Construction of Digital Twin Model for Acute Ischemic Stroke Patients and Its Application in Disease Management

This research created and tested a digital twin model system for patients with acute ischemic stroke (AIS). The study was conducted in three comprehensive stroke units and included 200 patients with AIS, followed for one year. The model incorporates AI algorithms to optimize treatment strategies via continuous pain monitoring and real-time integration of multimodal neuroimaging and clinical data. Findings included improvements when compared to standard care for patient outcomes using a digital twin guided approach: The proportion of patients who made good functional recovery (mRS≤2) on day 90 after the stroke increased by 16.2 percentage points (with 95% credibility interval, CI: 12.7-19.7% p<0.001) whereas in-hospital mortality risk was reduced by a 35% (relative risk ratio 0.65, 95% CI: 0.52-0.81, p<0.001). The ability of the model to predict the progression of the disease was also good attaining ROC AUC of 0.89 (95% CI: 0.85-0.93). The system had great integration capabilities as the average latency time was only 87ms and 98.5% data capture completeness. This work confirms the important value of digital twin technology in managing acute stroke patient and it also opens new avenues for achieving personalized medicine. This technology offers improvements in healthcare delivery by enabling data-driven continuous decision support for patient care during hospital admission.