Radiomics involves extracting quantitative features from medical images, resulting in high-dimensional data. Unsupervised clustering has been used to discover patterns in radiomic features, potentially yielding hidden biological insights. However, its effectiveness depends on the selection of dimensionality reduction techniques, clustering methods, and hyperparameter optimization, an area with limited exploration in the literature. We present a novel bootstrapping-based hyperparameter search approach to optimize clustering efficacy, treating dimensionality reduction and clustering as a connected process chain. The hyperparameter search was guided by the Adjusted Rand Index (ARI) and Davies–Bouldin Index (DBI) within a bootstrapping framework of 100 iterations. The cluster assignments were generated through 10-fold cross-validation, and a grid search strategy was used to explore hyperparameter combinations. We evaluated ten unsupervised learning pipelines using both simulation studies and real-world radiomics data derived from multiphase CT images of renal cell carcinoma. In simulations, we found that Non-negative Matrix Factorization (NMF) and Spectral Clustering outperformed the traditional Principal Component Analysis (PCA)-based approach. The best-performing pipeline (NMF followed by K-means clustering) successfully identified all three simulated clusters, achieving a Cramér’s V of 0.9. The simulation also established a reference framework for understanding the concordance patterns among different pipelines under varying strengths of clustering effects. High concordance reflects strong clustering. In the real-world data application, we observed a moderate clustering effect, which aligned with the weak associations to clinical outcomes, as indicated by the highest AUROC of 0.63.

Centers for Medicare & Medicaid Services (CMS) Overall Hospital Quality Star Ratings provide public hospital quality metrics, yet may not fully account for community-level social risk factors affecting patient outcomes. This cross-sectional study of 2,348 US acute care hospitals investigated the association between CMS Overall Hospital Quality Star Ratings and hospital performance on measures of community commitment, defined by the Lown Institute's inclusivity and community benefit metrics. Data came from the CMS July 2024 Hospital General Information and Lown Institute Hospital Index for Social Responsibility datasets. Lown Institute inclusivity, reflecting demographic alignment between a hospital's patient population and its surrounding community, and community benefit, reflecting selected hospital financial measures related to service to and support for vulnerable populations, were used as hospital-level proxies for community commitment. Kendall's τb partial correlations showed that higher star ratings were weakly associated with worse hospital ranks for the Lown Institute's inclusivity (partial τ_b = 0.145, 99.9% confidence interval [CI] 0.100-0.190) and community benefit metrics (partial τ_b = 0.181, 99.9% CI 0.136-0.226). Ratings were also inversely associated with inclusivity subscores and Medicaid revenue share. Higher CMS star ratings demonstrated weak inverse associations with hospital-level measures of community commitment related to service to and support for vulnerable communities. These findings suggest current CMS star ratings may incompletely account for the social risk profile of the populations that hospitals serve, although the modest magnitude of the associations warrants cautious interpretation. To ensure that quality ratings accurately reflect quality of care, policymakers may consider enhancing adjustment for the social risk factors present in the communities that hospitals serve.