Background: To accurately capture an individual’s food intake, dietitians are often required to ask clients about their food frequencies and portions, and they have to rely on the client’s memory, which can be burdensome. While taking food photos alongside food records can alleviate user burden and reduce errors in self-reporting, this method still requires trained staff to translate food photos into dietary intake data. Image-assisted dietary assessment (IADA) is an innovative approach that uses computer algorithms to mimic human performance in estimating dietary information from food images. This field has seen continuous improvement through advancements in computer science, particularly in artificial intelligence (AI). However, the technical nature of this field can make it challenging for those without a technical background to understand it completely. Objective: This review aims to fill the gap by providing a current overview of AI’s integration into dietary assessment using food images. The content is organized chronologically and presented in an accessible manner for those unfamiliar with AI terminology. In addition, we discuss the systems’ strengths and weaknesses and propose enhancements to improve IADA’s accuracy and adoption in the nutrition community. Methods: This scoping review used PubMed and Google Scholar databases to identify relevant studies. The review focused on computational techniques used in IADA, specifically AI models, devices, and sensors, or digital methods for food recognition and food volume estimation published between 2008 and 2021. Results: A total of 522 articles were initially identified. On the basis of a rigorous selection process, 84 (16.1%) articles were ultimately included in this review. The selected articles reveal that early systems, developed before 2015, relied on handcrafted machine learning algorithms to manage traditional sequential processes, such as segmentation, food identification, portion estimation, and nutrient calculations. Since 2015, these handcrafted algorithms have been largely replaced by deep learning algorithms for handling the same tasks. More recently, the traditional sequential process has been superseded by advanced algorithms, including multitask convolutional neural networks and generative adversarial networks. Most of the systems were validated for macronutrient and energy estimation, while only a few were capable of estimating micronutrients, such as sodium. Notably, significant advancements have been made in the field of IADA, with efforts focused on replicating humanlike performance. Conclusions: This review highlights the progress made by IADA, particularly in the areas of food identification and portion estimation. Advancements in AI techniques have shown great potential to improve the accuracy and efficiency of this field. However, it is crucial to involve dietitians and nutritionists in the development of these systems to ensure they meet the requirements and trust of professionals in the field.

Probiotics have the potential as a multi-target approach to modulate hypercholesterolemia associated with premature atherosclerosis. Various strains of Lactobacillus paracasei have been reported to affect hypercholesterolemia positively. This study aimed to investigate the effects of L. paracasei TISTR 2593 on lipid profile, cholesterol metabolism, and atherosclerosis according to the registration of Thai Clinical Trial Registry as identification number TCTR 20220917002. A total of 50 participants with hypercholesterolemia were randomly and equally assigned to consume L. paracasei TISTR 2593 or a placebo in maltodextrin capsules daily. Biomarkers of lipid profiles, oxidative stress state, inflammatory state, and other biological indicators were examined on days 0, 45, and 90. The results showed that subjects taking the L. paracasei TISTR 2593 could significantly reduce the level of serum low-density lipoprotein-cholesterol (p < 0.05), malondialdehyde (p < 0.001), and tumor necrosis factor-α (p < 0.01). Moreover, L. paracasei TISTR 2593 increased the level of serum apolipoprotein E (p < 0.01) and adiponectin (p < 0.001) significantly. No changes in serum total cholesterol, high-density lipoprotein-cholesterol, triglyceride, total bile acids, and monocyte chemoattractant protein-1 were observed during L. paracasei TISTR 2593 supplementation. Therefore, L. paracasei TISTR 2593 could be an adjuvant probiotic supplement to ameliorate hypercholesterolemia and prevent or delay the development of atherosclerosis.

