Over the past two years, I’ve been developing a deterministic digital nutrition intelligence (DNI) framework intended to function as a public health nutrition intervention, not simply a consumer app.
The theoretical architecture and scoring logic are operational and testable. The application layer is nearing completion and is being finalized in parallel with academic research, so findings can directly inform the final implementation.
Nine provisional patent applications cover the core methodology.
What’s needed now is independent, practice-based public health research to validate, challenge, and help complete the system.
At a high level, the intervention:
- Evaluates foods across multiple independent physiological dimensions (e.g., glycemic impact, cardiovascular health, inflammation), rather than a single “health score”
- Uses deterministic, transparent logic (fully reproducible, no black-box ML)
- Treats budget as a first-class constraint through health-per-dollar optimization
- Supports an end-to-end pipeline from scoring → personalization → meal planning → shopping → waste reduction
Key research questions include:
- Do dimension-specific nutrition scores improve adherence or population health outcomes?
- Does transparency support sustained behavior change?
- Can budget-aware optimization improve diet quality without increasing food costs?
- How does effectiveness vary across populations?
I’m offering research-ready infrastructure, access to a near-complete platform, reproducible methods, no restrictions on publication, pilot study support, and technical collaboration. Research independence is a priority.
I do have commercial interests in this work. I have a stronger interest in knowing—through rigorous research—what actually works.
If you’re an academic researcher or institution working in public health nutrition, behavioral science, health equity, or implementation science—and are interested in evaluating or shaping a transparent, practice-based nutrition intervention—I’d welcome a conversation.
