Background/Objectives: Suboptimal dietary patterns are among the leading modifiable contributors to global morbidity and mortality, particularly in cardiovascular disease, type 2 diabetes mellitus (T2DM), obesity, metabolic syndrome, and hypertension. Digital nutrition platforms have emerged to improve adherence to evidence-based dietary strategies; however, many systems lack structured optimization, processing-aware nutrient profiling, and explainable artificial intelligence (AI) mechanisms. The integration of large language models (LLMs) into digital health introduces conversational personalization but also risks hallucination and unsafe outputs without constraint enforcement. This study aimed to describe the system development, architecture, database infrastructure, optimization algorithms, explainability enforcement, and digital health implications of NutriSteppe-AI, a chatbot-first LLM-driven system for personalized health menu generation constrained by deterministic nutrient logic and processing-aware scoring. Methods: NutriSteppe-AI integrates: (1) a multi-source structured nutrient database of 20,000 food products with up to 130 tracked nutrients; (2) energy requirement estimation using the revised Harris-Benedict equation; (3) linear programming-based multi-objective optimization; (4) a Healthy Food Index (HFI; 0.5–5.0 scale) incorporating NOVA processing classification penalties; (5) traffic-light nutrient gating; and (6) a constrained LLM orchestration layer governed by structured API contracts. Algorithmic validation was performed using 10,000 simulated user profiles spanning diverse age, anthropometric, activity, dietary exclusion, and budget parameters. Results: The system achieved 96.8% full constraint satisfaction with macronutrient mean absolute errors of 11.60% (energy), 18.86% (protein), 16.26% (fat), and 20.91% (carbohydrates). Incorporating NOVA processing penalties reduced ultra-processed food HFI scores by 0.73 points (p < 0.001). Median optimized menu HFI improved from 3.6 to 4.3. Median system latency was 1.8 s. Explainability validation confirmed 100% deterministic alignment with zero hallucinated numeric claims. Conclusions: NutriSteppe-AI demonstrates that LLM-driven nutrition chatbots can achieve deterministic, explainable, and clinically aligned performance when governed by structured optimization, processing-aware scoring, and explainability enforcement. This architecture provides scalable digital health infrastructure for cardiometabolic disease prevention in diverse populations.

Published household statistics describe food quantities and budget allocation but do not directly measure individual dietary intake. This study examined food-group-specific socioeconomic and household-composition contrasts and food-purchase expenditure distributions in Kazakhstan in 2025. An ecological repeated cross-sectional study used official household survey aggregates. Regional maps reproduced published fruit and fish indicators for 2025. Recent regional urban–rural comparisons covered 2022–2025, with the principal interpretation restricted to 11 oblasts not involved in the 2022 regional splits; six oblasts with estimated 2022 values were displayed separately. The national annual series for 2001–2025 was retained as historical context rather than a fully harmonised estimate of dietary change. In 2025, the highest population decile of per capita income used for consumption had a fish indicator 3.9 times that of the lowest decile; corresponding ratios were approximately 3.3 for meat, milk/dairy products and fruit and 1.5 for bread/cereal products. Per capita indicators were lower across all ten food groups in households with five or more members than in one-person households. Food purchases exceeded 50% of consumer expenditure in 64.0% of households and 71.7% of households with five or more children. Recent regional changes differed by food group and urban–rural category. These descriptive findings identify contrasts in household apparent consumption and expenditure allocation. They do not establish individual dietary adequacy, food-insecurity prevalence, household-level associations between separately tabulated indicators, or independent causal effects.

Nutrient profiling models such as the Health Star Rating (HSR) are widely used to guide consumer food choices. However, nutrient-based models may not fully