Determining the effective factors in predicting diet adherence using an intelligent model

Abstract

Adhering to a healthy diet plays an essential role in preventing many nutrition-related diseases, such as obesity, diabetes, high blood pressure, and other cardiovascular diseases. This study aimed to predict adherence to the prescribed diets using a hybrid model of artificial neural networks (ANNs) and the genetic algorithm (GA). In this study, 26 factors affecting diet adherence were modeled using ANN and GA(ANGA). A dataset of 1528 patients, including 1116 females and 412 males, referred to a private clinic was applied. SPSS Ver.25 and MATLAB toolbox 2017 were employed to make the model and analyze the data. The results showed that the accuracy of the proposed ANN and ANGA models for predicting diet adherence was 93.22% and 93.51%, respectively. Also, the Pearson coefficient showed a significant relationship among the factors. The developed model showed the proper performance for predicting adherence to the diet. Moreover, the most effective factors were selected using GA. Some important factors that affect diet adherence include the duration of the marriage, the reason for referring to the clinic, weight, body mass index (BMI), weight satisfaction, lunch and dinner times, and sleep time. Therefore, applying the proposed model can help dietitians identify people who need more support to adhere to the diet.

Genetic variant panel allows predicting both obesity risk, and efficacy of procedures and diet in weight loss

“…In addition to the findings related to genetic analysis, we also observed interesting results regarding the overall utility of this approach. In dataset B, 78.27% of patients demonstrated a global adherence to dietarian changes, which is considerably higher compared to studies with non-genotyped patients (1,2,69,70). This suggests that nutrigenetic tools might also impact the efficacy of diet due to increased adherence.…”

Sequential model for predicting patient adherence in subcutaneous immunotherapy for allergic rhinitis

“… Mousavi et al (2022) demonstrated the effectiveness of a hybrid model that combines neural networks and genetic algorithms for predicting diet adherence. Wang et al (2020) explored another hybrid model that integrates neural networks and support vector machines to predict nonadherence in Crohn’s Disease patients by streamlining the intervention process in medicine-taking.…”

“…In healthcare, machine learning, especially sequential models, stands at the forefront of innovation, providing new ways to analyze complex medical data and improve patient treatments. Previous research primarily concentrated on non-sequential prediction methods for adherence ( Ruff et al, 2019 ; Wang et al, 2020 ; Mousavi et al, 2022 ; Warren et al, 2022 ). This approach presents a significant limitation in treatment processes, particularly for immunotherapy that often spans extended periods, such as 3 years.…”

The Role of Artificial Intelligence in Deciphering Diet–Disease Relationships: Case Studies

“…However, novel, unbiased methodologies are required to quantify and even predict adherence to dietary recommendations. One such modality was recently developed by Mousavi et al (141), who utilized a hybrid model of artificial neural networks (ANNs) and a genetic algorithm to evaluate 26 factors potentially affecting diet adherence in a data set of 1,528 patients. The accuracy for predicting adherence to diet was 93.51%; the main features associated with this prediction were duration of marriage, weight, body mass index, weight satisfaction, lunch and dinner times, and sleep time.…”