SCH: Ensemble Logic: A Formal Precision Phenotyping Framework for Cohort Discovery in Epilepsy

The University Of Texas Health Science Center At Houston, Houston TX

Investigators

Abstract

In medicine, a phenotype is a person's visible traits or behaviors, such as heart rhythm, brain activity, or signs of disease. Accurately describing these traits is important for making correct diagnoses and choosing the right treatment. But clinicians currently write descriptions of these traits in loose, unstructured text, which can create confusion and inconsistency. Two doctors might describe the same condition in different ways, making it harder to communicate clearly and to keep documented data reliable. This lack of clarity has real effects on health. To diagnose problems like heart or brain disorders, doctors often watch how signals in the body, such as an EKG (electrocardiogram) or EEG (electroencephalogram), change over time. If these changing patterns are not clearly defined, it becomes harder to detect disease early, track its course, or plan treatments tailored to each patient. This project tackles this issue by creating a better way to describe phenotypes. This research builds a new logical system, called Ensemble Logic, that allows clinicians to describe these patterns in a way that is clear, consistent, and easy for computers to understand. This logical system is meant to be both intuitive and flexible. It will be used to define and detect complex health conditions using structured rules that help improve patient care and value in healthcare data. This project has three main components: theoretical development to formulate Ensemble Logic and rigorously explore its expressive power and boundaries; translational work to convert the logic to practical tools usable by doctors and researchers; and experimental efforts using real brain signal data from epilepsy patients to test, refine, and validate these tools. If successful, this work will offer a robust, reliable way to describe dynamic biological signal patterns. It will support more precise diagnoses, enable better disease monitoring, and uncover new insights into how disorders present themselves. In the long term, this framework has the potential to help improve care for patients with epilepsy, heart conditions, and other complex diseases, while helping researchers extract meaningful patterns from large-scale health datasets. Ultimately, Ensemble Logic could serve as a foundational tool for analyzing a wide range of health data and for advancing research on human health. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.