Machine Learning to Predict Incident Radiographic Knee Osteoarthritis Over 8 Years using Combined MR Imaging Features, Demographics, And Clinical Factors: Data from the Osteoarthritis Initiative

2021 ◽  
Author(s):  
Gabby B. Joseph ◽  
Charles E. McCulloch ◽  
Michael C. Nevitt ◽  
Thomas M. Link ◽  
Jae Ho Sohn
Keyword(s):  
Machine Learning ◽  
Mr Imaging ◽  
Knee Osteoarthritis ◽  
Imaging Features ◽  
Clinical Factors ◽  
Osteoarthritis Initiative ◽  
Radiographic Knee Osteoarthritis

scholarly journals Radiogenomics of Glioblastoma: Machine Learning–based Classification of Molecular Characteristics by Using Multiparametric and Multiregional MR Imaging Features

Radiology ◽  
2016 ◽  
Vol 281 (3) ◽  
pp. 907-918 ◽  
Author(s):  
Philipp Kickingereder ◽  
David Bonekamp ◽  
Martha Nowosielski ◽  
Annekathrin Kratz ◽  
Martin Sill ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mr Imaging ◽  
Molecular Characteristics ◽  
Imaging Features

scholarly journals Two biomarkers improve the diagnosis of pre-radiographic knee osteoarthritis: data from the osteoarthritis initiative

2020 ◽  
Vol 28 ◽  
pp. S336
Author(s):  
M. Camacho-Encina ◽  
V. Balboa-Barreiro ◽  
I. Rego-Pérez ◽  
R. Paz-González ◽  
V. Calamia ◽  
...  
Keyword(s):  
Knee Osteoarthritis ◽  
Osteoarthritis Initiative ◽  
Radiographic Knee Osteoarthritis

scholarly journals Early T2 changes predict onset of radiographic knee osteoarthritis: data from the osteoarthritis initiative

2014 ◽  
Vol 74 (7) ◽  
pp. 1353-1359 ◽  
Author(s):  
Hans Liebl ◽  
Gabby Joseph ◽  
Michael C Nevitt ◽  
Nathan Singh ◽  
Ursula Heilmeier ◽  
...  
Keyword(s):  
Relaxation Time ◽  
Knee Osteoarthritis ◽  
Case Control ◽  
T2 Relaxation Time ◽  
T2 Relaxation ◽  
Knee Oa ◽  
Osteoarthritis Initiative ◽  
Nested Case Control ◽  
Radiographic Knee Osteoarthritis

ObjectiveTo evaluate whether T2 relaxation time measurements obtained at 3 T MRI predict the onset of radiographic knee osteoarthritis (OA).Materials and methodsWe performed a nested case–control study of incident radiographic knee OA in the Osteoarthritis Initiative cohort. Cases were 50 knees with baseline Kellgren–Lawrence (KL) grade of 0 that developed KL grade of 2 or more over a 4-year period. Controls were 80 knees with KL grade of 0 after 4 years of follow-up. Baseline T2 relaxation time measurements and laminar analysis of T2 in deep and superficial layers were performed in all knee compartments. The association of T2 values with incident OA was assessed with logistic regression and differences in T2 values by case–control status with linear regression, adjusting for age, sex, body mass index (BMI) and other covariates.ResultsBaseline T2 values in all compartments except the medial tibia were significantly higher in knees that developed OA compared with controls and were particularly elevated in the superficial cartilage layers in all compartments. There was an increased likelihood of incident knee OA associated with higher baseline T2 values, particularly in the patella, adjusted OR per 1 SD increase in T2 (3.37 (95% CI 1.72 to 6.62)), but also in the medial femur (1.90 (1.07 to 3.39)), lateral femur (2.17 (1.11 to 4.25)) and lateral tibia (2.23 (1.16 to 4.31)).ConclusionsThese findings suggest that T2 values assessed when radiographic changes are not yet apparent may be useful in predicting the development of radiological tibiofemoral OA.

Sign in / Sign up

Export Citation Format

Share Document