Conventional inclusion criteria used in osteoarthritis clinical trials are not very effective in selecting patients who would benefit from a therapy being tested. Typically majority of selected patients show no or limited disease progression during a trial period. As a consequence, the effect of the tested treatment cannot be observed, and the efforts and resources invested in running the trial are not rewarded. This could be avoided, if selection criteria were more predictive of the future disease progression. In this article, we formulated the patient selection problem as a multi-class classification task, with classes based on clinically relevant measures of progression (over a time scale typical for clinical trials). Using data from two long-term knee osteoarthritis studies OAI and CHECK, we tested multiple algorithms and learning process configurations (including multi-classifier approaches, cost-sensitive learning, and feature selection), to identify the best performing machine learning models. We examined the behaviour of the best models, with respect to prediction errors and the impact of used features, to confirm their clinical relevance. We found that the model-based selection outperforms the conventional inclusion criteria, reducing by 20–25% the number of patients who show no progression. This result might lead to more efficient clinical trials.

Objective: To design an automated workflow for hip radiographs focused on joint shape and tests its prognostic value for future hip osteoarthritis. Design: We used baseline and 8-year follow-up data from 1,002 participants of the CHECK-study. The primary outcome was definite radiographic hip osteoarthritis (rHOA) (Kellgren–Lawrence grade ≥2 or joint replacement) at 8-year follow-up. We designed a method to automatically segment the hip joint from radiographs. Subsequently, we applied machine learning algorithms (elastic net with automated parameter optimization) to provide the Shape-Score, a single value describing the risk for future rHOA based solely on joint shape. We built and internally validated prediction models using baseline demographics, physical examination, and radiologists scores and tested the added prognostic value of the Shape-Score using Area-Under-the-Curve (AUC). Missing data was imputed by multiple imputation by chained equations. Only hips with pain in the corresponding leg were included. Results: 84% were female, mean age was 56 (±5.1) years, mean BMI 26.3 (±4.2). Of 1,044 hips with pain at baseline and complete follow-up, 143 showed radiographic osteoarthritis and 42 were replaced. 91.5% of the hips had follow-up data available. The Shape-Score was a significant predictor of rHOA (odds ratio per decimal increase 5.21, 95%-CI (3.74–7.24)). The prediction model using demographics, physical examination, and radiologists scores demonstrated an AUC of 0.795, 95%-CI (0.757–0.834). After addition of the Shape-Score the AUC rose to 0.864, 95%-CI (0.833–0.895). Conclusions: Our Shape-Score, automatically derived from radiographs using a novel machine learning workflow, may strongly improve risk prediction in hip osteoarthritis.

Objective Bioactive oxidised lipids (oxylipins) are important signalling mediators, capable of modulating the inflammatory state of the joint and anticipated to be of importance in joint homeostasis and status of osteoarthritis. The aim of this study was to quantify oxylipin levels in plasma and synovial fluid from rats with experimentally induced osteoarthritis to investigate the potential role of oxylipins as a marker in the disease process of early osteoarthritis. Design Forty rats were randomly allocated to a standard or high-fat diet group. After 12 weeks, local cartilage damage was induced in one knee joint in 14 rats of each diet group. The remaining 6 rats per group served as controls. At week 24, samples were collected. Oxylipin levels were quantified by liquid chromatography–mass spectrometry. Results Overall, 31 lipid-derived inflammatory mediators were detected in fasted plasma and synovial fluid. Principal component analysis identified four distinct clusters associated with histopathological changes. Diet induced differences were evident for 13 individual plasma oxylipins, as well as 5,6-EET in synovial fluid. Surgical-model induced differences were evident for three oxylipins in synovial fluid (15-HETE, 8,9-DHET and 17R-ResolvinD1) with a different response in lipid concentrations for synovial fluid and plasma. Conclusions We demonstrate the quantification of oxidised lipids in rat plasma and synovial fluid in a model of early experimental osteoarthritis. Oxylipins in the synovial fluid that were altered as.

consequence of the surgically induced osteoarthritis were not represented in the plasma. Our findings suggest differential roles of the oxylipins in the local versus peripheral compartment.

Objectives: There is sparse evidence for a relationship between cardiovascular disease (CVD) and osteoarthritis (OA). We investigated the association between incidence of arterial calcifications and incidence of radiographic knee and/or hip OA. Design: We used baseline and 8-year follow-up data of Cohort Hip and Cohort Knee (CHECK). Knees and hips were either Kellgren-Lawrence (KL) grade 0 or 1 at baseline. Arterial calcifications were scored on hip and knee radiographs using a four-grade scale. Scores were summed for patient-level analyses. To investigate incidence, participants with arterial calcifications at baseline or missing follow-up were excluded. Incident OA was defined per joint as KL ≥ 2 or prosthesis at year eight. The association between incidenct of arterial calcifications and incident OA was studied using mixed-effects logistic regression. Results: Of 763 participants included, 623 (82%) were women. Mean (sd) age was 56 (5.1) years, mean (sd) body mass index (BMI) 26.2 (4.1) kg/m². Arterial calcifications developed in 174 participants (283 joints). OA developed in 456 participants (778 joints). Sex modified the association between arterial calcification and OA. In women, incident arterial calcification around a joint was positively associated with incident OA in that joint (adjusted OR 2.51 (95% CI 1.57-4.03)). In men, no association was observed on joint-level, but at patient-level the arterial calcification sum score was negatively associated with incident OA (adjusted OR per point increase 0.70 (95% CI 0.54-0.90)) indicating a systemic effect. Conclusions: We observed sex-dependent associations between incident arterial calcification and incident radiographic knee and/or hip OA, which differs between joint- and patient-level.