Dietary patterns, diet quality scores and the risk of diabetes: a multi-country study

Abstract Background Dietary patterns are key determinants of non-communicable disease (NCD) risk. Different dietary assessment approaches may capture diet quality differently. Methods include data-driven derived patterns and predefined diet quality scores such as the NCD-Protect and NCD-Risk indices. Evidence comparing agreement between these approaches and their associations with glycemic outcomes in low- and middle-income countries (LMICs) remains limited. Methods This cross-sectional analysis used data from the Severe Acute Malnutrition: Role of the Pancreas (SAMPA) study which included 2,251 participants (1,821 adults and 430 children) from Tanzania, Zambia, the Philippines, and India. Dietary patterns were derived using principal component analysis (PCA) of food frequency questionnaire (FFQ) data, NCD-Protect and NCD-Risk scores were generated by pragmatically recoding FFQ data to approximate 24-hour dietary recall-based indicators. Agreement between PCA-derived healthy/unhealthy patterns and NCD-Protect/NCD-Risk scores was assessed using Kappa-statistics. Associations between diet and glycemic markers, plasma glucose at 120 min during an oral glucose tolerance test (glucose120) and HbA1c were examined using multivariable linear regression adjusted for age, sex, socioeconomic status, and HIV status. Results Fair to very good agreement was observed between PCA-derived dietary patterns and NCD-Protect/NCD-Risk scores across cohorts (kappa 0.21–0.57), indicating overlap in constructs of diet quality. Associations with glycemic markers were inconsistent and cohort-specific. There were also paradoxical associations, including higher glucose120 among Zambian adults classified as having healthier diets. Additional analyses showed that prior wasting malnutrition did not modify associations between participant characteristics and diabetes, and that demographic, socioeconomic, and clinical factors alone did not explain the observed heterogeneity. Conclusions While PCA-derived dietary patterns and global diet quality scores show reasonable agreement, their associations with glycemic outcomes vary across populations and diagnostic measures. These highlight the need for context-specific dietary assessment tools and caution against the universal application of diet quality metrics when evaluating metabolic risk in diverse LMIC settings.