Knee osteoarthritis (KOA) diagnosis is based on symptoms, assessed through questionnaires such as the WOMAC. However, the inconsistency of pain recording and the discrepancy between joint phenotype and symptoms highlight the need for objective biomarkers in KOA diagnosis. To this end, we study relationships among clinical and molecular data in a cohort of women (n=51) with Kellgren-Lawrence grade 2–3 KOA through Support Vector Machine (SVM) and a regulation network model (RNM). Clinical descriptors (i.e., pain catastrophism (CA); depression (DE); functionality (FU); joint pain (JP); rigidity (RI); sensitization (SE); synovitis (SY)) are used to classify patients. A Youden's test is performed for each classifier to determine optimal binarization thresholds for the descriptors. Thresholds are tested against patient stratification according to baseline WOMAC data from the Osteoarthritis Initiative, and the mean accuracy is 0.97. For our cohort, the data used as SVM inputs are KOA descriptors, synovial fluid (SL) proteomic measurements (n=25), and transcription factors (TF) activation obtained from RNM [2] stimulated with the SL measurements. The relative weights after classification reflect input importance. The performance of each classifier is evaluated through AUC-ROC analysis. The best classifier with clinical data is CA (AUC = 0.9), highly influenced by FU and SE, suggesting that kinesophobia is involved in pain perception. With SL input, leptin strongly influences every classifier, suggesting the importance of low-grade inflammation. When TF are used, the mean AUC is limited to 0.608, which can be related to the pleomorphic behaviour of osteoarthritic chondrocytes. Nevertheless, FU has an AUC of 0.7 with strong importance of FOXO downregulation. Though larger and longitudinal cohorts are needed, this unique combination of SVM and RNM shall help to map objectively KOA descriptors.
This study investigates the relationships between Intervertebral Disc (IVD) morphology and biomechanics using patient-specific (PS) finite element (FE) models and poromechanical simulations. 169 3D lumbar IVD shapes from the European project MySpine (FP7-269909), spanning healthy to Pfirrmann grade 4 degeneration, were obtained from MRIs. A Bayesian Coherent Point Drift algorithm aligned meshes to a previously validated structural FE mesh of the IVD. After mesh quality analyses and Hausdorff distance measurements, mechanical simulations were performed: 8 and 16 hours of sleep and daytime, respectively, applying 0.11 and 0.54 MPa of pressure on the upper cartilage endplate (CEP). Simulation results were extracted from the anterior (ATZ) and posterior regions (PTZ) and the center of the nucleus pulposus (CNP). Data mining was performed using Linear Regression, Support Vector Machine, and eXtreme Gradient Boosting techniques. Mechanical variables of interest in DD, such as pore fluid velocity (FLVEL), water content, and swelling pressure, were examined. The morphological variables of the simulated discs were used as input features. Local morphological variables significantly impacted the local mechanical response. The local disc heights, respectively in the mid (mh), anterior (ah), and posterior (ph) regions, were key factors in general. Additionally, fluid transport, reflected by FLVEL, was greatly influenced (r2 0.69) by the shape of the upper and lower cartilage endplates (CEPs). This study suggests that disc morphology affects Mechanical variables of interest in DD. Attention should be paid to the antero-posterior distribution and local effects of disc heights. Surprisingly, the CEP morphology remotely affected the fluid transport in NP volumes around mid-height, and mechanobiological implications shall be explored. In conclusion, patient-specific IVD modeling has strong potential to unravel important correlations between IVD phenotypes and local tissue regulation.
