Answers are grounded in this paper and cite their sources.
Systematic review and network meta-analysis projects efficacy for a cisplatin, erdafitinib, and epirubicin triplet in bladder cancer, highlighting a computational candidate for future trials.
Bladder cancer, primarily manifesting as urothelial carcinoma, is among the ten most prevalent cancers worldwide and is associated with significant morbidity and mortality. Its clinical course is often marked by high recurrence rates and, in advanced stages, aggressive local and distant spread. Despite a range of treatment options, including surgery, intravesical therapy, systemic chemotherapy, and immunotherapy, therapeutic success is frequently limited by tumor heterogeneity, drug resistance, and adverse effects. As a result, there is an urgent need for effective combination therapies that can target multiple oncogenic pathways, overcome resistance mechanisms, and improve both survival outcomes and long-term disease control. We conducted a systematic review following PRISMA guidelines and searched PubMed, Embase, Scopus, Web of Science, and Google Scholar through December 2025. Inclusion criteria comprised RCTs and observational studies evaluating drug efficacy in non-muscle-invasive or muscle-invasive bladder cancer. The process comprises three stages: first, Graph Convolutional Networks (GCNs) are employed to generate drug, protein, and protein embeddings from a comprehensive biomedical knowledge graph, with text-mined associations validated against physical protein interaction and patient genomic databases to mitigate publication bias. Second, natural language processing is applied to screen clinical trial literature related to the proposed drugs. Finally, a network meta-analysis (NMA) is performed to provide indirect statistical evaluation of the therapeutic efficacy of the suggested combinations, bridging the gap between the computational hypothesis and existing clinical evidence. The GCN prioritized the triplet Cisplatin + Erdafitinib + Epirubicin. To explore its potential clinical utility, we synthesized trial data from 42 clinical studies of individual and doublet components. Network modeling of these arms provided an exploratory mathematical projection for the hypothetical triplet, suggesting favorable relative effectiveness estimates that serve solely as a computational hypothesis requiring direct clinical trials. Integrating GCN-based knowledge graphs with systematic evidence synthesis can generate biologically grounded hypotheses for drug combinations in bladder cancer. Our results nominate Cisplatin + Erdafitinib + Epirubicin as a promising computational candidate for future experimental validation, specifically in the FGFR-altered subpopulation of bladder cancer, but prospective preclinical and clinical studies are needed to confirm efficacy and safety. However, this triple combination should be considered a computational hypothesis requiring rigorous preclinical validation, due to potential cardiotoxicity and nephrotoxicity concerns. Clinical implementation would necessitate intensive cardiac and renal monitoring.
No takes yet. Share an insight, caveat, or question.
Askari et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: