Health Research Projects

Mechanistic Data-Driven Forecasting Anticipating Epidemic Transitions 

Dramatic changes in the dynamics of complex systems occur with significant consequences. Such an unexpected change is usually undesirable and notably difficult to predict since models of complex systems are usually not accurate enough to predict reliably where and when critical thresholds may occur. A model-free data-driven method that can quantitatively predict critical transitions and their consequences for large dimensional nonlinear systems would have a significant impact in a variety of fields, from public health to complex climate systems. 

In this research, we develop data-driven algorithms and machine learning techniques rooted in dynamical systems theory to evaluate the stability and resilience of dynamical systems and forecast the risk of critical transitions using a limited number of measurements. In particular, anticipating critical transitions in complex ecological and living systems is crucial, as it is often difficult to restore an ecological system to its pre-transition state once the transition occurs. The developed methods have introduced computationally efficient tools for nonlinear stability analysis and resilient design in a variety of natural and engineered systems. 

Therapeutic Vibration Device 

Prolonged immobilization from a critical illness can result in significant muscle atrophy and neuromuscular weakness. Existing physical therapy protocols are costly and labor intensive, with understaffing of frontline nurses and caregivers often prevalent relative to patient needs. In collaboration with The Max Harry Weil Institute for Critical Care Research & Innovation and Emergency Medical Department at UM Hospital, a therapeutic vibration device has been designed, developed, and patented to address these problems. This device uses whole body vibration at a dosage based on patient’s comfort for 5-10 minutes of session a few times a day, seeking to mitigate ICU-acquired weakness and associated sequelae with passive participation from patients who can be sedated or immobile 

Patients are expected to spend less time in step-down units and skilled nursing rehabilitation facilities before going home thus further reducing readmissions, leading to reduced staff effort and overall cost.