Verb-Based AI Paradigm Models Patient Trajectories from EHR Data

A new computer science paper introduces a verb-based modeling paradigm that redefines AI's ability to represent the future as an open temporal dimension. The framework, built on precise definitions of 'timing computation' and 'possibility', was applied to longitudinal electronic health record (EHR) data from 3,276 breast cancer patients. It achieved two data-driven results: automatic discovery of clinically significant patient trajectories and counterfactual timing deduction, both without prior domain knowledge. The authors claim these are the first such demonstrations in machine learning literature. The paper is available on arXiv.