The Breast Cancer Susceptibility Gene (BRCA)-associated tumors represent a constantly evolving and intriguing scenario in oncology, in which the availability of novel systemic treatment, mainly including the poly (ADP-ribose) polymerase (PARP) inhibitors, has enabled an improved survival benefit in clinical subgroups. The expanding regulatory approvals of PARP inhibitors have inevitably reshaped the clinical indications for BRCA testing, moving the BRCA1/2 profiling from the traditional and preventive workflows to therapeutic paths. Despite advances in technology and treatment, substantial limitations remain in current genetic and genomic tools for the detection of deleterious BRCA1/2 variants. Germline and tumor tissue testing provide only a snapshot of a patient’s disease, failing to capture the dynamic and longitudinal aspects of tumor clonal evolution. In this scenario, liquid biopsy (LB) profiling of BRCA1/2 genes, primarily as circulating tumor DNA, represents a highly active area of research potentially affecting many aspects of cancer screening, diagnosis, and monitoring in individuals who are carriers of BRCA1/2 deleterious variants. Beyond the attractive potential to surrogate the tumor tissue testing, to overcome the cancer spatial and temporal heterogeneity, and to monitor the tumor mutational profile over time, accurately detecting all clinically relevant BRCA genetic variants and epigenetic modifications using LB remains technically challenging.
L. Incorvaia, V. Gristina, F. Pepe et al.· ESMO Open· 0 citations
BACKGROUND
Enfortumab vedotin (EV) therapy for advanced urothelial carcinoma is limited by adverse events (AEs). Early identification of high-risk patients is needed. This proof-of-concept study evaluated whether machine learning (ML) with explainable AI (SHAP) could predict EV toxicities using real-world data.
RESEARCH DESIGN AND METHODS
Data from 542 patients (51 centers, 24 countries) were analyzed. Six outcomes were predicted including grade 3-4 AEs. Four ML algorithms were trained on an 80% split and tested on 20%. Performance was evaluated via standard metrics with SHAP for interpretability.
RESULTS
In this exploratory analyses, Random Forest achieved highest overall performance, yielding best AUC for diarrhea, severe AEs, and dose skipping. XGBoost led for cutaneous toxicity and diabetes; LASSO led for neuropathy (differences modest). Age was the most important associated variable, followed by prior immunotherapy and ECOG status. Liver metastases influenced diabetes and cutaneous toxicity; lung metastases impacted diarrhea, neuropathy, and skin toxicity. SHAP showed atezolizumab/nivolumab linked to lower cutaneous risk, and female sex to higher risk.
CONCLUSION
These preliminary, hypothesis-generating findings suggest ML may predict EV-related toxicities, but single train-test split, small event counts, and lack of external validation preclude clinical use. Prospective validation is essential.
K. Sridharan, Mattia Alberto Di Civita, G. Sivaramakrishnan et al.· Expert Review of Anticancer...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
