Metraipolis › archive › dc_d709e59e420e
TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment — arXiv:2608.30857
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30857
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:55:01.227Z
- SHA-256 of the archived text
5b0be1cf13ec3a5351fdac7b1ff7fbaa7a684068849595c5662154b11be398df- Stable URL of this page
https://metraipolis.com/documento/dc_d709e59e420e
How to cite
TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment — arXiv:2608.30857 — arXiv (en), https://arxiv.org/abs/2608.30857 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d709e59e420e (Metraipolis archive dc_d709e59e420e, sha256 5b0be1cf13ec3a5351fdac7b1ff7fbaa7a684068849595c5662154b11be398df)
BibTeX
@misc{dcd709e59e420e,
title = {TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment — arXiv:2608.30857},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30857},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d709e59e420e; sha256 5b0be1cf13ec3a5351fdac7b1ff7fbaa7a684068849595c5662154b11be398df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30857. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Depression and anxiety in older adults with Mild Cognitive Impairment (MCI) are frequently underdiagnosed due to limited access to care. Multimodal analysis of remote clinical interviews is a scalable screening approach, but existing methods have three limitations. First, they do not correct temporal misalignment across multimodal features extracted at different resolutions, inducing spurious cross-modal associations. Second, remote recordings exhibit uneven modality dropout, but missing values are often zero-filled, making them indistinguishable from valid near-zero measurements. Finally, they do not jointly attribute predictions to modalities, questions, and interview moments, limiting fine-grained clinical interpretation. We propose a Temporally-Aligned, Missingness-Aware, Interpretable (TAMI) multimodal fusion framework. TAMI aligns speech, language, facial, and physiological features within question-answer segments on a shared timeline, encodes modality-level missingness over time, and conditions fusion on question context. In interviews with 49 older adults with MCI, TAMI achieved area under the receiver operating characteristic curve (AUROC) scores of 0.68 (depression) and 0.69 (anxiety). Fine-grained temporal alignment of multimodal features produced the largest performance gain ($\Delta{\geq}0.1$). Multi-level interpretability analysis revealed that depression classification relied on eyegaze and open-ended questions, while anxiety classification depended on eyegaze and head pose, with attribution uniformly distributed across questions. Using only responses to the open-ended questions (5.1min), the depression model achieved an AUROC score of 0.67, which was not significantly different from using the full interview (19min) ($p>0.05$). Our findings support designing interview protocols centered on open-ended questions for depression screening in older adults with MCI.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.30857 — 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 2026-10-17T07:28:26.916Z 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).