Zhuldyz Omarova

Ms. Zhuldyz Omarova

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 October 2025 in Nutrients
Verified
Journal Article
Open access
PDF file
ZOZhuldyz Omarova
Zhuldyz Omarova
BNBibinur Nurmanova
Bibinur Nurmanova
ASAibota Sanatbyek
Aibota Sanatbyek
HVHuseyin Atakan Varol
Huseyin Atakan Varol
MCMei-Yen Chan
Mei-Yen Chan
Background/Objectives: Portion size estimation is important for dietary assessment and nutrition research, but has remained understudied in Central Asia, a region characterized by red meat-rich diets and high rates of diet-related noncommunicable diseases (NCDs). Therefore, this study aimed to develop a digital visual food atlas for Central Asian cuisine that would provide high-quality images of commonly consumed foods and beverages, while special focus was given to meat dishes that were not present in previous atlases. Methods: Foods were selected based on the Central Asian Food Dataset (CAFD) and Central Asian Food Scenes Dataset (CAFSD) and photographed in three portion sizes: small, average, and large. There were nine broad categories: main dishes, soups, meat dishes, salads, snacks, side dishes, bakery and bread, desserts, and beverages. Similar settings were preserved for each photograph: the 60° angle, sufficient lighting, and food setup (including reference objects like utensils, a ruler, and a neatly folded napkin). Results: The final digital visual food atlas comprised 115 items (95 food series, 20 beverage guides), with 12 meat-based dishes, reflecting the central role of meat in regional diets. Each entry included portion weights and names in both English and local languages, improving cultural and linguistic relevance. The digital format with clear labeling ensured accessibility on web and mobile platforms. Conclusions: This was the first digital visual food atlas developed for Central Asia, providing standardized portion-size references. The atlas offered a practical tool for dietary assessment, with applications in nutrition research, mobile health technologies, artificial intelligence (AI)-driven portion estimation, and policy development.

20 June 2026 in Foods
Verified
Journal Article
Open access
PDF file
AMAidana Mashrapova
Aidana Mashrapova
BNBibinur Nurmanova
Bibinur Nurmanova
ZOZhuldyz Omarova
Zhuldyz Omarova
AZAlua Zeinulla
Alua Zeinulla
DTdidier talamona
didier talamona
MCMei-Yen Chan
Mei-Yen Chan
Cultivar portfolio decisions and postharvest quality management in Kazakhstani fresh apple markets are made without locally validated consumer sensory benchmarks, limiting producers’ and breeders’ ability to align product design with regional consumer expectations. This exploratory study develops and pilot-tests a consumer sensory evaluation framework for fresh apple cultivars among young adults in an urban Kazakhstani context. Twenty-eight untrained adults evaluated firmness, crispness, juiciness, mealiness, sweetness, acidity, and aroma, alongside overall liking, using a 100 mm unstructured line scale, with reference-based calibration and triangle discrimination tests. Discrimination accuracy was high (96.4%; p < 0.001; d′ = 2.59), with no evidence of systematic anchoring bias, though this cannot be fully ruled out given the study design. Significant cultivar differences were observed for seven attributes (p < 0.01), with aroma showing no significant variation (p = 0.265). Crispness (⍴ = 0.44), sweetness (⍴ = 0.43), and juiciness (⍴ = 0.41) were the attributes most strongly and positively associated with overall liking, while mealiness exerted a negative influence (⍴ = −0.36). Exploratory factor analysis revealed three latent sensory dimensions—texture, taste, and aroma—explaining 71.22% of variance. Sex-based differences were limited to mealiness, acidity, and aroma. Given the small sample size and the absence of instrumental physicochemical measurements, these findings should be interpreted as exploratory and hypothesis-generating rather than definitive. As one of the first consumer sensory evaluation frameworks piloted in a Kazakhstani population, this study provides preliminary insights and a methodological foundation for future, larger-scale research on cultivar selection, postharvest management, and consumer-oriented product development.

