Cancer therapies have substantially improved survival outcomes, yet cancer therapy-related cardiovascular toxicity (CTR-CVT) remains a major concern, with approximately one in four anticancer drugs carrying cardiac or vascular safety warnings. Since current monitoring relies on periodic hospital-based assessments, transient or progressively evolving cardiovascular alterations often escape timely detection. Within the context of COMPASS (Cardio-Oncology Multidisciplinary Patient Assistance Solution), an EU Innovative Health Initiative (IHI) project (Grant Agreement No. 101253264), this extended abstract explores continuous wearable sensing in real-world environments as a complementary paradigm for early detection of CTR-CVT. After reviewing the clinical indicators most relevant to longitudinal monitoring, we survey the corresponding wearable modalities together with their typical accuracy ranges and metrological limitations, including measurement uncertainty, partial coverage of existing validation standards, and regulatory fragmentation. Within COMPASS, wearable-derived signals are integrated with imaging, blood biomarkers, and electronic health records into uncertainty-aware AI-based clinical decision support systems, enabling personalized and timely cardio-oncology care. We finally outline emerging research directions (including synthetic sensing, generative AI for data augmentation, and federated learning) toward reliable, patient-centered continuous monitoring frameworks.
Wearable Monitoring for Early Cardiotoxicity Detection in Cancer Patients: The COMPASS Vision
Barbuto V.
;Savaglio C.;Gravina R.
2026-01-01
Abstract
Cancer therapies have substantially improved survival outcomes, yet cancer therapy-related cardiovascular toxicity (CTR-CVT) remains a major concern, with approximately one in four anticancer drugs carrying cardiac or vascular safety warnings. Since current monitoring relies on periodic hospital-based assessments, transient or progressively evolving cardiovascular alterations often escape timely detection. Within the context of COMPASS (Cardio-Oncology Multidisciplinary Patient Assistance Solution), an EU Innovative Health Initiative (IHI) project (Grant Agreement No. 101253264), this extended abstract explores continuous wearable sensing in real-world environments as a complementary paradigm for early detection of CTR-CVT. After reviewing the clinical indicators most relevant to longitudinal monitoring, we survey the corresponding wearable modalities together with their typical accuracy ranges and metrological limitations, including measurement uncertainty, partial coverage of existing validation standards, and regulatory fragmentation. Within COMPASS, wearable-derived signals are integrated with imaging, blood biomarkers, and electronic health records into uncertainty-aware AI-based clinical decision support systems, enabling personalized and timely cardio-oncology care. We finally outline emerging research directions (including synthetic sensing, generative AI for data augmentation, and federated learning) toward reliable, patient-centered continuous monitoring frameworks.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


