Metraipolis › archive › dc_d308be0037fd
Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM — arXiv:2610.39464
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39464
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:13:17.314Z
- SHA-256 of the archived text
901ac1d3e4bdac9ad582f5b09a9b4aa1c5bfbb81ecd16ab1d55a5658723e4d06- Stable URL of this page
https://metraipolis.com/documento/dc_d308be0037fd
How to cite
Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM — arXiv:2610.39464 — arXiv (en), https://arxiv.org/abs/2610.39464 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d308be0037fd (Metraipolis archive dc_d308be0037fd, sha256 901ac1d3e4bdac9ad582f5b09a9b4aa1c5bfbb81ecd16ab1d55a5658723e4d06)
BibTeX
@misc{dcd308be0037fd,
title = {Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM — arXiv:2610.39464},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39464},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d308be0037fd; sha256 901ac1d3e4bdac9ad582f5b09a9b4aa1c5bfbb81ecd16ab1d55a5658723e4d06},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39464. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
View- and target-specific echocardiography AI models capture useful but complementary information and may not achieve sufficient predictive performance in isolation. A learned ensemble is a natural way to combine these outputs, but heterogeneous models typically require each output to be converted into a binary decision, probability, confidence score, or fixed-length feature vector. We developed a supervised large language model (LLM)-based late-fusion module that directly aggregates view-specific predicted finding statements and predicted measurements in language space and learns a case-level fusion function. In patient-level three-fold cross-validation of 859 examinations from 646 patients, the proposed method integrated heterogeneous outputs within a single framework, performed comparably to the best-performing reference strategy evaluated, and outperformed a general-purpose LLM without task-specific training. These results suggest that a supervised LLM can combine multiple upstream models without model-specific output conversion or feature engineering that requires medical knowledge. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.39464 — 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 2026-10-31T06:07:08.719Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).