17 February 2026 in medRxiv
Verified
Preprint
Open access
PDF file
RARozalina Alkeyeva
Rozalina Alkeyeva
INIlyas Nagiyev
Ilyas Nagiyev
DKDamir Kim
Damir Kim
BNBibinur Nurmanova
Bibinur Nurmanova
ZOZhuldyz Omarova
Zhuldyz Omarova
MCMei-Yen Chan
Mei-Yen Chan
Background: The growing interest in applying artificial intelligence in personalized nutrition is challenged by the complex nature of dietary advice that must balance health, economic, and personal factors. Though automated solutions using either Linear Programming (LP) or Large Language Models (LLMs) already exist, they have significant drawbacks. LP often lacks personalization, whereas LLMs can be unreliable for precise calculations. Objectives: To develop and assess a model that integrates a Mixed Integer Linear Programming (MILP) solver with an LLM to generate personalized meal plans and compare it with standalone LLM and MILP models. Methods: The proposed hybrid MILP+LLM model first uses an LLM (GPT-4o) to filter a unified food dataset (n=297), which combines regional Central Asian and global food items, according to the user’s profile. The filtered list of food items is then received by a MILP solver which identifies the set of top 10 optimal solutions. Finally, given this set of solutions, LLM chooses the most appropriate meal plan. The model was evaluated using five synthesized, clinically complex patient profiles sourced from Adilmetova et al. [4]. The performance of this hybrid model was compared against standalone MILP and LLM using 5-point Likert scale with Kruskal-Wallis and post hoc Dunn’s tests for Nutrient Accuracy, Personalization, Practicality, and Variety. Results: Findings demonstrated that the proposed MILP+LLM model reached balanced performance achieving scores of more than 3.6 points in all criteria, with high scores in Nutrient Accuracy (3.96), Personalization (3.81), and Practicality (3.99). The standalone LLM model performed the weakest in all criteria, with statistically significant lower scores compared to the other two methods. The standalone MILP model performed best in Nutrient Accuracy (4.93) and in Variety (4.10) but lagged behind the MILP+LLM model in Practicality and Personalization. Kruskal-Wallis and Dunn’s tests showed MILP and MILP+LLM outperformed LLM across all criteria. MILP was more accurate (p<0.0001), while MILP+LLM model was more practical (p=0.021). Conclusions: The findings suggest that integrating the LLM with the MILP solver creates a model that combines qualitative personalization with quantitative precision. This model produces comprehensive, reliable meal plans, addressing the limitations of using either model alone.

18 April 2026 in medRxiv
Verified
Preprint
Open access
PDF file
BNBibinur Nurmanova
Bibinur Nurmanova
ZOZhuldyz Omarova
Zhuldyz Omarova
ASAibota Sanatbyek
Aibota Sanatbyek
HVHuseyin Atakan Varol
Huseyin Atakan Varol
MCMei-Yen Chan
Mei-Yen Chan
Background: Accurate dietary assessment is essential for precision nutrition and effective nutrition surveillance. However, portion size estimation remains a persistent challenge, particularly in culturally diverse regions such as Central Asia. Traditional self-reporting tools often yield inconsistent results due to communal eating practices and unfamiliarity with standard measures. Objective: To address these limitations, this study aimed to compare three methods: unassisted human judgment, visual food atlas assistance, and an artificial intelligence (AI) model, using Central Asian food items. Methods: In this cross-sectional study, 128 participants from Astana, Kazakhstan, visually estimated portion sizes of 51 foods and 8 beverages from standardized photographs. Participants were randomized into two groups: one using unassisted visual estimation and the other aided by a regionally tailored digital food atlas. Additionally, an AI model trained on Central Asian food images was evaluated. Actual food weights served as the reference standard. Accuracy was assessed using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) across food types and portion sizes. Results: The atlas-assisted group demonstrated the highest accuracy, with the lowest MAE (80.81g) and MAPE (44.76%) across all portions. The AI model showed promising results for average portions (MAE: 79.07g, MAPE: 67.91%) but underperformed on small portions, particularly for meat-based items. Unassisted estimates were the least accurate (MAE: 133.86g, MAPE: 79.40%). Across food categories, visual aids consistently improved accuracy, while AI demonstrated variability by texture and portion size. Conclusions: Culturally adapted visual atlases significantly enhance portion size estimation accuracy in non-Western, communal-eating contexts. While AI models hold promise for dietary assessments, particularly with standard portions and beverages, further refinement is needed for complex food items and small portion types. These findings support the integration of visual and AI-based tools into region-specific dietary monitoring strategies.