Imaging
Clinical intelligence for neurology
AI that fits the problem.
Most clinical AI makes everyone adapt to it. Cognimark works the other way. Our multimodal models adapt to the data your site already has, turning routine records into attributable neurological insight for screening, trial recruitment, and earlier care.
Supported by
University of Southern CaliforniaPlatform
Your data doesn't adapt to us. Our AI adapts to you.
Most clinical AI demands a fixed input: a specific scan, test, or workflow. Cognimark reasons over whatever multimodal data is available at your site, and no more. No new tests, no new burden for patients or clinicians.
Text
Clinical notes & history
Assessment
Cognitive & functional tests
Labs
Laboratory results
Structured
Demographics & meds
Any subset
Works with what you have
Swift assessment
Evaluate cognitive health from routine clinical data - no added tests or procedures.
Mixed-dementia insight
Attributable scores per etiology help clinicians reason about co-occurring conditions.
Comprehensive analysis
Quantified signals across cognitive functions and dementia etiologies for a complete view.
Stronger screening
Identify more appropriate candidates while reducing the manual burden of chart review.
Expanded recruitment
Widen clinical trial pipelines through fast, data-supported patient pre-screening.
EHR connected
Standards-based clinical data across leading EHR platforms and care settings.
- 1
Connect
Start with standards-based EHR data and whatever multimodal information your site captures.
- 2
Understand
Longitudinal evidence is organized into clinical context - traceable to its source at every step.
- 3
Act
Focused neurological insight supports screening, recruitment, and next-step clinical decisions.
Use cases
Clinical intelligence where decisions begin
Routine patient screening
Preview neurological risk across a patient population using data already captured in the clinical workflow. Focus review on the patients who may benefit from evaluation, intervention, or a relevant study.
- 01Connect available EHR and multimodal data from routine care
- 02Run analysis across cognitive signals and attributable dementia scores
- 03Review actionable insight for screening and follow-up decisions
Clinical trial recruitment
Widen trial pipelines with fast, data-supported pre-screening. Identify more appropriate candidates while cutting the manual burden of chart review, now being piloted inside primary-care EHR workflows through the USC CTRL initiative.
Patient-facing cognitive insight
A future experience helping individuals securely understand their own cognitive status, connected to care and never replacing clinical evaluation.
Research
Not a demo. Proven science.
The methods behind Cognimark were developed at the Kolachalama Laboratory at Boston University, an interdisciplinary group publishing from Nature Medicine to ICML, and validated through peer-reviewed studies in multimodal dementia assessment.
Visit the labAlzheimer's & Dementia 2025
An AI-first framework for multimodal data in Alzheimer's disease and related dementias
Nature Communications 2025
AI-driven fusion of multimodal data for Alzheimer's disease biomarker assessment
J. Prev. Alzheimer's Dis. 2025
AI-augmented frameworks for Alzheimer's disease clinical trials
Nature Medicine 2024
AI-based differential diagnosis of dementia etiologies on multimodal data
iScience 2023
Deep learning for risk-based stratification of cognitively impaired individuals
Nature Communications 2022
Multimodal deep learning for Alzheimer's disease dementia assessment
Brain 2020
An interpretable deep learning framework for Alzheimer's disease classification
Company
Make earlier neurological insight part of routine care.
Cognimark is transforming dementia assessment by applying AI to standard healthcare data, improving early detection while supporting a nuanced understanding of different and co-occurring etiologies, from first signal through diagnosis and care.
Identify risk earlier
Recognize neurological signals in the record before they are overlooked.
Support clinical judgment
Present attributable insight clinicians can review in context.
Guide the next step
Route patients toward appropriate evaluation, care, or research.
Recent milestones
New - Jan 2026
Selected by the USC Schaeffer Clinical Trial Recruitment Lab
One of four pilots chosen from 30+ applicants, first presented as a Cognimark x OCHIN finalist in the CTRL pitch competition at CTAD 2025. With OCHIN, Cognimark will integrate its AI-enabled diagnostic platform into primary-care EHR workflows to support earlier identification and referral of patients for Alzheimer's trials - funded by Gates Ventures and the American Heart Association.
Read the announcement4pilots funded
from 30+ applicants
from 30+ applicants
<1%of eligible patients reach
Alzheimer's trials today
Alzheimer's trials today
MIT Ignite
Finalist among 100+ generative AI teams
MIT $100K
Finalist at the MIT $100K Competition
MIT Sloan Healthcare
Healthcare & BioInnovations finalist
Contact
Start with the workflow you need to improve.
Tell us about your organization, data environment, or research goals. We work with clinical, operational, research, and media teams.
Clinical workflowsResearch partnershipsProduct demosMedia inquiries