Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: 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
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