G Zhang1, B P Smith2, J F Plate3, R Casanova4, F-C Hsu5, J Li6, L Xia7, K C Li8, G G Poehling9, X Zhou10. 1. Department of Radiology, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: guzhang@wakehealth.edu. 2. Department of Orthopaedics, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: bpsmith@wakehealth.edu. 3. Department of Orthopaedics, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: jplate@wakehealth.edu. 4. Department of Biostatistical Sciences, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: casanova@wakehealth.edu. 5. Department of Biostatistical Sciences, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: fhsu@wakehealth.edu. 6. College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China. Electronic address: ljs@zju.edu.cn. 7. College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou, Zhejiang, China. Electronic address: xialing@zju.edu.cn. 8. Department of Radiology, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: kingli@wakehealth.edu. 9. Department of Orthopaedics, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: poehling@wakehealth.edu. 10. Department of Radiology, Wake Forest University School of Medicine, Winston-Salem, NC 27157, USA. Electronic address: xizhou@wakehealth.edu.
Abstract
OBJECTIVE: Unicompartmental knee arthroplasty (UKA) revision is usually due to the degenerative degree of knee articular osteochondral tissue in the untreated compartment. However, it is difficult to simulate the biomechanical behavior on this tissue accurately. This study presents and validates a reliable system to predict which osteoarthritis (OA) patients may suffer revision as a result of biomechanical reasons after having UKA. DESIGN: We collected all revision cases available (n = 11) and randomly selected 67 UKA cases to keep the revision prevalence of almost 14%. All these 78 cases have been followed at least 2 years. An elastic model is designed to characterize the biomechanical behavior of the articular osteochondral tissue for each patient. After calculated the force on the tissue, finite element method (FEM) is applied to calculating the strain of each tissue node. Kernel Ridge Regression (KRR) method is used to model the relationship between the strain information and the risk of revision. Therefore, the risk of UKA revision can be predicted by this integrated model. RESULTS: Leave-one-out (LOO) cross-validation (CV) is implemented to assess the prediction accuracy. As a result, the mean prediction accuracy is 93.58% for all these cases, demonstrating the high value of this model as a decision-making assistant for surgical plaining of knee OA. CONCLUSIONS: The results of this study demonstrated that this integrated model can predict the risk of UKA revision with theoretically high accuracy. It combines bio-mechanical and statistical learning approach to create a surgical planning tool which may support clinical decision in the future.
OBJECTIVE: Unicompartmental knee arthroplasty (UKA) revision is usually due to the degenerative degree of knee articular osteochondral tissue in the untreated compartment. However, it is difficult to simulate the biomechanical behavior on this tissue accurately. This study presents and validates a reliable system to predict which osteoarthritis (OA) patients may suffer revision as a result of biomechanical reasons after having UKA. DESIGN: We collected all revision cases available (n = 11) and randomly selected 67 UKA cases to keep the revision prevalence of almost 14%. All these 78 cases have been followed at least 2 years. An elastic model is designed to characterize the biomechanical behavior of the articular osteochondral tissue for each patient. After calculated the force on the tissue, finite element method (FEM) is applied to calculating the strain of each tissue node. Kernel Ridge Regression (KRR) method is used to model the relationship between the strain information and the risk of revision. Therefore, the risk of UKA revision can be predicted by this integrated model. RESULTS: Leave-one-out (LOO) cross-validation (CV) is implemented to assess the prediction accuracy. As a result, the mean prediction accuracy is 93.58% for all these cases, demonstrating the high value of this model as a decision-making assistant for surgical plaining of knee OA. CONCLUSIONS: The results of this study demonstrated that this integrated model can predict the risk of UKA revision with theoretically high accuracy. It combines bio-mechanical and statistical learning approach to create a surgical planning tool which may support clinical decision in the future.
Authors: Richard A Berger; R Michael Meneghini; Joshua J Jacobs; Mitchell B Sheinkop; Craig J Della Valle; Aaron G Rosenberg; Jorge O Galante Journal: J Bone Joint Surg Am Date: 2005-05 Impact factor: 5.284
Authors: C R Henak; E D Carruth; A E Anderson; M D Harris; B J Ellis; C L Peters; J A Weiss Journal: Osteoarthritis Cartilage Date: 2013-06-21 Impact factor: 6.576
Authors: Paul O Bolcos; Mika E Mononen; Ali Mohammadi; Mohammadhossein Ebrahimi; Matthew S Tanaka; Michael A Samaan; Richard B Souza; Xiaojuan Li; Juha-Sampo Suomalainen; Jukka S Jurvelin; Juha Töyräs; Rami K Korhonen Journal: Sci Rep Date: 2018-11-26 Impact factor: 4.379