Validating Accuracy of a Mobile Application against Food Frequency Questionnaire on Key Nutrients with Modern Diets for mHealth Era

Simple methods for estimating the maximum 24-hour urinary potassium excretion in kidney failure without replacement therapy patients

BACKGROUND

Adjusting dietary potassium intake based on 24-hour urinary potassium excretion is the primary method of preventing hyperkalemia. Currently, there is no accurate and convenient method for calculating maximum 24-hour urinary potassium excretion in kidney failure without replacement therapy patients. We developed and validated two new models to assess the upper limit of dietary potassium consumption in this high-risk cohort, using the maximum 24-hour urinary potassium excretion as a proxy.

METHODS

The data of 145 kidney failure without replacement therapy patients with hyperkalemia was gathered. The prediction models were developed using multilayer perceptron and stepwise multiple linear regression utilizing a stochastic sample of 102 (70%) patients. Within the rest 43 (30%), the performance of various models was independently verified.

RESULTS

The two new models had low bias (-0.02 and -0.57 mmol/24h vs 66.74 and 79.91 mmol/24h, mean absolute error = 5.57 and 5.22 vs 68.95 and 81.37), high accuracy (percentage of calculated values within_±30% of measured values = 83.45% and 84.14% vs 0.00% and 0.00%), high correlation with measured values (Spearman correlation coefficient = 0.72 and 0.72 vs 0.46 and 0.45, intraclass correlation coefficient = 0.67 and 0.70 vs 0.03 and 0.03) and high agreement with 24-hour urine potassium measurements (95% limits of agreement of Bland-Altman plot = 13.70 and 13.20 mmol/24h vs 113.8 and 191.3 mmol/24h).

CONCLUSION

These new models show high clinical application value for the calculation of maximum 24-hour urinary potassium excretion in kidney failure without replacement therapy patients with hyperkalemia.

Sex-specific dietary habits and their association with weight change in healthy adults

BACKGROUND

Dietary intake plays a pivotal role in the prevalence and management of obesity. While women and men exhibit differences in dietary habits and food-related behaviors, sex-based weight loss recommendations are lacking. This study aims to examine the impact of specific foods and food categories on weight reduction in men and women over a two-year period.

METHODS

A total of 8,548 participants from the 10K cohort, from 2019 to 2023, were included in the analysis (53.1% women, mean age 51.7 years). Anthropometric measurements and laboratory results were collected at baseline and at the two-year follow-up visit. Dietary assessment was based on daily food intake digitally logged through an application for at least 3 consecutive days at both timepoints. We compared intake of macronutrients, micronutrients, food groups and daily energy consumption between sex and body mass index (BMI) categories at baseline and weight change categories at follow-up. Using linear regression, we assessed the associations between food categories or specific foods and BMI at baseline as well as weight change percentage at follow-up.

RESULTS

Dietary habits varied by BMI and sex. Women and men living with obesity (BMI > 30 kg/m2) reported a greater intake of animal-based protein and lower intake of plant-based proteins and fats at baseline, as compared to participants with normal weight. In linear regression models predicting two-year weight change, including age, income, and baseline weight, the explained variance was 5.6% for men and 5.8% for women. Adding food categories and specific foods increased the explained variance to 20.6% for men and 17.5% for women. Weight reduction in men was linked to daily consumption of an egg (1.2% decrease) and beef (1.5% decrease), while in women, the most pronounced reductions were associated with an apple (1.2% decrease) and cashew nuts (3.4% decrease). Notably, total energy intake changes significantly impacted weight outcomes only in women.

CONCLUSIONS

Sex-specific dietary habits significantly influence weight change over time. In men, weight loss was primarily associated with the addition of animal-based protein, while in women, it was linked to caloric deficit and plant-based fat, suggesting that sex-based nutritional interventions may demonstrate greater efficacy.

TRIAL REGISTRATION

NCT05817734 (retrospectively registered January 31, 2023).

A Study on the Compatibility of a Food-Recording Application with Questionnaire-Based Methods in Healthy Japanese Individuals

In Japan, nutritional guidance based on food-recording apps and food frequency questionnaires (FFQs) is becoming popular. However, it is not always recognized that different dietary assessment methods have different nutritional values. Here, we compared the compatibility of dietary intake data obtained from an app with those obtained from FFQs in 59 healthy individuals who recorded information regarding their diet for at least 7 days per month using an app developed by Asken (Tokyo, Japan). The diurnal coefficient of variation in total energy and protein intake was 20%, but those for vitamins B12 and D were >80%, reflecting the importance of 7 days of recording rather than a single day of recording for dietary intake analyses. Then, we compared the results of two FFQs-one based on food groups and one based on a brief self-administered diet history questionnaire-for 7 days, as recorded by the app. There was a correlation coefficient of >0.4 for all the items except salt. Regarding the compatibility between the app and FFQs, the percentage errors for total energy and nutrients were >40-50%, suggesting no agreement between the app and the two FFQs. In conclusion, careful attention should be paid to the impact of different dietary assessment methods on nutrient assessment.

