PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets.

AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system's effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.

Users' Perspective on the AI-Based Smartphone PROTEIN App for Personalized Nutrition and Healthy Living: A Modified Technology Acceptance Model (mTAM) Approach.

The ubiquitous nature of smartphone ownership, its broad application and usage, along with its interactive delivery of timely feedback are appealing for health-related behavior change interventions via mobile apps. However, users' perspectives about such apps are vital in better bridging the gap between their design intention and effective practical usage. In this vein, a modified technology acceptance model (mTAM) is proposed here, to explain the relationship between users' perspectives when using an AI-based smartphone app for personalized nutrition and healthy living, namely, PROTEIN, and the mTAM constructs toward behavior change in their nutrition and physical activity habits. In particular, online survey data from 85 users of the PROTEIN app within a period of 2 months were subjected to confirmatory factor analysis (CFA) and regression analysis (RA) to reveal the relationship of the mTAM constructs, i.e., perceived usefulness (PU), perceived ease of use (PEoU), perceived novelty (PN), perceived personalization (PP), usage attitude (UA), and usage intention (UI) with the users' behavior change (BC), as expressed via the acceptance/rejection of six related hypotheses (H1-H6), respectively. The resulted CFA-related parameters, i.e., factor loading (FL) with the related p-value, average variance extracted (AVE), and composite reliability (CR), along with the RA results, have shown that all hypotheses H1-H6 can be accepted (p < 0.001). In particular, it was found that, in all cases, FL > 0.5, CR > 0.7, AVE > 0.5, indicating that the items/constructs within the mTAM framework have good convergent validity. Moreover, the adjusted coefficient of determination (R 2) was found within the range of 0.224-0.732, justifying the positive effect of PU, PEoU, PN, and PP on the UA, that in turn positively affects the UI, leading to the BC. Additionally, using a hierarchical RA, a significant change in the prediction of BC from UA when the UI is used as a mediating variable was identified. The explored mTAM framework provides the means for explaining the role of each construct in the functionality of the PROTEIN app as a supportive tool for the users to improve their healthy living by adopting behavior change in their dietary and physical activity habits. The findings herein offer insights and references for formulating new strategies and policies to improve the collaboration among app designers, developers, behavior scientists, nutritionists, physical activity/exercise physiology experts, and marketing experts for app design/development toward behavior change.

Modifiable risk factors for bone health & fragility fractures.

Osteoporosis is an ageing disorder characterised by poor microstructural architecture of the bone and an increase in the risk of fragility fractures, which often leads to hospitalisation and eventually a loss of mobility and independence. By 2050, it is estimated that more than 30 million people in Europe will be affected by bone diseases, and European hospitalisation alone can approximately cost up to 3.5 billion euros each year [1]. Although inherited variation in bone mineral density (BMD) is pre-determined by up to 85% [2], there is a window of opportunity to optimise BMD and reduce fracture risk through key modifiable lifestyle factors during the life course. An optimal diet rich in micronutrients, such as calcium, vitamin D, and potassium, has long been considered an important modifiable component of bone health, which is attributed to their direct roles within bone metabolism. Recently, there has been emerging evidence to suggest that protein and even an adequate intake of fruit and vegetables may also play an important role in improving BMD [3,4]. Maintaining a physically active lifestyle is not only protective from non-communicable diseases such as cardiovascular disease but it also has been shown to lessen the risk of fractures later in life, thereby making it an imperative modifiable factor for bone health, particularly as it also supports peak bone mass attainment during childhood/adolescence and can facilitate the maintenance of bone mass throughout adulthood [5]. Other key lifestyle factors that could be potentially modified to reduce the risk of osteoporosis or osteoporotic fractures later in life include smoking status, alcohol intake, and body composition [6]. Therefore, the principle aim of this review is to highlight the recent evidence pertaining to modifiable lifestyle factors that contribute to optimal bone health and the prevention of fragility fractures in later life.

The relationship between vitamin D status, intake and exercise performance in UK University-level athletes and healthy inactive controls.

