Research & Publications
Md. Mehedi Hassan is a Ph.D. researcher at Texas Tech University, working on World Models and AI-driven cardiovascular intelligence with the Causal Dynamics Lab — exploring causal reasoning, dynamic system modelling, and predictive AI for cardiovascular health.
His work bridges advanced AI research with real-time, industry-oriented applications: modelling cardiovascular dynamics, understanding how disease progresses, and supporting clinical decision-making.
He holds M.Sc. and B.Sc. degrees in Computer Science and Engineering and has authored peer-reviewed scientific publications (2,440+ citations, h-index 27), edited 8 scholarly books with premier publishers, and holds two granted patents. He serves as Associate Editor and Academic Editor across leading Q1/Q2 journals.
His Field-Weighted Citation Impact (SciVal) stands at 2.09 — within Scopus's top 1% of global impact — across 47 papers as first, lead, or corresponding author.
World Models & Causal Reasoning
World models of cardiovascular dynamics built with the Causal Dynamics Lab — causal reasoning and dynamic system modelling to trace how disease progresses and to support clinical decision-making in real time.
Cardiovascular Intelligence
Predictive AI for cardiovascular health, carrying advanced research through to industry-oriented applications that run against live clinical signals rather than retrospective datasets.
Volumetric Segmentation
3D U-Net & hybrid CNN–Transformer architectures for liver, brain lesion, and tumor segmentation from CT/MRI, optimized for Dice similarity and low inference latency.
Metabolic & Chronic Disease AI
Machine learning pipelines for early detection of diabetes, coronary artery disease, chronic kidney disease, and obesity-related conditions from clinical and imaging data.
Biomedical Signal AI
EEG-based epileptic seizure detection and emotion recognition; brain–computer interface systems combining CNN/LSTM architectures with explainable AI.
Federated & Privacy-Preserving Learning
Federated deep learning frameworks for multi-institution medical imaging, reducing data-sharing barriers across clinical sites.
Explainable AI
Grad-CAM, LIME, and interpretability frameworks for clinical trust — applied across monkeypox, breast cancer, and NLP-based diagnostic models.
Graph Neural Networks for the Brain
GNN-based modeling of brain connectomes and networks for neurological disorder classification and personalization.
109 Papers · 2,440+ Citations
Full bibliography sourced directly from author records — search by keyword or filter by type. Sorted by year, most recent first.
Selected High-Impact Work
Global burden of enteric & diarrhoeal diseases
The Lancet Infectious Diseases, 2026 — GBD 2023 Collaborators.
Crop damage classification via depth channel shuffling
Engineering Applications of AI (Elsevier), 2025.
FedVGM: Federated Learning on Multi-Dataset Medical Images
IEEE J. Biomedical & Health Informatics, 2025.
Coronary artery disease prediction with feature selection
Computers and Electrical Engineering (Elsevier), 2024.
NeuroNet19: explainable brain tumor classification (MRI)
Scientific Reports (Nature), 2024.
Efficient prediction of Water Quality Index (WQI)
Human-Centric Intelligent Systems (Springer), 2021.