Literature DB >> 33749148

Machine learning-based individualized survival prediction model for total knee replacement in osteoarthritis: Data from the Osteoarthritis Initiative.

Afshin Jamshidi1,2, Jean-Pierre Pelletier1, Aurelie Labbe3, François Abram4, Johanne Martel-Pelletier1, Arnaud Droit2.   

Abstract

OBJECTIVE: By using machine learning (ML), our study aimed to build a model to predict risk and time to total knee replacement (TKR) of an osteoarthritic knee.
METHODS: Features were from OAI at baseline. Lasso's Cox identified the ten most important among 1107 features. The prognostic power of the selected features was assessed by Kaplan-Meier and applied to seven ML methods: Cox, DeepSurv, Random Forest, linear/kernel Support Vector Machine (SVM), and linear/neural Multi-Task Logistic Regression. As some of the ten features included similar X-ray measurements, we further looked at using the least features without compromising the accuracy of the model. Prediction performance was assessed by the concordance index (C-index), Brier score, and time-dependent area under the curve (AUC).
RESULTS: Identified features included X-rays, the MRI feature bone marrow lesions (BML) in medial condyle, hyaluronic acid injection, performance measure, medical history, and knee symptoms. The methodologies Cox, DeepSurv, and linear SVM demonstrated the highest accuracy (C-index, 0.85, Brier score 0.02, and AUC, 0.87). DeepSurv was chosen to build the prediction model to estimate the time to TKR for a given knee. Moreover, we were able to use only three features (C-index, 0.85, Brier score 0.02, and AUC, 0.86) including BML, KL grade and knee symptoms, to predict risk and time of a TKR event.
CONCLUSION: For the first time, using the OAI cohort, we developed a model to predict with high accuracy if and when a given osteoarthritic knee would require TKR and who would likely progress fast toward this event. This article is protected by copyright. All rights reserved.

Entities:  

Keywords:  X-ray; feature selection; machine learning; magnetic resonance imaging; osteoarthritis; prediction; survival analysis; total knee replacement

Year:  2021        PMID: 33749148     DOI: 10.1002/acr.24601

Source DB:  PubMed          Journal:  Arthritis Care Res (Hoboken)        ISSN: 2151-464X            Impact factor:   4.794


  3 in total

1.  The role of bone mineral density and cartilage volume to predict knee cartilage degeneration.

Authors:  Federica Kiyomi Ciliberti; Giuseppe Cesarelli; Lorena Guerrini; Arnar Evgeni Gunnarsson; Riccardo Forni; Romain Aubonnet; Marco Recenti; Deborah Jacob; Halldór Jónsson; Vincenzo Cangiano; Anna Sigríður Islind; Monica Gambacorta; Paolo Gargiulo
Journal:  Eur J Transl Myol       Date:  2022-06-28

Review 2.  Discovering Knee Osteoarthritis Imaging Features for Diagnosis and Prognosis: Review of Manual Imaging Grading and Machine Learning Approaches.

Authors:  Yun Xin Teoh; Khin Wee Lai; Juliana Usman; Siew Li Goh; Hamidreza Mohafez; Khairunnisa Hasikin; Pengjiang Qian; Yizhang Jiang; Yuanpeng Zhang; Samiappan Dhanalakshmi
Journal:  J Healthc Eng       Date:  2022-02-18       Impact factor: 2.682

3.  Editorial: One Step at a Time: Advances in Osteoarthritis.

Authors:  Ali Mobasheri; Troy N Trumble; Christopher R Byron
Journal:  Front Vet Sci       Date:  2021-07-16
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.