Скачать или смотреть The Critical Illness Digital Twin (CIDT):A NASEM-Compliant Digital Twins to Cure Sepsis Dr. Gary An

Sepsis remains one of the leading causes of death in intensive care units worldwide — and modern medicine still lacks effective molecular therapies to treat the underlying immune dysfunction. In this talk, Dr. Gary An presents a National Academies of Sciences, Engineering, and Medicine (NASEM)-compliant digital twin designed specifically to control and reverse critical illness through adaptive, personalized immune intervention.
Rather than relying on population averages, predictive AI, or static models, this approach treats sepsis as a dynamic control problem, integrating:
• mechanistic immune system modeling
• real-time biological sensing
• adaptive cyber-physical systems
• deep reinforcement learning
• closed-loop decision and intervention frameworks
This Critical Illness Digital Twin (CIDT) is not built to merely predict outcomes — it is designed to actively steer patient biology back toward health, using continuous model updating, uncertainty-aware control, and personalized immune modulation strategies.
The talk explores why traditional AI, clinical data analytics, and population-based precision medicine approaches fail in critical illness, and why only a true NASEM-compliant digital twin architecture can enable real-time, patient-specific therapy in diseases defined by heterogeneity, uncertainty, and biological complexity.
This is a vision of medicine that moves beyond prediction — toward control, adaptation, and cure.

If you found this video useful, please check out our other videos on computational modeling, infection and immunology:
Please consider joining our IMAG/MSM WG on Multiscale Modeling and Viral Pandemics: https://www.imagwiki.nibib.nih.gov/co...
Please also consider joining the Global Alliance for Immune Prediction and Intervention: http://glimprint.org/

#digitaltwins , #SepsisResearch, #criticalcare , #computationalimmunology,
#precisionmedicine, #medicalai , #systemsbiology , #healthcareinnovation , #aiinmedicine