Presented By: Student AIM Seminar - Department of Mathematics
Student AIM Seminar: From Signals to Signatures: Mathematical Approaches to Modeling the Human Stress Response + Casual Networking Mixer
Aditya Jalin
The increasing adoption of wearable devices in healthcare presents unique opportunities and analytical challenges for applied mathematics. This talk will explore two interconnected research directions in digital health monitoring: analyzing physiological adaptation in bone marrow transplant (BMT) patients and developing mathematical frameworks for stress detection.
In the first part, we'll examine methods for quantifying physiological acclimatization in BMT patients using continuous heart rate, activity, and sleep data. We'll discuss the mathematical challenges in processing high-dimensional, temporally-correlated physiological signals and approaches for detecting significant changes during vs post engraftment period.
The second part will introduce our novel MOXIE (MultimOdal eXploration of psychological challenges in Interactive Environments) study, which aims to characterize individual stress signatures through multiple biophysiological signals. We'll explore planned approaches for integrating diverse data streams - from continuous physiological monitoring to ecological momentary assessments to video and blood samples. Special attention will be given to emerging computational frameworks, including applications of Long Short-Term Memory networks for temporal pattern recognition, self-attention mechanisms for capturing long-range dependencies in stress responses, and state-space models for efficient sequence modeling. We'll discuss how these advanced architectures might help bridge the gap between traditional time series analysis and the inherent complexity of mind-body interactions.
The talk will conclude by exploring how these mathematical frameworks could advance our understanding of psychoneuroimmunology in cancer patients. We'll discuss the potential impact on developing targeted interventions to improve survival outcomes, particularly in understanding how psychological stress influences immune function and disease progression in cancer patients. This work aims to bridge the gap between computational modeling and personalized clinical interventions in oncology.
Casual Networking Mixer:
Graduate students, postdocs, and faculty, especially those working in Applied Math are invited to a casual networking mixer after the talk. Foods and drinks will be provided.
In the first part, we'll examine methods for quantifying physiological acclimatization in BMT patients using continuous heart rate, activity, and sleep data. We'll discuss the mathematical challenges in processing high-dimensional, temporally-correlated physiological signals and approaches for detecting significant changes during vs post engraftment period.
The second part will introduce our novel MOXIE (MultimOdal eXploration of psychological challenges in Interactive Environments) study, which aims to characterize individual stress signatures through multiple biophysiological signals. We'll explore planned approaches for integrating diverse data streams - from continuous physiological monitoring to ecological momentary assessments to video and blood samples. Special attention will be given to emerging computational frameworks, including applications of Long Short-Term Memory networks for temporal pattern recognition, self-attention mechanisms for capturing long-range dependencies in stress responses, and state-space models for efficient sequence modeling. We'll discuss how these advanced architectures might help bridge the gap between traditional time series analysis and the inherent complexity of mind-body interactions.
The talk will conclude by exploring how these mathematical frameworks could advance our understanding of psychoneuroimmunology in cancer patients. We'll discuss the potential impact on developing targeted interventions to improve survival outcomes, particularly in understanding how psychological stress influences immune function and disease progression in cancer patients. This work aims to bridge the gap between computational modeling and personalized clinical interventions in oncology.
Casual Networking Mixer:
Graduate students, postdocs, and faculty, especially those working in Applied Math are invited to a casual networking mixer after the talk. Foods and drinks will be provided.
Related Links
Co-Sponsored By
Explore Similar Events
-
Loading Similar Events...
