2 papers
cs.CL2026
CG-Probes: Recovering Guardrail Directions from Patient Query Embeddings
Marko Řeháček, Vítězslav Dušek, Martin Rusinko +1
Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncologists to define three ordin…
cs.LG2026
Computing patient similarity based on unstructured clinical notes
Petr Zelina, Marko Řeháček, Jana Halámková +3
Clinical notes hold rich yet unstructured details about diagnoses, treatments, and outcomes that are vital to precision medicine but hard to exploit at scale. We introduce a method…