Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910067559759872 |
|---|---|
| author | Liu, Sheng Chen, Long Zhao, Zeyun Gou, Qinglin Wei, Qingyue Masurkar, Arjun Spiegler, Kevin M. Kuball, Philip Bray, Stefania C. Bernath, Megan Willis, Deanna R. Bian, Jiang Xing, Lei Topol, Eric Cho, Kyunghyun Huang, Yu Fang, Ruogu Razavian, Narges Zou, James |
| author_facet | Liu, Sheng Chen, Long Zhao, Zeyun Gou, Qinglin Wei, Qingyue Masurkar, Arjun Spiegler, Kevin M. Kuball, Philip Bray, Stefania C. Bernath, Megan Willis, Deanna R. Bian, Jiang Xing, Lei Topol, Eric Cho, Kyunghyun Huang, Yu Fang, Ruogu Razavian, Narges Zou, James |
| contents | Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment Liu, Sheng Chen, Long Zhao, Zeyun Gou, Qinglin Wei, Qingyue Masurkar, Arjun Spiegler, Kevin M. Kuball, Philip Bray, Stefania C. Bernath, Megan Willis, Deanna R. Bian, Jiang Xing, Lei Topol, Eric Cho, Kyunghyun Huang, Yu Fang, Ruogu Razavian, Narges Zou, James Artificial Intelligence Computer Vision and Pattern Recognition Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care. |
| title | Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.21597 |