How Clinicians Think and What AI Can Learn From It

arXiv:2601.12547v2 Announce Type: replace Abstract: Clinical artificial intelligence increasingly builds high-dimensional representations of patients, yet every finite clinical model is an abstraction. The key question is not only how accurately a model predicts, but which distinctions need to be represented, at what resolution, for the decision at hand. We argue that purposive clinical AI should use decision-sufficient abstraction: model detail should be conditioned by the objective structure of the decision and limited by the evidence available to support that detail. We further argue that this objective structure should often be ordinal-first. The primitive objects are objective-threshold propositions that may recur at progressively finer levels. For example, mortality below 10 percent may appear early and mortality below 5 percent later. We formalize ordered threshold refinement, a set-valued decision relation, and threshold-sufficient abstraction. A model needs only enough resolution to preserve the survivor set induced by the thresholds reached so far. Once an earlier threshold resolves the choice, further refinement of later objectives has no decision value for that choice. When a potentially decisive threshold is unresolved, additional information or model complexity should be targeted to that threshold rather than added globally. The framework links clinical reasoning, model abstraction, causal inference, lexicographic optimization, constrained learning, and human-AI collaboration. Its central claim is that clinical AI should pursue purpose before fidelity, order before abstraction, and refinement until decision-sufficient rather than reality-complete.

Abstract:Clinical artificial intelligence increasingly builds high-dimensional representations of patients, yet every finite clinical model is an abstraction. The key question is not only how accurately a model predicts, but which distinctions need to be represented, at what resolution, for the decision at hand. We argue that purposive clinical AI should use decision-sufficient abstraction: model detail should be conditioned by the objective structure of the decision and limited by the evidence available to support that detail. We further argue that this objective structure should often be ordinal-first. The primitive objects are objective-threshold propositions that may recur at progressively finer levels. For example, mortality below 10 percent may appear early and mortality below 5 percent later. We formalize ordered threshold refinement, a set-valued decision relation, and threshold-sufficient abstraction. A model needs only enough resolution to preserve the survivor set induced by the thresholds reached so far. Once an earlier threshold resolves the choice, further refinement of later objectives has no decision value for that choice. When a potentially decisive threshold is unresolved, additional information or model complexity should be targeted to that threshold rather than added globally. The framework links clinical reasoning, model abstraction, causal inference, lexicographic optimization, constrained learning, and human-AI collaboration. Its central claim is that clinical AI should pursue purpose before fidelity, order before abstraction, and refinement until decision-sufficient rather than reality-complete.

Artificial Intelligence (cs.AI)

arXiv:2601.12547 [cs.AI]

(or arXiv:2601.12547v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2601.12547 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

How Clinicians Think and What AI Can Learn From It

Subiecte conexe