{"resourceId":"ucsf-addi-grip-alzheimers-ai-chatad-agentic-assistant-20261030","versions":[{"version":"external-58dda9bb001082f1ff4b98388a94703e7f5ca15e88008d374652b4a1563ab2b8","resource":{"id":"ucsf-addi-grip-alzheimers-ai-chatad-agentic-assistant-20261030","title":"UCSF labs and the Alzheimer's Disease Data Initiative plan AI risk models on UC health records and an agentic research assistant, ChatAD","organization":"UCSF Sirota Lab and NeuroAI Lab (Bakar Computational Health Sciences Institute, Fein Memory and Aging Center); Global Research & Imaging Platforms (GRIP), Alzheimer's Disease Data Initiative (ADDI)","sector":"Academic medical research and research data platforms","geography":"United States (California)","publishedAt":"30 October 2026 (UCSF NeuroAI Lab news)","publicationDate":"2026-10-30","eventDate":null,"sourceName":"UCSF NeuroAI Lab","sourceLabel":"UCSF NeuroAI Lab, \"New Collaboration with the Sirota Lab and GRIP (ADDI) to Advance AI for Alzheimer's Disease,\" 30 Oct 2026","sourceUrl":"https://neuroailab.ucsf.edu/blog/2026/10/30/addi-grip-collaboration","evidenceClass":"vendor-claim","outcomeClass":"emerging","topics":["developers-agents","data-security","knowledge-work"],"finding":"UCSF's Sirota Lab and NeuroAI Lab announced a collaboration with GRIP, part of ADDI, with two aims. First, integrate longitudinal electronic health records from across the University of California health system with multimodal Alzheimer's Disease Neuroimaging Initiative (ADNI) data to build AI models for earlier risk prediction and to study disease mechanisms. Second, develop AD Commons and ChatAD, including an agentic AI research assistant meant to help scientists discover datasets, navigate research resources and design studies in natural language. The post frames the goal as making tools, data and resources accessible to investigators worldwide. No funding, timeline, models or results are given.","sledRelevance":"Shows an academic research group pairing system-wide clinical records with an agentic assistant over shared research data, a pattern research offices and health-science IT will need to govern. The agent targets dataset discovery and study design, not just literature, which raises data-access and validation questions.","evidence":"Read the full post. It is a short announcement of intent; no methods, governance arrangements, funding or evaluation are described.","architectureImplications":"Linking UC-wide EHR data with ADNI multimodal data implies a controlled research data environment; the assistant sits over a data commons for discovery and study design.","governanceImplications":"Use of UC health system records for model development requires IRB and data-use approvals that the post does not describe.","securityPrivacyImplications":"Longitudinal patient records are highly sensitive; de-identification, access controls and what the agent can see are not described.","caveats":"Lab blog announcement of planned work, with no results. Clinical data and Alzheimer's focus overlap health services; included here for research data infrastructure and agentic research assistants. Transfer depends on access to comparable health-system data.","streamIds":["research"],"roles":{"sales":"Lead with governance of agentic assistants over sensitive research data. UCSF labs said on 30 October they will pair University of California health-record data with ADNI data for Alzheimer's risk models and build ChatAD, an agentic assistant to help scientists find datasets and design studies. Research and health-science leaders will face similar requests. Offer a bounded review of data-access and agent controls for one research commons. Do not claim accuracy or adoption; no results exist.","engineering":"Frame fit around an agent layered on a controlled research data commons. UCSF plans to link system-wide health records with multimodal ADNI data and expose datasets through a natural-language assistant. Prerequisites are de-identified or access-controlled data enclaves, dataset metadata good enough for retrieval, and logging of agent queries. Validate by testing whether the assistant returns only datasets a user is approved for and whether its study-design suggestions hold up under expert review.","delivery":"Treat delivery as research data governance plus agent rollout. Work covers data-use approvals, metadata curation, access controls, assistant testing and investigator onboarding. Ownership sits with the principal investigators and the data platform partner, with the IRB and health-system privacy office as gatekeepers. Acceptance criteria are proposals, such as expert-reviewed accuracy of dataset recommendations and zero unauthorized data exposures, not results UCSF reported."},"roleDetails":{"sales":{"customerProblem":"Research data for complex diseases is fragmented across clinical and imaging sources and hard for investigators to discover and combine.","stakeholders":["Vice chancellor for research","Health-science research IT director","IRB and privacy office","Principal investigators in neurology"],"discoveryQuestions":["Which research data commons do your investigators use today?","Who approves AI model development on health-system records?","Would an assistant be allowed to see restricted metadata?"],"valueHypothesis":"A governed assistant over curated research data may shorten dataset discovery and study planning, if access controls hold.","potentialEngagement":"A review of data-access and agent controls for one research data commons.","unsupportedClaims":["Prediction accuracy","Faster discovery","Safe handling of patient data by the agent"]},"engineering":{"fit":"Fits academic medical centers with curated research datasets and a secure data environment.","architectureIntegration":"Natural-language agent over a data commons, linked to access-controlled enclaves holding EHR and imaging data.","prerequisites":["Access-controlled data enclave","Rich dataset metadata","Agent query logging"],"constraints":["Patient privacy and IRB rules","Health-system data-use agreements","No published methods"],"security":"Restrict the agent to metadata and approved datasets per user, and log every query and result.","proofOfValue":["Test that the agent respects user permissions","Expert review of study-design suggestions","Measure dataset discovery time against a baseline"]},"delivery":{"work":"Secure data-use approvals, curate metadata, set access controls, test the assistant and onboard investigators.","dependencies":["IRB approvals","UC health data access","Data platform partner"],"ownership":"Principal investigators with the data platform partner and research IT.","skillsAdoption":"Investigators learn to query and verify assistant outputs; data stewards maintain metadata.","governanceCheckpoints":["IRB and data-use approval before model training","Privacy review of agent access","Periodic audit of agent logs"],"acceptanceCriteria":["Dataset recommendations meet an expert-reviewed accuracy target (proposal)","Zero unauthorized data exposures","Investigator onboarding completed"],"risks":["Privacy breach through the agent","Plausible but flawed study designs","Data-access delays"]}},"retrievedAt":"2026-10-31T21:59:27-05:00","enrichedAt":"2026-10-31T21:59:28-05:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Natural-language access aims to lower the skill barrier for investigators using complex datasets.","procurementImplications":"Partnership with a nonprofit data initiative; no commercial vendors named.","operatingModelImplications":"Academic labs and an external data platform jointly build tools intended for a global investigator community.","peerReview":"unknown","sourceVerification":{"openedUrl":"https://neuroailab.ucsf.edu/blog/2026/10/30/addi-grip-collaboration","referenceExcerpt":"including an agentic AI research assistant designed to help scientists discover datasets, navigate research resources, and design rigorous studies using natural language","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}