Who I am

A visionary AI/ML leader and founder of AICardioHealth, Inc., with 15+ years driving enterprise AI in healthcare. As CEO & Chief AI Officer, I pioneer ethical, scalable solutions like our Stacking Generative AI model for CVD prediction—achieving 98% accuracy and 0.993 ROC AUC, validated on 9 diverse datasets (up to 400K records, including CDC and Framingham). Holding a Ph.D. in Data Sciences (2024) and fresh from Harvard Medical School’s Healthcare Transformation program (2025), I blend hands-on coding (Python/PyTorch/Azure) with strategic execution to transform data into life-saving insights, targeting a $150B+ AI healthcare market.

What I do

As CEO of AICardioHealth, I lead the development of AI-powered tools revolutionizing CVD prevention—early detection, personalized risk stratification, and B2B integrations for insurers, telehealth, hospitals, and clinics. My work focuses on ethical AI for chronic diseases (CVD, diabetes, CKD), turning complex EHR data into actionable pathways that reduce hospitalizations by up to 80% and optimize claims. From prototyping (cvdstack.streamlit.app) to scaling, I bridge research and real-world impact, as published in IEEE (July 2025).

View my research publication
Download my published research paper (pdf)

How I do it

I combine traditional ML (RF/XGBoost), deep learning (CNN/GRU), and generative AI (GANs for bias reduction) with XAI (SHAP/LIME) for transparent, fair models—ensuring HIPAA/FDA compliance and outperforming baselines by 10-20% AUC. Through rigorous feature engineering, cross-validation on diverse datasets (e.g., Framingham’s 11,627 records), and HITL collaboration with cardiologists, I optimize for scalability (Azure/Snowflake) and ethical deployment, delivering 98% accuracy in real-world scenarios.

Learn more from my researches
Learn more from research on diabetes.

20

AI/ML/DL Researches

81

Machine Learning

31

Deep Learning

105

Completed Projects

Machine Learning

Machine Learning is a subset of artificial intelligence that focuses on building systems capable of learning from and adapting to data without explicit programming. It involves algorithms that identify patterns, make decisions, and improve over time through experience, enabling predictions and insights from complex datasets.

Deep Learning

Deep Learning is a specialized branch of machine learning that utilizes neural networks with multiple layers (deep neural networks) to model complex patterns and representations in data. It excels in processing large volumes of unstructured data, such as images, audio, and text, to achieve high levels of accuracy in tasks like classification and prediction.

© Howard Nguyen, PhD in Data Science. Huntington Beach, CA