Closing Local Gaps in Chronic Health and Obesity Through Data & Action

From original Machine Learning research to grassroots community service.

Explore Our Research See Our Programs
4,000+
Nutrition Kits Distributed (per year)
3,000+
Wellness Kits Distributed (year to date)
500+
Census Tracts Analyzed (Santa Clara & San Mateo Cty)
The Research

Data-Driven Advocacy

We utilize original Machine Learning (ML) research to pinpoint chronic health and obesity gaps across the Peninsula, South Bay and other regions.

Read Our Mission →
Presented To
Senator Dave Cortese's District Office
01

Behavioral health beats demographics as a predictor

Depression, smoking, and housing insecurity predict obesity better than race, income, or education, even when both sets of factors are given to the model together. Mental health is an obesity intervention, not a separate concern.

SHAP Analysis · Random Forest
02

The geography is sharply divided

An east/west fault line runs through the county, with roughly a 5× gap in composite risk scores between the highest and lowest burden areas, where structural disadvantage compounds the cycle of chronic stress and poor health outcomes.

Composite Risk Score · 500+ Tracts
03

Preventive care is inverted

Tracts with the highest obesity have the lowest checkup and cholesterol screening rates. The communities that need preventive care most are getting it least, a critical equity finding with direct policy implications.

Care Gap · Equity Finding

A note on the model: The Random Forest model behind these findings (Test R² = 0.96) was built by comparing health-only, demographics-only, and combined predictor sets, which is how we know behavioral health factors outperform demographics even when both are available to the model. Because the underlying CDC PLACES estimates are themselves modeled figures, not directly measured ones, we treat tract scores as a tool for prioritizing outreach, not a diagnosis of any individual neighborhood.

Read the Research Findings

Obesity affects up to 34% of residents in Santa Clara County's highest-burden neighborhoods - driving diabetes, cardiovascular disease, and depression, while compounding barriers to education and employment in communities already under structural stress.

Based on modeled estimates, not direct measurement; see methodology below.

East San Jose carries 5× the obesity risk of Cupertino (composite risk score, modeled estimate).
370
Census tracts analyzed across Santa Clara County.
14–34%
Obesity rates vary by neighborhood.
#1
Depression outranks race and income as a predictor.

Source: CDC PLACES (2025); U.S. Census Bureau, ACS (2019–2023); Random Forest Model (Test R² = 0.96)

New: Our tool now includes San Mateo County data →
How We Serve Our Community

Our Programs

Healthy Santa Clara quick-meal recipe handouts for food box families
🥦

Family Nutrition

We offer food ingredient nutrition and benefits info, no-cook and low-cook recipe kits, and nutrition tips pamphlets, available in English and Spanish. These are distributed via ongoing food boxes and emails, addressing a key challenge to eating healthy faced by unhoused and low-income community members.

Healthy Santa Clara youth wellness kits ready for distribution
🎒

Children's and Youth Wellness Kits

Kits teach children and youth healthy eating, naming your feelings, and breathing techniques, with materials available in English, Spanish, Vietnamese, and Chinese. Each kit also includes fitness challenge cards and stress-relief exercise toys.

Youth mental health workshop presentation slide
🧠

Mental Health

We teach youth mental health workshops, including a "Listen, Validate, Connect" peer-support session at Lead Beyond (ACDS). We also offer mindful art kits for adults and children, available in multiple languages.

View a Sample Custom Project
Custom Projects

Place-based programs, tailored to each community

Beyond these three focus areas, we design custom interventions matched to each neighborhood's specific risk profile. In Alum Rock, for example, a high-burden area spanning 3 census tracts with a composite risk score of 63.2/100, our recommended focus combines culturally-competent Medi-Cal enrollment through community health workers and bilingual access to county social services, alongside peer navigation to address depression (19.3% prevalence), the leading driver of risk there.

Sample focus areas: Mental health · Preventive care · Housing stability · Smoking cessation

Alum Rock Critical

3 census tracts · sample project

63.2 / 100
Depression prevalence 19.3%
Resource Gaps

Estimated unmet need vs. availability

Mental health providers 71% gap
Affordable housing units 64% gap
Preventive care access 58% gap
Methodology & limitations

Data sources

  • Mental health: Curated: SCC county mental health clinics, AACI, Momentum for Health, Gardner Health, El Camino Health, Stanford Psychiatry.
  • Cessation: Curated: SCC Public Health tobacco prevention, FQHC cessation programs (Gardner, AACI, Valley Health), Kick It CA sites. FQHCs used as a proxy where a dedicated cessation dataset was unavailable.
  • Housing: Curated: Sacred Heart, HomeFirst, LifeMoves, Catholic Charities, Charities Housing, SCC Office of Supportive Housing, Housing Authority, West Valley Community Services, Next Door Solutions, and others.
  • Primary care: Curated: Valley Health Center network (FQHC), Gardner Health, AACI, Ravenswood FHC, VMC, El Camino Health, Kaiser Permanente, Palo Alto Medical Foundation, Stanford Health. HRSA download attempted (supplemented where available).

Gap score method

need_percentile − resource_percentile. Need = percentile rank of indicator value in the SCC distribution. Resource = percentile rank of 2-mile facility count. Range ≈ −100 to +100. Positive values mean need exceeds resources.

Distance measurement

Straight-line (haversine) distance from census tract centroid, not walking or driving distance. May overstate access in hillside tracts with large area.

Limitations

  • Resource directories may be outdated; facilities occasionally close or relocate.
  • Distance is measured from the tract centroid; for large rural tracts in the western foothills, actual resident travel may be significantly greater.
  • Cessation data uses FQHCs as a proxy where a dedicated dataset is unavailable.
  • Kaiser and private-pay facilities are included in the primary care count regardless of insurance coverage.

Data last updated: 2026-05-02

Trusted Partners

In Collaboration With

Sacred Heart Community Service

Ecumenical Hunger Program

Asian American Community Involvement (AACI)

Updates From Our Community Work

Latest News & Field Stories

📋
Policy Update

Briefing Senator Cortese's District Office

We shared our research findings on chronic health and obesity trends with Senator Dave Cortese's district staff, and have been invited to table at the Senator's next Unhoused Health Fair.

Read more →
🥗
Community Impact

Recap: Kits Delivered to EHP Families

We brought nutrition resources, exercise kits, and mental health leaflets to families through EHP's National Night Out and 20th Annual Blockfest events, alongside EHP's food boxes.

Read more →
🎤
Workshop Highlights

Recap: Lead Beyond at ACDS

Henri co-led a "Listen, Validate, Connect" youth mental health workshop at Lead Beyond, as part of Sacred Heart Community Service's delegation to the Almaden Country Day School event.

Read more →
Visit the Full News Page →
Get In Touch

Ready to collaborate or learn more?

Whether you're a community organization, a policymaker, a researcher, or simply someone who cares about health equity in Northern California, we'd love to hear from you.

Fill out this form or reach us directly at hsmit@healthysantaclara.com.