Giovanna Guidoboni, University of Missouri
Authors: Giovanna Guidoboni, James Keller, Chris Wikle, Erin Robinson, Robert Nunez, Daphne Zou, Rajat Rai, Aaron Beckwith, Maggie Lin, Alice Chandra Verticchio Vercellin, Brent Siesky, Alon Harris
2022 AWM Research Symposium
Mathematical Modeling of the Eye: A Window to Our Health

Artificial Intelligence (AI) aims at extracting information and knowledge from data. AI is naturally interdisciplinary, as it bridges fundamental techniques of data analysis, typically developed by mathematicians, statisticians and computer scientists, with the needs of actionable insights that are specific to the particular application domain. Mechanism-driven models are based on the principles of physics and physiology and allow for identification of cause-to-effect relationships among interplaying factors in a complex system. While invaluable for causality, mechanism-driven models are often based on simplifying assumptions to make them tractable for analysis and simulation; however, this often brings into question their relevance beyond theoretical explorations. Data-driven models offer a natural remedy to address these short-comings. Data-driven methods may be supervised (based on labeled training data) or unsupervised (clustering and other data analytics) and they include models based on statistics, machine learning, deep learning and neural networks. Data-driven models naturally thrive on large datasets, making them scalable to a plethora of applications. While invaluable for scalability, data-driven models are often perceived as black- boxes, as their outcomes are difficult to explain in terms of fundamental principles of physics and physiology and this limits the delivery of actionable insights. The combination of mechanism-driven and data-driven models allows us to harness the advantages of both, as mechanism-driven models excel at interpretability but suffer from a lack of scalability, while data-driven models are excellent at scale but suffer in terms of generalizability and insights for hypothesis generation. This combined, integrative approach represents the pillar of the interdisciplinary approach to data science that will be discussed in this talk, with application to glaucoma research. Glaucoma is the leading cause of irreversible blindness worldwide. Unfortunately, poor understanding of glaucoma risk factors has constrained currently approved treatments to intraocular pressure (IOP) reduction. Other factors such as vascular health, specifically blood pressure (BP), are known to alter risk of glaucoma onset and progression. BP and IOP vary by person, with both high and low BP being associated with the disease process. In this talk, we will show how combining mechanism-driven and data-driven methods can help quantify the relative contribution of BP as a risk factor in combination with IOP for a given individual to advance glaucoma management.

Back to Search Research Symposium Abstracts