E Halilaj1, Y Le2, J L Hicks3, T J Hastie2, S L Delp4. 1. Department of Bioengineering, Stanford University, USA. Electronic address: ehalilaj@stanford.edu. 2. Department of Statistics, Stanford University, USA. 3. Department of Bioengineering, Stanford University, USA. 4. Departments of Bioengineering, Mechanical Engineering, and Orthopaedic Surgery, Stanford University, USA.
Abstract
OBJECTIVE: The goal of this study was to model the longitudinal progression of knee osteoarthritis (OA) and build a prognostic tool that uses data collected in 1 year to predict disease progression over 8 years. DESIGN: To model OA progression, we used a mixed-effects mixture model and 8-year data from the Osteoarthritis Initiative (OAI)-specifically, joint space width measurements from X-rays and pain scores from the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) questionnaire. We included 1243 subjects who at enrollment were classified as being at high risk of developing OA based on age, body mass index (BMI), and medical and occupational histories. After clustering subjects based on radiographic and pain progression, we used clinical variables collected within the first year to build least absolute shrinkage and selection (LASSO) regression models for predicting the probabilities of belonging to each cluster. Areas under the receiver operating characteristic curve (AUC) represent predictive performance on held-out data. RESULTS: Based on joint space narrowing, subjects clustered as progressing or non-progressing. Based on pain scores, they clustered as stable, improving, or worsening. Radiographic progression could be predicted with high accuracy (AUC = .86) using data from two visits spanning 1 year, whereas pain progression could be predicted with high accuracy (AUC = .95) using data from a single visit. Joint space narrowing and pain progression were not associated. CONCLUSION: Statistical models for characterizing and predicting OA progression promise to improve clinical trial design and OA prevention efforts in the future.
OBJECTIVE: The goal of this study was to model the longitudinal progression of knee osteoarthritis (OA) and build a prognostic tool that uses data collected in 1 year to predict disease progression over 8 years. DESIGN: To model OA progression, we used a mixed-effects mixture model and 8-year data from the Osteoarthritis Initiative (OAI)-specifically, joint space width measurements from X-rays and pain scores from the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) questionnaire. We included 1243 subjects who at enrollment were classified as being at high risk of developing OA based on age, body mass index (BMI), and medical and occupational histories. After clustering subjects based on radiographic and pain progression, we used clinical variables collected within the first year to build least absolute shrinkage and selection (LASSO) regression models for predicting the probabilities of belonging to each cluster. Areas under the receiver operating characteristic curve (AUC) represent predictive performance on held-out data. RESULTS: Based on joint space narrowing, subjects clustered as progressing or non-progressing. Based on pain scores, they clustered as stable, improving, or worsening. Radiographic progression could be predicted with high accuracy (AUC = .86) using data from two visits spanning 1 year, whereas pain progression could be predicted with high accuracy (AUC = .95) using data from a single visit. Joint space narrowing and pain progression were not associated. CONCLUSION: Statistical models for characterizing and predicting OA progression promise to improve clinical trial design and OA prevention efforts in the future.
Authors: Janet Wesseling; Alex N Bastick; Saskia ten Wolde; Margreet Kloppenburg; Floris P J G Lafeber; Sita M A Bierma-Zeinstra; Johannes W J Bijlsma Journal: J Rheumatol Date: 2015-07-01 Impact factor: 4.666
Authors: A N Bastick; S P J Verkleij; J Damen; J Wesseling; W K H A Hilberdink; P J E Bindels; S M A Bierma-Zeinstra Journal: Osteoarthritis Cartilage Date: 2016-02-21 Impact factor: 6.576
Authors: David T Felson; Sara McLaughlin; Joyce Goggins; Michael P LaValley; M Elon Gale; Saara Totterman; Wei Li; Catherine Hill; Daniel Gale Journal: Ann Intern Med Date: 2003-09-02 Impact factor: 25.391
Authors: M Lethbridge-Cejku; W W Scott; R Reichle; W H Ettinger; A Zonderman; P Costa; C C Plato; J D Tobin; M C Hochberg Journal: Arthritis Care Res Date: 1995-09
Authors: J Wesseling; J Dekker; W B van den Berg; S M A Bierma-Zeinstra; M Boers; H A Cats; P Deckers; K J Gorter; P H T G Heuts; W K H A Hilberdink; M Kloppenburg; R G H H Nelissen; F G J Oosterveld; J C M Oostveen; L D Roorda; M A Viergever; S ten Wolde; F P J G Lafeber; J W J Bijlsma Journal: Ann Rheum Dis Date: 2008-09-04 Impact factor: 19.103
Authors: B Guan; F Liu; A Haj-Mirzaian; S Demehri; A Samsonov; T Neogi; A Guermazi; R Kijowski Journal: Osteoarthritis Cartilage Date: 2020-02-06 Impact factor: 6.576
Authors: David J Hunter; Leticia A Deveza; Jamie E Collins; Elena Losina; Jeffrey N Katz; Michael C Nevitt; John A Lynch; Frank W Roemer; Ali Guermazi; Michael A Bowes; Erik B Dam; Felix Eckstein; C Kent Kwoh; Steve Hoffmann; Virginia B Kraus Journal: Arthritis Care Res (Hoboken) Date: 2022-05-03 Impact factor: 5.178
Authors: Thomas A Perry; Xia Wang; Michael Nevitt; Christina Abdelshaheed; Nigel Arden; David J Hunter Journal: Rheumatology (Oxford) Date: 2021-10-02 Impact factor: 7.580