Digital Twins in stroke and spreading depression
Introduction Multiscale modeling (MSM) permits us to better understand how ischemia and spreading depolarization (SD) together damage neurons. However, it is a long step from there to producing clinical tools to counter or prevent stroke. Such tools must include clinical data from neurology and cardiology, endocrinology and other clinical specialties, as well as from other biomedical sciences, and must engage with body sensors (data integrators -DIs -for sensor information consolidation) and with the patient him or herself. We are developing digital twins (DTs) to incorporate these elements to extend personalized care. DTs will incorporate MSMs and DIs with large language models (LLMs) to communicate with the patient and with clinicians. Methods We have developed LLM to interact with patients and now combine them with our MSMs that include neural and vascular elements. MSM simulates and constrains detailed reaction-diffusion, electrophysiology, circuit models. LLM correlates literature and simulation details to identify simulation boundaries. Results LLMs structured patient information by free-form interviewing. 3 trials/46 cases; GPT-4; 1e5 tokens/min showed consistent results for hemisphere stroke (F1 0.9) and cord (0.94) strokes, worse for brainstem (0.8) or cerebellar stroke (0.37) Using MSM, tissue scale simulations showed interpretable spreading depression signature, worsening with degree of hypoxia. Our reaction--diffusion--electrophysiology MSMs showed changes in altered activation network dynamics. Data assimilation was implemented using "functional avatar" principles, including MRI-derived structural and diffusion features, perfusion proxies and oxygenation-related signals, electrophysiology signatures, pathology/autopsy findings to provide approximate capillary densities. Discussion DT medical personalization can help distinguish multiscale parameters, enabling patient-specific predictions and suggest therapy testing. Pairing of MSM detailed models with LLMs allows ingesting large electronic medical record (EMR) and archival research text to structured knowledge, further augmented with DI access to personal (digital watch and monitors) and clinical tools. Brain ischemia is a bridge disease since mutli-organ (cardiac, brain, vessel, lung); detailed clinical correlates and preventive strategies. microscale; multi-physics; multi-specialty: neurology, vascular, cardiac, endocrine. Acknowledgments Supported by NIH R01MH086638