The Potential of Digital Twins for Pediatric Rare Diseases

Abstract

Rare diseases affect over 300 million people globally, with approximately 75% manifesting in childhood. Their diagnosis is often delayed and approved treatments are lacking for most of the conditions. Pediatric rare diseases research is further complicated by ethical constraints and developmental diversity across childhood. Digital Twins, virtual representations of patients built from mechanistic and AI/ML models, offer a promising solution by enabling hypothesis testing, precision diagnostics, personalized therapies, and in silico trials for pediatric rare diseases. This article discusses the potential of DT applications in advancing precision medicine for pediatric rare diseases, alongside associated regulatory perspectives, modeling strategies, uncertainty analysis, as well as data, ethical and legal challenges.

Ähnliche Arbeiten