Predictive Phenotyping in Cardio-Oncology: Advancing Prevention and Survivorship

Recent advances in cardio-oncology have underscored the importance of precise, individualized risk assessment for patients at risk of cardiovascular complications due to cancer therapy. While cancer survivorship rates continue to improve, the cardiotoxic effects of cancer treatments remain a significant concern, with late-onset cardiac events posing an ongoing threat even years after completion of therapy. Despite the availability of pre-treatment risk models and emerging data-driven approaches, current strategies often fall short in guiding timely interventions, resource allocation, and equitable care delivery across diverse patient populations.Efforts to enhance patient outcomes have given rise to longitudinal survivorship clinics, dynamic risk stratification tools, and pragmatic artificial intelligence (AI) solutions designed to inform clinical decision-making, such as when to deploy echo or MRI imaging. Key studies have demonstrated the potential of integrating AI and advanced phenotyping algorithms into routine care, yielding early signals of improved prediction accuracy and pathway optimization. However, notable gaps persist, including limited generalizability of predictive models, insufficient representation of diverse populations, and barriers to wide-scale implementation due to resource constraints and infrastructure disparities.This Research Topic aims to advance the field of predictive phenotyping in cardio-oncology by fostering research that refines pre-treatment risk modeling, promotes dynamic survivor risk assessment, and leverages AI to optimize clinical pathways and policy. It seeks to address how best to align novel predictive tools with real-world care delivery, ensuring transportability, equity, and practical utility for clinicians and policymakers. Specifically, we are interested in research that explores the intersection of predictive analytics, clinical workflow integration, and implementation science in achieving better patient outcomes.To gather further insights in predictive phenotyping for cardio-oncology prevention and survivorship, this Research Topic is limited to models, tools, and strategies with demonstrable clinical relevance and translatable policy value. We welcome articles addressing, but not limited to, the following themes:o Development and validation of pre-treatment risk models to guide cardio-protective interventions.o Implementation and outcomes from longitudinal survivorship clinics using dynamic risk stratification.o Pragmatic use of AI for optimizing imaging and diagnostics in clinical care pathways.o Strategies for ensuring equity, inclusivity, and transportability of predictive models across diverse populations.o Best practices and barriers in implementation science for effective policy uptake and scaling of novel tools.Appendix: Acceptable article types include original research, reviews, perspectives, policy briefs, and implementation science studies. Topic editors: Arinze Nkemdirim Okere, Agnes S Kim Source: https://www.frontiersin.org/research-topics/74970/predictive-phenotyping-in-cardio-oncology-advancing-prevention-and-survivorship