Committee Chair

Gao, Lan

Committee Member

Barioli, Francesco; Le, Thien; Ma, Ziwei

Department

Dept. of Mathematics

College

College of Engineering and Computer Science

Publisher

University of Tennessee at Chattanooga

Place of Publication

Chattanooga (Tenn.)

Abstract

Rapid detection of large vessel occlusion (LVO) is critical due to its high mortality and narrow treatment window. Although machine learning (ML) and deep learning tools show promise for LVO prediction, their clinical use is hindered by inconsistent pre-hospital data, variable LVO rates, limited interpretability, and high costs. This study introduces a hybrid neural network (HNN) that integrates classical statistical learning with neural networks to combine interpretability and structure with flexibility and regularization. The model was validated through simulations using NIHSS scores, demographics, and medical history across diverse sample sizes and LVO prevalence rates, and benchmarked against logistic regression, Naive Bayes, Decision Tree, Random Forest, and standard neural networks using sensitivity, specificity, accuracy, PPV, NPV, AUC, and ROC metrics. When applied to a large multi-center dataset from over 100 hospitals, the HNN maintained consistent performance, with sampling methods improving data balance and SHAP analysis revealing key predictors. Across simulated and real-world data, the HNN improved sensitivity by at least 20% while sustaining strong overall accuracy, demonstrating its potential as an interpretable, scalable tool for pre-hospital LVO detection to enhance clinical decision-making and improve stroke outcomes.

Acknowledgments

I would like to thank the Department of Mathematics and the Graduate School at UTC for allowing me the opportunity to obtain my Ph.D. Thank you to all of the UTC Mathematics faculty that have taught and supported me throughout the years. I would like to acknowledge Dr. Devlin of CHI Memorial and Dr. Sevilis of TeleSpecialists for providing data, research opportunities, and funding. I would also like to thank Samuel Glandon for his help and support on various projects. Finally, special thanks to Dr. Gao for her help and wisdom as an advisor, whose statistics courses were the spark that ignited my interest in this field.

Degree

Ph. D.; A dissertation submitted to the faculty of the University of Tennessee at Chattanooga in partial fulfillment of the requirements of the degree of Doctor of Philosophy.

Date

12-2025

Subject

Cerebrovascular disease--Prevention--Statistical methods; Neural networks (Computer science); Predictive analytics

Keyword

statistical methods;machine learning methods;hybrid model;ensemble methods;LVO prediction

Document Type

Doctoral dissertations

DCMI Type

Text

Extent

xii, 101 leaves

Language

English

Rights

http://rightsstatements.org/vocab/InC/1.0/

License

http://creativecommons.org/licenses/by/4.0/

Download

Share

COinS