Metraipolis › archive › dc_70055fb29efb

Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates — arXiv:2609.19865

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19865
License (as archived)
CC0-1.0
Archived
2026-10-10T04:08:46.734Z
SHA-256 of the archived text
6d188203442f95e84d4bde0d9868fcd1bc4c338e1d95bc0dbf113bb59dce7481
Stable URL of this page
https://metraipolis.com/documento/dc_70055fb29efb

How to cite

Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates — arXiv:2609.19865 — arXiv (en), https://arxiv.org/abs/2609.19865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70055fb29efb (Metraipolis archive dc_70055fb29efb, sha256 6d188203442f95e84d4bde0d9868fcd1bc4c338e1d95bc0dbf113bb59dce7481)
BibTeX
@misc{dc70055fb29efb,
  title = {Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates — arXiv:2609.19865},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19865},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70055fb29efb; sha256 6d188203442f95e84d4bde0d9868fcd1bc4c338e1d95bc0dbf113bb59dce7481},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Representation learning from medical code sequences in electronic health records and medical claims data has been successful in various clinical applications, such as those regarding disease prediction. However, significant challenges remain in extending this approach to the discovery of scientific hypotheses. One reason is that many existing BERT-based models fail to adequately capture the hierarchical structure of medical codes and the complex interactions between diagnoses and treatments. To address these limitations, we propose a new unified pre-training framework that explicitly integrates hierarchical sub-token aggregation, partial masking, and cross-reference mechanisms. The proposed model consistently outperformed existing methods on both pre-training objectives and downstream clinical event prediction tasks, including the onset of dementia and hospitalization. We also conducted an in silico drug repositioning case study targeting Alzheimer's disease. In the hypothesis generation step, our approach successfully rediscovered known promising drugs in a data-driven manner without relying on such external knowledge sources as the literature. Subsequently, in the hypothesis prioritization step, we introduced a Task-Adaptive Representation Approach to alleviate the over-encoding of historical prescription information within diagnostic vectors, enabling the robust prioritization of generated hypotheses. This study establishes an exploratory screening workflow for hypothesis generation and prioritization based on observational associations. Importantly, this framework is not intended to provide causal evidence, but rather to identify promising candidates for subsequent rigorous causal inference. Overall, this study demonstrates that domain-informed representation learning combined with task-adaptive representation control can enable a practical hypothesis discovery workflow.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19865 — 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 2026-10-10T03:48:18.295Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).