Research
Dr. Shamsuddin's lab is dedicated to advancing machine learning and artificial intelligence to address pressing needs in healthcare and public health. The team focuses on developing models that support clinical decision-making, enhance diagnostic accuracy, and provide interpretable insights into complex medical data, tackling major challenges in healthcare informatics. By generating synthetic healthcare data and applying time series analysis, the lab improves predictive models, making them useful even in data-scarce environments—such as in early sepsis detection, hypertension management, and personalized medicine. The lab's bioinformatics and neuroinformatics projects explore genetic and neural biomarkers, leveraging machine learning for disease prediction and patient monitoring.
With a strong commitment to explainable AI, the lab designs frameworks to make machine learning models more transparent, particularly for clinical and policy applications where trust and interpretability are essential. The lab’s research extends to public health initiatives, using machine learning to understand health behaviors, develop substance abuse indices, and analyze policies related to chronic diseases and opioid use. Through this multifaceted approach, Dr. Shamsuddin’s lab not only advances machine learning techniques but also delivers actionable, data-driven solutions to improve health outcomes and support informed decision-making in healthcare and public health.
Currently, we’re excited about introducing Functional Explainable AI (fXAI) in our work, with two of our journal papers on this topic pending revision in Springer’s AI Perspectives & Advances and IEEE Pattern Recognition and Machine Learning. Stay tuned for more updates! If you are interested in knowing more about fXAI, please check out this page and send an email to: ileadlabml@gmail.com
My publication record can be found at: Google Scholar , ResearchGate
Below, you will find research focus organized first by subject area type, then by research methodology, and finally by application area. For questions on any specific publication, feel free to message me, and a member will respond as soon as possible.
Subject Area
Machine Learning and Artificial Intelligence
Data Science
Healthcare Informatics
Clinical Informatics
Bioinformatics
Neuroinformatics
Social Informatics
Public Health Informatics and Policy
Research Methodology
Neural Networks (Deep Learning)
Convolutional Neural Networks (CNNs)
Semi-Supervised Learning
Domain Adaptation Techniques
Synthetic Data Generation for Healthcare
Time Series Data Analysis
Virtual Patient Modeling
Model Interpretation Frameworks
Visualization and Functional Analysis of Machine Learning Models
Integrating Social and Behavioral Science with XAI
Predictive Modeling (e.g., for disease progression and risk factors)
Clustering and Classification Algorithms
Data Imbalance Solutions and Comparative Study of ML Techniques
Word Embeddings and NLP Techniques (e.g., Word2Vec for Policy Summarization)
Self-Organizing Maps (SOM) for State Health Policy Profiles
Multimodal Data Analysis
Application Area
Clinical Decision Support
Disease Prediction (e.g., Sepsis Detection, Hypertension Management)
Diagnostic Models for Improving Clinical Accuracy
Early Detection and Risk Prediction in Chronic Diseases
Bioinformatics and Biomarker Discovery
Genetic Biomarker Identification for Cancer (e.g., Glioblastoma)
Computational Analysis of Biological Processes (e.g., protein hinge joints, EEG for security)
Functional Analysis of Neuroimaging Data
Healthcare Policy and Public Health Informatics
Opioid and Substance Abuse Policy Analysis
Social Informatics for Public Health Intervention
Health Behavior Modeling and Social Data in Health
Education and STEM
Curriculum Development in Data Science and Machine Learning for Healthcare
Inclusive STEM Programs and Teaching AI to K-12 and Undergraduates
Research and Training Experiences for Teachers (RET) in Big Data and AI