Paper
A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment
Authors
Sheng Liu, Long Chen, Zeyun Zhao, Qinglin Gou, Qingyue Wei, Arjun Masurkar, Kevin M. Spiegler, Philip Kuball, Stefania C. Bray, Megan Bernath, Deanna R. Willis, Jiang Bian, Lei Xing, Eric Topol, Kyunghyun Cho, Yu Huang, Ruogu Fang, Narges Razavian, James Zou
Abstract
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.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.21597v1</id>\n <title>A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment</title>\n <updated>2026-03-23T05:46:45Z</updated>\n <link href='https://arxiv.org/abs/2603.21597v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.21597v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-23T05:46:45Z</published>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Sheng Liu</name>\n </author>\n <author>\n <name>Long Chen</name>\n </author>\n <author>\n <name>Zeyun Zhao</name>\n </author>\n <author>\n <name>Qinglin Gou</name>\n </author>\n <author>\n <name>Qingyue Wei</name>\n </author>\n <author>\n <name>Arjun Masurkar</name>\n </author>\n <author>\n <name>Kevin M. Spiegler</name>\n </author>\n <author>\n <name>Philip Kuball</name>\n </author>\n <author>\n <name>Stefania C. Bray</name>\n </author>\n <author>\n <name>Megan Bernath</name>\n </author>\n <author>\n <name>Deanna R. Willis</name>\n </author>\n <author>\n <name>Jiang Bian</name>\n </author>\n <author>\n <name>Lei Xing</name>\n </author>\n <author>\n <name>Eric Topol</name>\n </author>\n <author>\n <name>Kyunghyun Cho</name>\n </author>\n <author>\n <name>Yu Huang</name>\n </author>\n <author>\n <name>Ruogu Fang</name>\n </author>\n <author>\n <name>Narges Razavian</name>\n </author>\n <author>\n <name>James Zou</name>\n </author>\n </entry>"
}