The Global Diet Quality Score (GDQS) was developed for monitoring nutrient adequacy and diet-related noncommunicable disease risk in diverse populations. A software application (GDQS app) was recently developed for the standardized collection of GDQS data. The application involves a simplified 24-h dietary recall (24HR) where foods are matched to GDQS-food groups using an onboard database, portion sizes are estimated at the food group level using cubic models, and the GDQS is computed. The study aimed to estimate associations between GDQS scores collected using the GDQS app and nutrient adequacy and metabolic risks. In this cross-sectional study of 600 Thai males and nonpregnant/nonlactating females (40-60 y), we collected 2 d of GDQS app and paper-based 24HR, food-frequency questionnaires (FFQs), anthropometry, body composition, blood pressure, and biomarkers. Associations between application scores and outcomes were estimated using multiple regression, and application performance was compared with that of metrics scored using 24HR and FFQ data: GDQS, Minimum Dietary Diversity-Women, Alternative Healthy Eating Index-2010, and Global Dietary Recommendations score. In covariate-adjusted models, application scores were significantly (P < 0.05) associated with higher energy-adjusted mean micronutrient adequacy computed using 24HR (range in estimated mean adequacy between score quintiles 1 and 5: 36.3%-44.5%) and FFQ (Q1-Q5: 40.6%-44.2%), and probability of protein adequacy from 24HR (Q1-Q5: 63%-72.5%). Application scores were inversely associated with BMI kg/m² (Q1-Q5: 26.3-24.9), body fat percentage (Q1-Q5: 31.7%-29.1%), diastolic blood pressure (Q1-Q5: 84-81 mm Hg), and a locally-developed sodium intake score (Q1-Q5: 27.5-24.0 points out of 100); positively associated with high-density lipoprotein cholesterol (Q1-Q5: 49-53 mg/dL) and 24-h urinary potassium (Q1-Q5: 1385-1646 mg); and inversely associated with high midupper arm circumference (Q5/Q1 odds ratio: 0.52) and abdominal obesity (Q5/Q1 odds ratio: 0.51). Significant associations for the application outnumbered those for metrics computed using 24HR or FFQ. The GDQS app effectively assesses nutrient adequacy and metabolic risk in population surveys.

Oxidative stress and inflammation play key roles in the pathophysiology in the pathophysiology of dyslipidemia, which are positive risks that increase atherosclerosis leading to important healthcare problems. Therefore, we aimed to study the antioxidant, anti‐inflammatory, and lipid‐lowering effects of jelly drink containing polyphenol‐rich roselle calyces extract and passion fruit juice with pulp concentrate (RP jelly drink) in comparison to a placebo jelly drink for 8 weeks. Forty‐three adults with dyslipidemia were randomly assigned into two groups: the RP jelly drink group and the placebo group. Glucose, total cholesterol (TC) triglyceride (TG), low‐density lipoprotein‐cholesterol (LDL‐C), high‐density lipoprotein‐cholesterol (HDL‐C), oxidative stress biomarkers, inflammatory parameters, and monocyte chemotactic protein‐1 (MCP‐1) were measured with fasting blood samples at baseline, 4 weeks and 8 weeks of intervention. Results showed a significant decrease in LDL‐C and TG, respectively, after 8 weeks of RP jelly drink consumption (LDL‐C: 107.63 ± 22.98 mg/dL; TG: 109.79 ± 38.83 mg/dL) compared to baseline measurements (LDL‐C: 128.43 ± 32.74 mg/dL; TG: 132.33 ± 75.11 mg/dL). These may be possible due to reduced inflammation and improvements in oxidative stress, as demonstrated by the reduction of tumor necrosis factor‐ (TNF‐) α and malondialdehyde (MDA), and the enhancement of glutathione (GSH) after consuming the RP jelly drink for 8 weeks. However, no significant differences of treatment on glucose, total cholesterol, MCP‐1, interleukin‐6, and interleukin‐10 were observed. In conclusion, daily consumption of RP jelly drink for 8 weeks resulted in significant improvement in lipid profiles in subjects with dyslipidemia. However, more research is needed to assess its nutritional and functional potential.

Previous studies have highlighted differences in faecal short-chain fatty acids (SCFAs) between hypercholesterolemic (HC) and normocholesterolemic (NC) individuals; however, the impact of nutritional factors on SCFAs remains underexplored. This cross-sectional observational study involved 42 HC and 38 NC Thai adults and examined faecal SCFA concentrations and their associations with nutritional factors. Aliphatic (acetic, propionic, butyric acids) and branched (isobutyric and isovaleric acids) SCFAs were analysed. Although NC participants exhibited higher aliphatic and total SCFAs than HC participants, these differences were insignificant. Carbohydrate intake was positively associated with acetic and propionic acid, in the NC group. Sugar intake was negatively correlated with isobutyric and isovaleric acids in the NC group but positively correlated in the HC group. These findings suggest less efficient sugar and carbohydrate fermentation in the HC group, potentially affecting SCFA profiles. Future studies should investigate gut microbiota composition, bile acid secretion and gut pH as contributing factors.