June 26, 2026
Amanda Randles was invited to present at the 2nd Advancing Autonomous Scientific Discovery (A2SD) Workshop during the ISC High Performance Conference (ISC 2026) in Hamburg, Germany.
Her presentation, "Chronophysiomics: Autonomous Discovery Through Longitudinal Digital Twins," explores a vision for combining wearable sensor data, medical imaging, electronic health records, and physics-based blood flow simulations to construct patient-specific cardiovascular digital twins that capture physiological changes across millions of heartbeats.
The talk highlights recent advances in scalable computational methods that make longitudinal digital twins feasible on today's heterogeneous high-performance computing systems. These developments enable continuous reconstruction of cardiovascular physiology at unprecedented temporal resolution while leveraging AI to accelerate computation and extract clinically meaningful insights.
Looking beyond digital twin construction, the presentation discussed how these technologies can serve as the computational foundation for autonomous scientific discovery. By integrating data-driven learning with mechanistic modeling, longitudinal digital twins have the potential to continuously learn from new data, reason through underlying physiology, and support predictive, personalized, and proactive healthcare.
The A2SD Workshop brings together researchers working at the intersection of artificial intelligence, automation, and scientific computing to explore how autonomous scientific ecosystems can transform research across disciplines. The workshop provided an opportunity to discuss emerging directions in AI-enabled scientific discovery and the role of trustworthy computational models in next-generation healthcare.