CS PhD Dissertation Defense , Trusting Inekwe " Predictive and Causal Machine Learning Models of the Impact of Pandemics on Cardiovascular Disease Patient Biomarkers"

Trusting Inekwe

PhD Candidate

WPI - Computer Science Department 

Date: Monday, June 23, 2025,

Time:  12:00 p.m. to 2 :00 p.m.

Location: Fuller Labs 311

Committee members:

Advisor:  Prof. Emmanuel Agu, WPI – Computer Science Dept.

Prof. Dmitry Korkin, WPI – Computer Science Dept.

Prof. Chun-Kit Ngan, WPI – Computer Science Dept. and Data Science Program 

Prof. Andres Colubri, Genomics and Computational Biology UMass Medical School – External Committee member

 Abstract:

Pandemic-induced disruptions to routine healthcare and lifestyle changes in cardiovascular diseases (CVDs) patients triggered changes in critical CVD biomarkers (measurable parameters of the body that can indicate health or illness). Prior work has overlooked models for predicting these biomarker trajectories or modeling causality during pandemics. Utilizing a first-of-a-kind Electronic Health Record (EHR) dataset of 426,022 patient records treated at the UMass Memorial hospital before and during the Covid pandemic, this doctoral dissertation applied ML predictive and causal models of the COVID-19 pandemic’s impact on CVD patient biomarkers using three methodological approaches.  

The first, published in the flagship IEEE CHASE conference, explored traditional ML models on EHR data attributes, to predict the impact of the COVID-19 pandemic on CVD patient biomarker trajectories (BP,  LDLchol, HbA1c and BMI) and ML causal analysis exploring the Debiased ML for Difference-in-Differences approach.  Findings revealed limited predictive capacities of traditional DL models.

To address this limitation, the second thrust, published in the IEEE CHASE conference, applied Genetic Algorithm Neural Architecture Search (GA-NAS) to automate deep learning model design for CVD biomarker prediction. GA-NAS leverages evolutionary optimization to discover high-performing architectures and hyperparameters without expert intervention. This approach significantly improved predictive accuracy over traditional ML models. 

The final study developed a Multi-target Bayesian Transformer model (MBT-CB) for robust pandemic-induced CVD biomarker prediction. It captures biomarker interdependence and temporal dynamics via transformer attention and DeepMTR layers, while estimating uncertainty through Bayesian variational inference. MBT-CB outperformed prior models in both accuracy and reliability.

This research will advance predictive and causal modeling of pandemic impacts on CVD patients and facilitate tools for early detection of health deterioration, uncovering latent trends, and forecasting pandemic-induced health risks. Such tools could be utilized by healthcare professionals, epidemiologists, and public health policymakers for more informed decision-making and targeted interventions during pandemics.