Autosoft Journal

Online Manuscript Access


Surgical Outcome Prediction in Total Knee Arthroplasty using Machine Learning


Authors



Abstract

This work aimed to predict postoperative knee functions of a new patient prior to total knee arthroplasty (TKA) surgery using machine learning, because such prediction is essential for surgical planning and for patients to better understand the TKA outcome. However, the main difficulty is to determine the relationships among individual varieties of preoperative and postoperative knee kinematics. The problem was solved by constructing predictive models from the knee kinematics data of 35 osteoarthritis patients, operated by posterior stabilized implant, based on generalized linear regression (GLR) analysis. Two prediction methods (without and with principal component analysis followed by GLR) along with their sub-classes were proposed, and they were finally evaluated by a leave-one-out cross-validation procedure. The best method can predict the postoperative outcome of a new patient with a Pearson's correlation coefficient (cc) of 0.84 ± 0.15 (mean±SD) and a root-mean-squared-error (RMSE) of 3.27±1.42 mm for anterior-posterior vs. flexion/extension (A-P pattern), and a cc of 0.89±0.15 and RMSE of 4.25±1.92° for valgus-varus vs. flexion/extension (v-v pattern). Although these were validated for one type of prosthesis, they could be applicable to other implants, because the definition of knee kinematics, measured by a navigation system, is appropriate for other implants.


Keywords


Pages

Total Pages: 16

DOI
10.31209/2018.100000034


Manuscript ViewPdf Subscription required to access this document

Obtain access this manuscript in one of the following ways


Already subscribed?

Need information on obtaining a subscription? Personal and institutional subscriptions are available.

Already an author? Have access via email address?


Published

Online Article

Cite this document


References

H. Akaike. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19(6), 716-723. https://doi.org/10.1109/TAC.1974.1100705

K. R. Berend, A. V. Lombardi Jr, & J. B. Adams. (2013). Which total knee replacement implant should I pick? Correcting the pathology: the role of knee bearing designs. Bone & Joint Journal, 95-B(11), 119-132. https://doi.org/10.1302/0301-620x.95b11.32835

Y. J. Choi & H. J. Ra. (2016). Patient satisfaction after total knee arthroplasty. Knee surgery Related. Research, 28(1), 1-15. https://doi.org/10.5792/ksrr.2016.28.1.1

R. O. Duda, P. E. Hart, & D. G. Stork. (2000). Pattern Classification (2nd ed.). 22-24, New York, NY: Wiley-Blackwell.

O. A. Galarranga, C. V. Vigneron, B. Dorizzi, N. Khouri, & E. Desailly. (2017). Predicting postoperative gait in cerebral palsy. Gait & posture, 52, 45-51. https://doi.org/10.1016/j.gaitpost.2016.11.012

E. S. Grood & W. J. Suntay. (1983). A joint coordinate system for the clinical description of three-dimensional motions: application to the knee. Journal of Biomechanical Engineering, 105(2), 136-144. https://doi.org/10.1115/1.3138397

M. Hasegawa, H. Takagita, & A. Sudo. (2015). Prediction of postoperative range of motion using intraoperative soft tissue balance in total knee arthroplasty with navigation. Computer Aided Surgery, 20(1), 47-51. https://doi.org/10.3109/10929088.2015.1076045

H. Hiroshi, A. Shaw, T. Tetsuya, K. Sugamoto, T. Yamazaki, & N. Shimizu. (2012). In vivo kinematic analysis of cruciate-retaining total knee arthroplasty during weight-bearing and non-weight-bearing deep knee bending. The Journal of Arthroplasty, 27(6), 1196-1202. https://doi.org/10.1016/j.arth.2012.01.017

B. M. Hossain, M. Nii, T. Morooka, M. Okuno, S. Yoshiya, & S. Kobashi. (2016). Post-operative implanted knee kinematics prediction in total knee arthroscopy using clinical big data. In Lecture notes in Computer Science, Springer, 9835(2), 405-412. https://doi.org/10.1007/978-3-319-43518-3_39

I. T. Jolliffe. (2002). Principal Component Analysis, 10-27, New York, NY: Springer-Verlag.

S. Kobashi, S. T. Tomosada, N. Shibanuma, M. Yamaguchi, M. Muratsu, K. Kondo, S. Yoshiya, and M. Kurosaka. (2005). Fuzzy image matching for pose recognition of occluded knee implants using fluoroscopy images. Journal of Advanced Computational Intelligence and Intelligent Informatics, 9(2), 181-195. https://doi.org/10.20965/jaciii.2005.p0181

Y. Z. Miao, X. P. Ma, & S. P. Bu. (2017). Research on the Learning Method Based on PCA-ELM. Intelligent Automation & Soft Computing. 23(4), 637-642. https://doi.org/10.1080/10798587.2017.1316071

McCullagh, P., and J. A. Nelder. "Generalized Linear Models." (1989): n. pag. Crossref. Web. https://doi.org/10.1007/978-1-4899-3242-6

Miller, R. G. (1974). The jackknife-a review. Biometrika, 61(1), 1-15.

