MIT CSAIL MEDG

Our Missions

We focus on the urgent and critical nature of decision-making in diverse applications. Our methods include improving the gathering, availability, security, and use of information throughout the organization and beyond—supporting decisions and information use across diverse settings and boundaries.

Some of our recent work includes establishing a scalable informatics framework and implementing tools and techniques to "understand" text from data. We use natural language processing to extract meaningful information from narratives that capture most professional observations, and we apply a variety of machine learning techniques—including LLMs, deep learning, matrix and tensor factorization, Gaussian processes, support vector machines, conditional random fields, logistic regression, Bayesian models, random forests, and reinforcement learning—adapted to the characteristics of each application.