Population evidence & health burden
Public data, access patterns, and disease-burden measures that help clarify where health systems and communities face avoidable friction.
- Open data
- Health equity
- Evidence synthesis
A research initiative of Northern Medical Center
We connect clinical context, biostatistics, data science, and responsible AI to make complex health information more transparent—and more useful.
Part of Northern Medical Center, an organization working across clinical care, research, and whole-person health.
Clinical context · Quantitative methodsResearch areas
Our work moves between population-level evidence and individual clinical context, with methods chosen for the question rather than the trend.
Public data, access patterns, and disease-burden measures that help clarify where health systems and communities face avoidable friction.
Imaging-derived features and explainable models for neurological, oncological, and other clinically grounded research questions.
Reproducible analysis across structured health data, images, and emerging molecular measurements, with uncertainty kept visible.
Mental health, brain health, prevention, and implementation questions studied with clinical context, measurable outcomes, and respect for the full person.
Programs & work
Projects are documented as they develop within standing lines of inquiry, keeping work in progress distinct from capabilities and individual prior scholarship.
DOL / 001
Selected as a Phase 1 winner in the HHS TOPx Tech Sprint for AI and Invisible Illness , Diagnostic Odyssey Ledger is advancing through Phase 2 in the Cost of Illness challenge area. The evidence-linked prototype explores how fragmented public and health data can illuminate the time, cost, and access burdens associated with prolonged diagnostic journeys in invisible illness. View the TOPx sprint community page.
Program areas
Standing lines of inquiry that guide projects and collaborations as data, clinical needs, and partners align.
Connecting clinical context, imaging, and meaningful outcome measures.
Comparing predictive performance with explanations people can inspect.
Turning dispersed evidence into traceable, uncertainty-aware views.
Research outputs
Research outputs are labeled by provenance so that contributor scholarship is not mistaken for work produced by the Data Center.
SPIE Medical Imaging · Computer-Aided Diagnosis
Peer-reviewed prior work
These peer-reviewed articles reflect contributors’ independent work and prior affiliations. They were not produced by Data Center, Northern Medical Center.
Metabolic Brain Disease · 2014 · DOI 10.1007/s11011-014-9504-9
Cancer Imaging · 2013 · DOI 10.1102/1470-7330.2013.0009
People
A small, interdisciplinary group with experience extending beyond any one project.
A biomedical data science researcher working across biostatistics, medical imaging, explainable AI, spatial data, and reproducible research.
A psychiatrist and integrative medicine physician whose work connects mental health, conventional care, Chinese medicine, and whole-person approaches.
His books include Clinical Acupuncture and Ancient Chinese Medicine and Facing East.
A medical imaging researcher with prior work spanning CT, PET, MRI, oncology, brain connectivity, and neuroinflammation.
About the Data Center
Data Center, Northern Medical Center is an interdisciplinary research initiative. We explore focused questions where clinical experience, public evidence, and quantitative methods can produce something more useful together than apart.
Define who needs the evidence, what it can support, and what it cannot.
Document sources, assumptions, uncertainty, and material limitations.
Apply AI where it adds value, with human review and an appropriate use case.
Connect