Investigating how generative models and large language models can support healthcare professionals, patients, and healthcare organizations.
Research topics include clinical applications, administrative support, patient engagement, medical knowledge processing, and healthcare resource optimization.
Studying how intelligent systems fail, how anomalies can be detected, and how AI systems can become more robust and reliable.
One recent research direction from the group specifically addresses AI failures and anomalies.
Developing methods for understanding and evaluating large language models, with an emphasis on transparency, reliability, and human-centered explanations.
This research is particularly important for healthcare applications where AI-generated results must be interpretable and trustworthy.
Exploring machine learning and reinforcement learning approaches for intelligent clinical and healthcare decision-making.
Developing NLP and language-model-based methods for extracting information, analyzing documents, and assisting users in domain-specific environments.
Investigating the use of large language models and reinforcement learning for financial market analysis and decision-making.
Explainable Large Language Models in Healthcare Applications
Springer, 2026
TinyGuard:A lightweight Byzantine Defense for Resource-Constrained Federated Learning via Statistical Update Fingerprints
WWW, 2026
SketchSA Enables Communication-Efficient Secure Aggregation with Shared-Coordinate Compression
Springer, 2026
Advancements in Reinforcement Learning for Clinical Decision-Making: A Systematic Review
2026
A Survey on LLM-Enhanced Reinforcement Learning in Financial Markets
2026
Improving Effort-Aware Defect Prediction Using Machine Learning Methods
2026
Developing a BERT-Enhanced Blockchain Model for Health Insurance Fraud Detection
2025
Application of Generative AI in Healthcare Systems
Edited by Azadeh Zamanifar and Miad Faezipour.
Springer, 2025.
Dr. Azadeh Zamanifar — Google Scholar
Dr. Amirfarhad Farhadi — Google Scholar