Background Post-treatment Lyme disease syndrome (PTLDS) and rheumatoid arthritis (RA) are both characterized by chronic inflammation and immune dysregulation; however, whether they share underlying molecular immune mechanisms remains unclear. Methods Peripheral blood mononuclear cell (PBMC) transcriptomic datasets from the GEO database were analyzed to identify common differentially expressed genes (DEGs) between PTLDS and RA. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were subsequently performed. Feature genes were screened using least absolute shrinkage and selection operator (LASSO) regression and support vector machine-recursive feature elimination (SVM-RFE) machine learning algorithms. Gene set enrichment analysis (GSEA) and xCell analysis were conducted to characterize signaling pathway features and immune cell infiltration patterns in both diseases. In addition, prediction-based ceRNA regulatory network analysis and drug association analysis were performed as exploratory components. Results A total of 44 common DEGs were identified, which were primarily enriched in neutrophil chemotaxis, complement activation, and immune-inflammatory processes. Machine learning analysis ultimately identified ZNF83 as the feature gene. GSEA revealed that both diseases were associated with innate immune-related pathways and immunoregulatory processes and exhibited certain similarities in immune cell composition. ZNF83 showed preliminary discrimination between disease and control samples in both PTLDS and RA (AUC = 0.934 and 0.765, respectively), although these estimates require validation in larger independent cohorts. Furthermore, DSigDB analysis suggested potential associations between ZNF83 and several candidate therapeutic compounds. Conclusion PTLDS and RA share certain common features at the level of immune-inflammatory regulation, and ZNF83 may serve as a potential feature regulatory molecule involved in the immune processes of both diseases. This study provides new insights into the immunopathological mechanisms of PTLDS and its relationship with autoimmune diseases.
Yantong Chen, Xingui Guo, Xinyuan Xu et al.· Frontiers in Immunology· 0 citations
Background Prediction models are central to advancing precision oncology, yet many fail to translate into clinical practice due to methodological flaws and inadequate validation. This review provides a practical, clinician-oriented guide to the statistical principles and advanced methods for developing, validating, and interpreting robust prediction models. Methods This narrative review used a targeted literature search of PubMed, Embase, and Web of Science to identify methodological papers, reporting guidelines, and representative oncology prediction model studies, with a focus on literature published between January 1, 2005, and February 28, 2025. Landmark methodological papers published before 2005 were also included when directly relevant. Rather than performing a systematic review or meta-analysis, we synthesized key statistical principles and illustrative examples to guide clinicians and researchers through model development, validation, interpretation, and clinical translation. Findings A multifaceted evaluation encompassing discrimination, calibration, clinical utility, and external validation is essential for prediction models. Over-reliance on discrimination metrics such as the area under the receiver operating characteristic curve (AUC), while neglecting calibration and clinical utility, can lead to misleading conclusions about a model’s value. Rigorous external validation in geographically or temporally distinct cohorts is the most direct test of generalizability, and performance degradation should be interpreted through root-cause analysis rather than treated simply as model failure. Key challenges include managing overfitting, selecting appropriate modeling and validation strategies for different oncology scenarios, addressing special settings such as rare tumors and real-world data, and improving the interpretability of complex “black-box” models. Conclusion Building a trustworthy prediction model requires a combination of advanced computational methods and rigorous statistical principles. To bridge the gap from model development to clinical impact, researchers must prioritize comprehensive validation, transparent reporting, scenario-appropriate modeling decisions, and critical assessment of a model’s real-world utility.
Xuexing Wang, Youxian Dou, Yufeng Wang et al.· Frontiers in Oncology· 1 citation