The potential ergogenic effects of vitamin D (vitD) in high performing athletes has received considerable attention in the literature and media. However, little is known about non-supplemented university athletes and students residing at a higher latitude. This study aimed to investigate the effects of vitD (biochemical status and dietary intake) on exercise performance in UK university athletes and sedentary students. A total of 34 athletes and 16 sedentary controls were studied during the spring and summer months. Serum vitD status and sunlight exposure were assessed using LC-MS/MS and dosimetry, respectively. Muscular strength of the upper and lower body was assessed using handgrip and knee extensor dynamometry (KE). Countermovement jump (CMJ) and aerobic fitness were measured using an Optojump and VO2max test, respectively. Statistical analysis was performed using paired/ independent t-tests, ANCOVA and Pearson/ Spearman correlations, depending on normality. VitD status increased significantly over the seasons, with athletes measuring higher status both in spring (51.7±20.5 vs. 37.2±18.9 nmol/L, p = 0.03) and summer (66.7±15.8 vs 55.6±18.8 nmol/L, p = 0.04) when compared to controls, respectively. Notably, 22% of the subjects recruited were vitD deficient during the spring term only (<25nmol/L, n 9). Subjects with 'insufficient' vitD status (<50nmol/L) elicited significantly lower CMJ when contrasted to the vitD 'sufficient' (>50nmol/l) group (p = 0.055) and a lower VO2 max (p = 0.05) in the spring and summer term (p = 0.05 and p = 0.01, respectively). However, an ANCOVA test showed no significant difference detected for either CMJ or VO2max following adjustments for co-variates. In conclusion, we provide novel information on the vitD status, dietary intake, physical fitness and sunlight exposure of UK young adults across two separate seasons, for which there is limited data at present.

Seasonal variation in vitamin D status, bone health and athletic performance in competitive university student athletes: a longitudinal study.

Vitamin D deficiency has been commonly reported in elite athletes, but the vitamin D status of UK university athletes in different training environments remains unknown. The present study aimed to determine any seasonal changes in vitamin D status among indoor and outdoor athletes, and whether there was any relationship between vitamin D status and indices of physical performance and bone health. A group of forty-seven university athletes (indoor n 22, outdoor n 25) were tested during autumn and spring for serum vitamin D status, bone health and physical performance parameters. Blood samples were analysed for serum 25-hydroxyvitamin D (s-25(OH)D) status. Peak isometric knee extensor torque using an isokinetic dynamometer and jump height was assessed using an Optojump. Aerobic capacity was estimated using the Yo-Yo intermittent recovery test. Peripheral quantitative computed tomography scans measured radial bone mineral density. Statistical analyses were performed using appropriate parametric/non-parametric testing depending on the normality of the data. s-25(OH)D significantly fell between autumn (52·8 (sd 22·0) nmol/l) and spring (31·0 (sd 16·5) nmol/l; P < 0·001). In spring, 34 % of participants were considered to be vitamin D deficient (<25 nmol/l) according to the revised 2016 UK guidelines. These data suggest that UK university athletes are at risk of vitamin D deficiency. Thus, further research is warranted to investigate the concomitant effects of low vitamin D status on health and performance outcomes in university athletes residing at northern latitudes.

Estimation of the dietary requirement for vitamin D in adolescents aged 14-18 y: a dose-response, double-blind, randomized placebo-controlled trial.

BACKGROUND: Adolescents are a population group at high risk of low vitamin D status, yet the evidence base for establishing dietary vitamin D requirements remains weak. OBJECTIVE: The aim was to establish the distribution of vitamin D intakes required to maintain serum 25-hydroxyvitamin D [25(OH)D] concentrations above proposed cutoffs (25, 30, 40, and 50 nmol/L) during winter in white males and females (14-18 y of age) in the United Kingdom (51°N). DESIGN: In a dose-response trial, 110 adolescents (aged 15.9 ± 1.4 y; 43% males) were randomly assigned to receive 0, 10, or 20 µg vitamin D3 supplements/d for 20 wk during winter. A nonlinear regression model was fit to total vitamin D intake and postintervention serum 25(OH)D concentrations, and regression-predicted values estimated the vitamin D intakes required to maintain serum 25(OH)D concentrations above specific cutoffs. RESULTS: Mean ± SD serum 25(OH)D concentrations increased from 49.2 ± 12.0 to 56.6 ± 12.4 nmol/L and from 51.7 ± 13.4 to 63.9 ± 10.6 nmol/L in the 10- and 20-µg/d groups, respectively, and decreased in the placebo group from 46.8 ± 11.4 to 30.7 ± 8.6 nmol/L (all P ≤ 0.001). Vitamin D intakes required to maintain 25(OH)D concentrations >25 and >30 nmol/L in 97.5% of adolescents were estimated to be 10.1 and 13.1 µg/d, respectively, and 6.6 µg/d to maintain 50% of adolescents at concentrations >40 nmol/L. Because the response of 25(OH)D reached a plateau at 46 nmol/L, there is uncertainty in estimating the vitamin D intake required to maintain 25(OH)D concentrations >50 nmol/L in 97.5% of adolescents, but it exceeded 30 µg/d. CONCLUSION: Vitamin D intakes between 10 and ∼30 µg/d are required by white adolescents during winter to maintain serum 25(OH)D concentrations >25-50 nmol/L, depending on the serum 25(OH)D threshold chosen. This trial was registered at clinicaltrials.gov as NCT02150122 and as International Standard Randomized Controlled Trial Number ISRCTN40736890.