D. W. Murray, G. S. MacLennan, S. Breeman, H. A. Dakin, L. Johnston, M. K. Campbell, and A. M. Gray, KAT group. (2014). A randomized controlled trial of the clinical effectiveness and cost-effectiveness of different knee prostheses: the knee arthroplasty trial (KAT). Health Technology 352 Assessment., 18(19), 1-235, vii-viii. https://doi.org/10.3310/hta18190

S. V. Onsem, V. D. Straeten, N. Arnout, P. Deprez, G. Damme, & J. Victoe. (2016). A new prediction model for patient satisfaction after Total Knee Arthroplasty. Journal of Arthroplasty, 31(12), 2660-2667. https://doi.org/10.1016/j.arth.2016.06.004

R Core Team (2016). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. K. Tei, N. Shibanuma, S. Kubo, T. Matsumoto, A. Matsumoto, H. Tateishi, M. Kurosaka, and R. Kuroda. (2012). Kinematic analysis of mobile-bearing total knee arthroplasty using image matching technique. Journal of Bone & Joint Surgery Br, 94, 242.

J.A. Reinbolt, M. D. Fox, M. H. Schwartz, & S. L. Delp. (2009). Predicting outcomes of rectus femoris transfer surgery. Gait & posture, 30(1), 100-105. https://doi.org/10.1016/j.gaitpost.2009.03.008

J. K. Seon, J. K. Park, M. S. Jeong, W. B. Jung, K. S. Park, T. R. Yoon, & E. K. Song. (2011). Correlation between preoperative and postoperative knee kinematics in total knee arthroplasty using cruciate retaining designs. International Orthopaedics, 35, 515-520. https://doi.org/10.1007/s00264-010-1029-1

M. Sridevi, P. Prakasam, S. Kumaravel, & P. Madhavsarma. (2017). Tibia Fracture Healing Prediction Using Adaptive Neuro Fuzzy Inference System. Intelligent Automation & Soft Computing, 23(2), 359-363. https://doi.org/10.1080/10798587.2016.1231477

Tomaru, Akitomo et al. "A 3-DOF Knee Joint Angle Measurement System with Inertial and Magnetic Sensors." 2010 IEEE International Conference on Systems, Man and Cybernetics (2010): n. pag. Crossref. Web. https://doi.org/10.1109/ICSMC.2010.5642420

J. Victor, J. K. Mueller, R. D. Komistek, A. Sharma, M.C. Nadaud, & J. Bellemans. (2010). In vivo kinematics after a cruciate-substituting TKA. Clinical Orthopaedics Related Research, 468(3), 807-814. https://doi.org/10.1007/s11999-009-1072-7

T. Yamazaki, T. Watanabe, Y. Nakajima K. Sugamoto, T. Tomita, H. Yoshikawa, & S. Tamura. (2004). Improvement of depth position in 2-D/3-D Registration of knee implants using single-plane fluoroscopy. IEEE Transactions Medical Imaging, 23(5), 602-612. https://doi.org/10.1109/TMI.2004.826051

S. Yoshiya, N. Matsui, R.D. Komistek, D. A. Dennis, M. Mahfouz, & M. Kurosaka. (2005). In vivo kinematic comparison of posterior cruciate-retaining and posterior stabilized total knee arthroplasties under passive and weight-bearing conditions. Journal of Arthroplasty, 20(6), 777-83. https://doi.org/10.1016/j.arth.2004.11.012

JOURNAL INFORMATION


ISSN PRINT: 1079-8587
ISSN ONLINE: 2326-005X
DOI PREFIX: 10.31209
10.1080/10798587 with T&F
IMPACT FACTOR: 0.652 (2017/2018)
Journal: 1995-Present




CONTACT INFORMATION


TSI Press
18015 Bullis Hill
San Antonio, TX 78258 USA
PH: 210 479 1022
FAX: 210 479 1048
EMAIL: tsiepress@gmail.com
WEB: http://www.wacong.org/tsi/