Beyond maximum grade: the role of real-world digital health technologies to capture, predict, and manage treatment toxicity in haematological cancers.

Abstract

Real-world data are essential for understanding treatment-related toxicities in haematology, but traditional analyses are limited by data access, sharing constraints, and reduced data granularity. Emerging digital health technologies (DHTs), such as electronic patient-reported outcomes and wearable devices, can be used to capture continuous, patient-generated data not reliably captured by current post-marketing toxicity assessments. Artificial intelligence, synthetic data, and digital twins can be used to predict and simulate toxicity at a much larger scale beyond the capacity of traditional methodologies. These emerging DHTs could overcome barriers, such as data fragmentation and lack of harmonisation, between existing real-world toxicity data sources. However, they also come with new challenges, including data quality and interpretability, integration into existing clinical workflows, privacy protection, and data governance. Developing and implementing them in partnership with patients, clinicians, payers, and regulators is necessary to maximise their impact in both individual patient and population-level clinical care.