Majid Afshar

Majid Afshar is an Associate Professor in the Division of Pulmonary and Critical Care Medicine at the University of Wisconsin–Madison's Department of Medicine. He leads the ICU Data Science Lab, focusing on AI-driven solutions for critical care and clinical decision support. His research integrates machine learning, natural language processing (NLP), and electronic health records (EHR) to improve outcomes in areas like clinical deterioration prediction, substance use disorder identification, and personalized treatment planning.

Key research themes include multimodal deep learning models for early detection of critical events, large language model applications in healthcare documentation and bias detection, and development of diagnostic tools for infection and opioid use. He has pioneered the use of AI digital twins for medication prediction in ICUs and created validated clinical prediction scores like eCARTv5 for early warning systems. His work emphasizes real-world implementation, including EHR-integrated AI tools for opioid risk screening and patient message response automation.

Awards and recognitions are not explicitly listed in the provided text. However, his contributions to TRIPOD-LLM reporting guidelines for large language models highlight his leadership in AI ethics and methodological rigor. Collaborative projects involve multi-center validations and partnerships with state agencies for substance misuse data dashboards. His lab actively develops tools to reduce healthcare disparities and improve clinical workflows through NLP and machine learning.