic scans, and magnetic resonance imaging scans. ➤: There is a growing body of evidence showing clinical utility for deep learning in musculoskeletal radiography, as evidenced by studies that use deep learning to achieve an expert or near-expert level of performance for the identification and localization of fractures on radiographs. ➤: Deep learning is currently in the very early stages of entering the clinical setting, involving validation and proof-of-concept studies for automated medical image interpretation. ➤: The success of deep learning in the analysis of medical imaging has been propelling the field forward so rapidly that now is the time for surgeons to pause and understand how this technology works at a conceptual level, before (not after) the technology ends up in front of us and our patients. That is the purpose of this article.