Healthcare System
Healthcare systems are undergoing a digital transformation driven by the need to improve efficiency, equity, and patient outcomes. Current research focuses on leveraging machine learning, particularly deep learning models (like Residual Networks and Transformers) and large language models (LLMs), to analyze diverse data sources (electronic health records, medical images, wearable sensor data) for predictive analytics, personalized interventions, and improved diagnostics. This work emphasizes addressing biases and ensuring fairness in algorithms, as well as enhancing data privacy and security through techniques like federated learning and data-free quantization. The ultimate goal is to create more efficient, equitable, and effective healthcare delivery systems through data-driven insights and AI-powered tools.
Papers
Sample Selection Bias in Machine Learning for Healthcare
Vinod Kumar Chauhan, Lei Clifton, Achille Salaün, Huiqi Yvonne Lu, Kim Branson, Patrick Schwab, Gaurav Nigam, David A. Clifton
Federated Hierarchical Tensor Networks: a Collaborative Learning Quantum AI-Driven Framework for Healthcare
Amandeep Singh Bhatia, David E. Bernal Neira