Objective: Osteoarthritis (OA) is typically studied in isolated joints, but humans are interconnected systems. This raises the question of how multi-joint OA manifests, and whether it forms a distinct subgroup. This study aimed to investigate whether individuals with OA worsening in both the hip and the knee exhibit unique clinical, structural, or demographic characteristics compared to those with isolated OA worsening or no worsening. Design: We conducted a retrospective analysis using data from the Osteoarthritis Initiative, including 1958 participants with radiographic assessments of hip and knee joints at baseline and 48-month follow-up. Participants were categorized into four groups based on joint space narrowing: no worsening, hip-only worsening, knee-only worsening, or combined worsening in 48 months. Univariate comparisons and multivariate logistic regression analyses were performed to compare the combined worsening group to the other groups. Results: Combined worsening occurred in 12.5% of participants. Compared to those with no worsening, the combined worsening group had more severe baseline radiographic knee OA (aOR: 1.38 (1.15–1.64)). Compared to hip-only OA worsening, the combined group had more severe knee OA (aOR: 1.36 (1.11–1.67)). Compared to those with knee-only OA worsening, combined OA worsening was associated with female sex (aOR: 1.92 (1.31–2.76)). Conclusions: Our findings show differences between individuals with combined or isolated OA worsening, which may reflect accumulation of single-joint risk factors rather than a distinct trajectory. This research provides a foundation for large-scale investigations into multi-joint OA subtypes to improve patient stratification and inform targeted interventions.

The gap between predicted brain age using magnetic resonance imaging (MRI) and chronological age may serve as a biomarker for early-stage neurodegeneration. However, owing to the lack of large longitudinal studies, it has been challenging to validate this link. We aimed to investigate the utility of such a gap as a risk biomarker for incident dementia using a deep learning approach for predicting brain age based on MRI-derived gray matter (GM). We built a convolutional neural network (CNN) model to predict brain age trained on 3,688 dementia-free participants of the Rotterdam Study (mean age 66 ± 11 y, 55% women). Logistic regressions and Cox proportional hazards were used to assess the association of the age gap with incident dementia, adjusted for age, sex, intracranial volume, GM volume, hippocampal volume, white matter hyperintensities, years of education, and APOE ε4 allele carriership. Additionally, we computed the attention maps, which shows which regions are important for age prediction. Logistic regression and Cox proportional hazard models showed that the age gap was significantly related to incident dementia (odds ratio [OR] = 1.11 and 95% confidence intervals [CI] = 1.05-1.16; hazard ratio [HR] = 1.11, and 95% CI = 1.06-1.15, respectively). Attention maps indicated that GM density around the amygdala and hippocampi primarily drove the age estimation. We showed that the gap between predicted and chronological brain age is a biomarker, complimentary to those that are known, associated with risk of dementia, and could possibly be used for early-stage dementia risk screening.