Metraipolis › archive › dc_bbee4f89f9ee
Structured Clinical Memory as Context for Probabilistic Decision Models: A Synthetic Evaluation with Jev — arXiv:2611.04101
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04101
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:34:18.509Z
- SHA-256 of the archived text
048fc762551b43f5f4e6cf7ad01038b06b1d1c623373f59902e4ddc5ba408c80- Stable URL of this page
https://metraipolis.com/documento/dc_bbee4f89f9ee
How to cite
Structured Clinical Memory as Context for Probabilistic Decision Models: A Synthetic Evaluation with Jev — arXiv:2611.04101 — arXiv (en), https://arxiv.org/abs/2611.04101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbee4f89f9ee (Metraipolis archive dc_bbee4f89f9ee, sha256 048fc762551b43f5f4e6cf7ad01038b06b1d1c623373f59902e4ddc5ba408c80)
BibTeX
@misc{dcbbee4f89f9ee,
title = {Structured Clinical Memory as Context for Probabilistic Decision Models: A Synthetic Evaluation with Jev — arXiv:2611.04101},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04101},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbee4f89f9ee; sha256 048fc762551b43f5f4e6cf7ad01038b06b1d1c623373f59902e4ddc5ba408c80},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Longitudinal clinical context is often distributed across noisy, repetitive forms and narrative records. We study whether a compact structured memory can improve a probabilistic decision model's answers when the underlying patient vignette is already available. We created 30 fully synthetic cases spanning twelve clinical domains, paired each with synthetically generated structured memory, and evaluated 120 typed questions with Jev. The raw-vignette arm achieved 90.0% accuracy (95% normal-approximation confidence interval: 84.6%-95.4%); adding memory achieved 93.3% (88.9%-97.8%). Five questions changed from incorrect to correct and one changed in the opposite direction (exact McNemar $p=0.219$). Choice log loss decreased from 0.258 to 0.175 and binary Brier score from 0.054 to 0.022. Memory added 310 input tokens per call on average, while observed mean latency was unchanged at approximately 0.5 seconds. These results are directionally positive rather than clinically validating: the cases are synthetic, the labels are single-author judgments, and the memory is an oracle upper bound rather than extracted production output. The pilot supports evaluating structured clinical memory as a reusable state interface for decision models. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04101 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T18:32:37.276Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).