Metraipolis › archive › dc_c544fc4b9548

INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction — arXiv:2608.29901

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29901
License (as archived)
CC0-1.0
Archived
2026-10-17T07:52:15.637Z
SHA-256 of the archived text
fd60a6093843feed44fa42db4f48f592827f06ee4cf5003668c6a16e40ddc227
Stable URL of this page
https://metraipolis.com/documento/dc_c544fc4b9548

How to cite

INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction — arXiv:2608.29901 — arXiv (en), https://arxiv.org/abs/2608.29901 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c544fc4b9548 (Metraipolis archive dc_c544fc4b9548, sha256 fd60a6093843feed44fa42db4f48f592827f06ee4cf5003668c6a16e40ddc227)
BibTeX
@misc{dcc544fc4b9548,
  title = {INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction — arXiv:2608.29901},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29901},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c544fc4b9548; sha256 fd60a6093843feed44fa42db4f48f592827f06ee4cf5003668c6a16e40ddc227},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29901. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Electronic Health Record (EHR) prediction models in the intensive care unit must learn from sparse and irregular measurements while preserving the clinical meaning of time and supporting transparent decision-making. We present INTERVenE, a family of Transformer architectures whose input is an interval-based, knowledge-based temporal abstraction (KBTA), a token stream of named clinical concepts (states, trends, events, contexts) drawn from a curated medical ontology, rather than an unnamed bin index or a raw measurement triplet. This naming layer is what we ask KBTA to do: it makes the model's per-token attributions resolve to clinical concepts by construction. INTERVenE offers two complementary variants: an auto-regressive decoder that generates future abstraction trajectories with a per-step risk readout (localizing \emph{when} and \emph{after which events} risk rises), and a bidirectional encoder for single-pass joint risk and time-to-event prediction. On 57,078 MIMIC-IV admissions, INTERVenE-Enc outperformed GRU-D, STraTS, and KarmaLego, reaching a support-weighted AUPRC of 0.672 ($+0.046$ over the strongest neural baseline, with non-overlapping 95\% bootstrap CIs), AUROC of 0.901, and length-of-stay MAE of 44.4\,h. INTERVenE-Ar complements these predictions with generated abstraction trajectories and evolving risk scores, achieving AUROC of 0.854 and AUPRC of 0.588 under the harder generative readout. An alternative-discretization ablation preserved predictive performance, supporting KBTA's role as a clinically named attribution substrate rather than a prerequisite for accuracy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.29901 — 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 2026-10-17T07:28:26.800Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).