Validating Healthy Eating Index, Glycemic Index, and Glycemic Load with Modern Diets for E-Health Era

Predictors of healthy eating parameters, including the Healthy Eating Index (HEI), Glycemic Index (GI), and Glycemic Load (GL), were examined using various modern diets (n = 131) in preparation for personalized nutrition in the e-health era. Using Nutrition Data Systems for Research computerized software and artificial intelligence machine-learning-based predictive validation analyses, we included domains of HEI, caloric source, and various diets as the potentially modifiable factors. HEI predictors included whole fruits and whole grains, and empty calories. Carbohydrates were the common predictor for both GI and GL, with total fruits and Mexican diets being additional predictors for GI. The median amount of carbohydrates to reach an acceptable GL < 20 was predicted as 33.95 g per meal (median: 3.59 meals daily) with a regression coefficient of 37.33 across all daily diets. Diets with greater carbohydrates and more meals needed to reach acceptable GL < 20 included smoothies, convenient diets, and liquids. Mexican diets were the common predictor for GI and carbohydrates per meal to reach acceptable GL < 20; with smoothies (12.04), high-school (5.75), fast-food (4.48), Korean (4.30), Chinese (3.93), and liquid diets (3.71) presenting a higher median number of meals. These findings could be used to manage diets for various populations in the precision-based e-health era.

Food Frequency Questionnaire Personalisation Using Multi-Target Regression

Fondazione Bruno Kessler is developing a mobile app prototype for empowering citizens to improve their health conditions through different lifestyle interventions that will be incorporated into a mobile application for lifestyle promotion of the Province of Trento in the context of the Trentino Salute 4.0 Competence Center. The envisioned interventions are based on promoting behaviour change in various domains such as physical activity, mental health and nutrition. In particular, the nutrition component is a self-monitoring module that collects dietary habits to analyse them and recommend healthier eating behaviours. Dietary assessment is completed using a Food Frequency Questionnaire on the Mediterranean diet that is presented to the user as a grid of images. The questionnaire returns feedback on 11 aspects of nutrition. Although the questionnaire used in the application only consists of 24 questions, it still could be a bit overwhelming and a bit crowded when shown on the screen. In this paper, we tried to find a machine-learning-based solution to reduce the number of questions in the questionnaire. We proposed a method that uses the user’s previous answers as additional information to find the goals that need more attention. We compared this method with a case where the subset of questions is randomly selected and with a case where the subset is chosen using feature selection. We also explored how large the subset should be to obtain good predictions. All the experiments are conducted as a multi-target regression problem, which means several goals are predicted simultaneously. The proposed method adjusts well to the user in question and has the slightest error when predicting the goals.

Validating Accuracy of an Internet-Based Application against USDA Computerized Nutrition Data System for Research on Essential Nutrients among Social-Ethnic Diets for the E-Health Era

Internet-based applications (apps) are rapidly developing in the e-Health era to assess the dietary intake of essential macro-and micro-nutrients for precision nutrition. We, therefore, validated the accuracy of an internet-based app against the Nutrition Data System for Research (NDSR), assessing these essential nutrients among various social-ethnic diet types. The agreement between the two measures using intraclass correlation coefficients was good (0.85) for total calories, but moderate for caloric ranges outside of <1000 (0.75) and >2000 (0.57); and good (>0.75) for most macro- (average: 0.85) and micro-nutrients (average: 0.83) except cobalamin (0.73) and calcium (0.51). The app underestimated nutrients that are associated with protein and fat (protein: −5.82%, fat: −12.78%, vitamin B12: −13.59%, methionine: −8.76%, zinc: −12.49%), while overestimated nutrients that are associated with carbohydrate (fiber: 6.7%, B9: 9.06%). Using artificial intelligence analytics, we confirmed the factors that could contribute to the differences between the two measures for various essential nutrients, and they included caloric ranges; the differences between the two measures for carbohydrates, protein, and fat; and diet types. For total calories, as an example, the source factors that contributed to the differences between the two measures included caloric range (<1000 versus others), fat, and protein; for cobalamin: protein, American, and Japanese diets; and for folate: caloric range (<1000 versus others), carbohydrate, and Italian diet. In the e-Health era, the internet-based app has the capacity to enhance precision nutrition. By identifying and integrating the effects of potential contributing factors in the algorithm of output readings, the accuracy of new app measures could be improved.

Prediction Tool to Estimate Potassium Diet in Chronic Kidney Disease Patients Developed Using a Machine Learning Tool: The UniverSel Study

There is a need for a reliable and validated method to estimate dietary potassium intake in chronic kidney disease (CKD) patients to improve prevention of cardiovascular complications. This study aimed to develop a clinical tool to estimate potassium intake using 24-h urinary potassium excretion as a surrogate of dietary potassium intake in this high-risk population. Data of 375 adult CKD-patients routinely collecting their 24-h urine were included to develop a prediction tool to estimate potassium diet. The prediction tool was built from a random sample of 80% of patients and validated on the remaining 20%. The accuracy of the prediction tool to classify potassium diet in the three classes of potassium excretion was 74%. Surprisingly, the variables related to potassium consumption were more related to clinical characteristics and renal pathology than to the potassium content of the ingested food. Artificial intelligence allowed to develop an easy-to-use tool for estimating patients' diets in clinical practice. After external validation, this tool could be extended to all CKD-patients for a better clinical and therapeutic management for the prevention of cardiovascular complications.