Externally validated models for first diagnosis and risk of progression of knee osteoarthritis

Abstract

Objective We develop and externally validate two models for use with radiological knee osteoarthritis. They consist of a diagnostic model for KOA and a prognostic model of time to onset of KOA. Model development and optimisation used data from the Osteoarthritis initiative (OAI) and external validation for both models was by application to data from the Multicenter Osteoarthritis Study (MOST). Materials and methods The diagnostic model at first presentation comprises subjects in the OAI with and without KOA (n = 2006), modelling with multivariate logistic regression. The prognostic sample involves 5-year follow-up of subjects presenting without clinical KOA (n = 1155), with modelling with Cox regression. In both instances the models used training data sets of n = 1353 and 1002 subjects and optimisation used test data sets of n = 1354 and 1003. The external validation data sets for the diagnostic and prognostic models comprised n = 2006 and n = 1155 subjects respectively. Results The classification performance of the diagnostic model on the test data has an AUC of 0.748 (0.721–0.774) and 0.670 (0.631–0.708) in external validation. The survival model has concordance scores for the OAI test set of 0.74 (0.7325–0.7439) and in external validation 0.72 (0.7190–0.7373). The survival approach stratified the population into two risk cohorts. The separation between the cohorts remains when the model is applied to the validation data. Discussion The models produced are interpretable with app interfaces that implement nomograms. The apps may be used for stratification and for patient education over the impact of modifiable risk factors. The externally validated results, by application to data from a substantial prospective observational study, show the robustness of models for likelihood of presenting with KOA at an initial assessment based on risk factors identified by the OAI protocol and stratification of risk for developing KOA in the next five years. Conclusion Modelling clinical KOA from OAI data validates well for the MOST data set. Both risk models identified key factors for differentiation of the target population from commonly available variables. With this analysis there is potential to improve clinical management of patients.

From past to future: Bibliometric analysis of global research productivity on nomogram (2000–2021)

“…Over time, nomogram is no longer limited to the study of oncology, but more applied to the study of diagnosis and prediction of non-tumor-related diseases. For example, nomograms were used to analyze the correlation between factors in genomics or proteomics and the development and progression of diseases ( 32 – 34 ); Nomograms were used to predict adverse outcomes in obstetrics or reproductive medicine ( 35 – 38 ); it can also be combined with radiomics to analyze the relationship between different image features or image segmentation factors and disease diagnosis ( 39 , 40 ), predict chronic disease incidence in orthopedics ( 41 – 43 ), or analyze and detect the incidence of chronic diseases combined with metabolomics ( 37 ). In addition, the display modes of nomogram are gradually diversified.…”

Radiographic imaging-based joint degradation detection using deep learning

“…On 21 risk indicators, the best random forest (RF) classifier model had 73.55% classification accuracy. Two verified radiographic knee OA models were suggested by McCabe et al [29]. The diagnostic and prognostic model of KOA onset time was added.…”