Therapeutics and Clinical Risk Management

Circulating Biomarkers and AI in Therapeutics and Clinical Risk Management: From Molecular Signals to Precision Medicine

Circulating biomarkers are increasingly reshaping the landscape of modern medicine by enabling minimally invasive, dynamic assessment of disease processes across diverse clinical settings. Among these, cell-free DNA (cfDNA) has emerged as a particularly versatile analyte, offering insights into tissue damage, clonal evolution, and therapeutic response in real time. Beyond its established role in oncology, cfDNA and related circulating markers are gaining traction in cardiovascular disease, transplantation monitoring, infectious diseases, and chronic inflammatory conditions, where early detection and longitudinal surveillance remain critical challenges. At the same time, the growing complexity and volume of biomarker-derived data have accelerated the integration of artificial intelligence (AI) and machine learning approaches, which enable more robust interpretation, risk prediction, and clinical decision support. Together, these advances are driving a shift toward data-informed, precision-based therapeutics and more proactive clinical risk management strategies.

This topic is particularly important because many current clinical paradigms still rely on static, late-stage indicators that fail to capture the dynamic and heterogeneous nature of disease progression. As a result, opportunities for early intervention, timely treatment adjustment, and precise risk stratification are often missed. Circulating biomarkers, especially when assessed longitudinally, offer a unique window into ongoing biological processes, enabling earlier detection of relapse, identification of therapeutic resistance, and more accurate monitoring of treatment efficacy. However, the clinical utility of these signals is frequently limited by their complexity and context dependency, which cannot be fully resolved through conventional analytical approaches alone. The integration of AI provides a critical solution by uncovering hidden patterns, modeling temporal changes, and combining multi-dimensional data into clinically actionable insights. Together, these advances have the potential to transform reactive healthcare models into proactive, predictive, and personalized systems.

This Collection will focus on the clinical application and translational potential of circulating biomarkers and AI in therapeutic decision-making and risk management across a range of disease settings. Particular emphasis will be placed on studies evaluating cfDNA and other liquid biopsy approaches for treatment monitoring, minimal residual disease detection, and early identification of therapeutic resistance, as well as biomarker-driven patient stratification and prognosis. Contributions exploring the integration of multi-omics data with clinical variables, imaging, and real-world datasets using AI-based models are especially encouraged, provided they demonstrate clear relevance to clinical practice. In line with the journal’s scope, submissions should prioritize clinical utility, validation, and implementation rather than purely exploratory analyses. We welcome original research articles, systematic reviews, and clinically oriented narrative reviews, as well as studies leveraging real-world evidence to inform therapeutic strategies and risk prediction in routine care settings.

Keywords:

• Circulating Biomarkers
• Cell-free DNA (cfDNA)
• Artificial Intelligence in Healthcare
• Precision Medicine
• Clinical Risk Stratification