Predicting Total Knee Replacement from Symptomology and Radiographic Structural Change Using Artificial Neural Networks—Data from the Osteoarthritis Initiative (OAI)

Abstract

The aim of the study was to longitudinally investigate symptomatic and structural factors prior to total knee replacement (TKR) surgery in order to identify influential factors that can predict a patient’s need for TKR surgery. In total, 165 participants (60% females; 64.5 ± 8.4 years; 29.7 ± 4.7 kg/m2) receiving a TKR in any of both knees within a four-year period were analyzed. Radiographic change, knee pain, knee function and quality of life were annually assessed prior to the TKR procedure. Self-learning artificial neural networks were applied to identify driving factors for the surgical procedure. Significant worsening of radiographic structural change was observed prior to TKR (p ≤ 0.0046), whereas knee symptoms (pain, function, quality of life) worsened significantly only in the year prior to the TKR procedure. By using our prediction model, we were able to predict correctly 80% of the classified individuals to undergo TKR surgery with a positive predictive value of 84% and a negative predictive value of 73%. Our prediction model offers the opportunity to assess a patient’s need for TKR surgery two years in advance based on easily available patient data and could therefore be used in a primary care setting.

Risk factors for progression to total knee arthroplasty within two years of presentation for knee osteoarthritis

“…A strength of our study is the inclusion of a predictive model that could potentially be integrated into the electronic health record (EHR) to streamline the triage process for knee OA patients. In a similar study, Heisinger et al 21 used artificial neural networks to identify symptomatic and structural predictors of a patient's need for TKA surgery. The researchers found that structural changes to the knee documented via KL grade worsened significantly at every annual visit 4 years prior to the TKA procedure.…”

Artificial intelligence in diagnosis of knee osteoarthritis and prediction of arthroplasty outcomes: a review

“… OA diagnosis and TKA need El-Galaly, A. 2020 Clinical Orthopaedics and Related Research [ 12 ] Heisinger, S. 2020 Journal of Clinical Medicine [ 13 ] Jafarzadeh, S. 2020 Osteoarthritis Cartilage [ 14 ] Leung, K. 2020 Radiology [ 15 ] Tolpadi, A.A. 2020 Scientific Reports [ 16 ] Yi, P. H. 2020 Knee [ 17 ] Norman, B. 2019 Journal of Digital Imaging [ 18 ] Tiulpin, A.…”

“… The provision of probability distributions for each KL grade prediction may assist clinicians in choosing KL grade in ambiguous cases. Heisinger (2020) [ 13 ] Journal of Clinical Medicine Need for TKA Artificial neural networks (ANNs) with linear, radial basis function and three-layer perceptron neural networks architectures Total percentage of correctly predicted knees: 80%. Positive predictive value: 84%.…”

“…In 2020, Heisinger et al [ 13 ] first designed an ML prediction model by investigating knee symptomatology (e.g., pain, function, and quality of life), Kellgren-Lawrence grading, and socioeconomic and demographic factors four years before TKA. The longitudinal analyses showed that significant worsening in knee symptomatology before TKA was the most important factor in decision making for TKA, compared to the radiographic progression of KOA.…”

Machine Learning–Based Individualized Survival Prediction Model for Total Knee Replacement in Osteoarthritis: Data From the Osteoarthritis Initiative

“…To date, there have been no comprehensive attempts to identify the most important features and to build a survival‐based model for predicting the time to TKR for an individual with OA. Recently, Heisinger et al, with the use of a small cohort (n = 165), applied 14 factors in a 4‐year period prior to TKR to predict an individual’s need for TKR surgery (11). In addition, an image‐based model with knee radiographs to classify individuals with OA who are at high risk of TKR has also been recently developed (12).…”