Predicting Obesity in Adults Using Machine Learning Techniques: An Analysis of Indonesian Basic Health Research 2018

Artificial intelligence-enabled obesity prediction: A systematic review of cohort data analysis

BACKGROUND

Obesity, now the fifth leading global cause of death, has seen a dramatic rise in prevalence over the last forty years. It significantly increases the risk of diseases such as type 2 diabetes and cardiovascular disease. Early identification of obesity risk allows for preventative actions against obesity-related factors. Despite the existence of AI-based predictive models, developing a comprehensive obesity screening tool requires extensive cohort data.

METHODS

A thorough review of 6,351 articles, focusing on AI predictions for obesity in cohort studies, was conducted up to March 2024 across databases including PubMed, Scopus, and Web of Science.

RESULTS

Using the JBI checklist, 10 studies involving 411,580 participants were critically appraised. These cohorts varied in length and size, with half lasting 1-5 years and involving less than 5,000 participants. The data types were categorized into nine groups, with demographic (7 studies) and biomarker data (4 studies) being the most frequently used. Machine learning was predominantly used (95 % of studies), mostly employing supervised learning techniques. Algorithms like random forest (RF) (18 %), linear regression (18 %), and stochastic gradient boosting (GBM) (14 %) were common. Top-performing models were noted for k-means (accuracy of 0.977), artificial neural networks (AUC of 0.99), GBM (specificity of 0.95 and sensitivity of 0.65), RF (RMSE of 0.146), and least absolute shrinkage and selection operator (r-squared of 0.684).

CONCLUSION

Findings indicate that AI algorithms can predict obesity; however, further research is needed to assess their effectiveness in analyzing obesity-related data and examine most advanced AI methods. This review is a valuable resource for dietitians and researchers engaged in developing predictive models and intelligent clinical decision support systems using AI technology.

The Role of Artificial Intelligence in Obesity Risk Prediction and Management: Approaches, Insights, and Recommendations

Greater than 650 million individuals worldwide are categorized as obese, which is associated with significant health, economic, and social challenges. Given its overlap with leading comorbidities such as heart disease, innovative solutions are necessary to improve risk prediction and management strategies. In recent years, artificial intelligence (AI) and machine learning (ML) have emerged as powerful tools in healthcare, offering novel approaches to chronic disease prevention. This narrative review explores the role of AI/ML in obesity risk prediction and management, with a special focus on childhood obesity. We begin by examining the multifactorial nature of obesity, including genetic, behavioral, and environmental factors, and the limitations of traditional approaches to predict and treat morbidity associated obesity. Next, we analyze AI/ML techniques commonly used to predict obesity risk, particularly in minimizing childhood obesity risk. We shift to the application of AI/ML in obesity management, comparing perspectives from healthcare providers versus patients. From the provider's perspective, AI/ML tools offer real-time data from electronic medical records, wearables, and health apps to stratify patient risk, customize treatment plans, and enhance clinical decision making. From the patient's perspective, AI/ML-driven interventions offer personalized coaching and improve long-term engagement in health management. Finally, we address key limitations and challenges, such as the role of social determinants of health, in embracing the role of AI/ML in obesity management, while offering our recommendations based on our literature review.

Deep learning captures the effect of epistasis in multifactorial diseases

Background

Polygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer's disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis.

Methods

Simulated data with 2- and 3-loci interactions and tested three different models of epistasis: additive, multiplicative and threshold, were generated using the GAMETES. Penetrance tables were generated using PyTOXO package. For machine learning methods we used multilayer perceptron (MLP), convolutional neural network (CNN) and recurrent neural network (RNN), Lasso regression, random forest and gradient boosting models. Performance of machine learning models were assessed using accuracy, AUC-ROC, AUC-PR, recall, precision, and F1 score.

Results

First, we tested ensemble tree methods and deep learning neural networks against LASSO linear regression model on simulated data with different types and strength of epistasis. The results showed that with the increase of strength of epistasis effect, non-linear models significantly outperform linear. Then the higher performance of non-linear models over linear was confirmed on real genetic data for multifactorial phenotypes such as obesity, type 1 diabetes, and psoriasis. From non-linear models, gradient boosting appeared to be the best model in obesity and psoriasis while deep learning methods significantly outperform linear approaches in type 1 diabetes.

Conclusion

Overall, our study underscores the efficacy of non-linear models and deep learning approaches in more accurately accounting for the effects of epistasis in simulations with specific configurations and in the context of certain diseases.

Development and validation of cardiometabolic risk predictive models based on LDL oxidation and candidate geromarkers from the MARK-AGE data

The predictive value of the susceptibility to oxidation of LDL particles (LDLox) in cardiometabolic risk assessment is incompletely understood. The main objective of the current study was to assess its relationship with other relevant biomarkers and cardiometabolic risk factors from MARK-AGE data. A cross-sectional observational study was carried out on 1089 subjects (528 men and 561 women), aged 40-75 years old, randomly recruited age- and sex-stratified individuals from the general population. A correlation analysis exploring the relationships between LDLox and relevant biomarkers was undertaken, as well as the development and validation of several machine learning algorithms, for estimating the risk of the combined status of high blood pressure and obesity for the MARK-AGE subjects. The machine learning models yielded Area Under the Receiver Operating Characteristic Curve Score ranging 0.783-0.839 for the internal validation, while the external validation resulted in an Under the Receiver Operating Characteristic Curve Score between 0.648 and 0.787, with the variables based on LDLox reaching significant importance within the obtained predictions. The current study offers novel insights regarding the combined effects of LDL oxidation and other ageing markers on cardiometabolic risk. Future studies might be extended on larger patient cohorts, in order to obtain reproducible clinical assessment models.

Visualization obesity risk prediction system based on machine learning

Obesity is closely associated with various chronic diseases.Therefore, accurate, reliable and cost-effective methods for preventing its occurrence and progression are required. In this study, we developed a visualized obesity risk prediction system based on machine learning techniques, aiming to achieve personalized comprehensive health management for obesity. The system utilized a dataset consisting of 1678 anonymized health examination records, including individual lifestyle factors, body composition, blood routine, and biochemical tests. Ten multi-classification machine learning models, including Random Forest and XGBoost, were constructed to identify non-obese individuals (BMI < 25), class 1 obese individuals (25 ≤ BMI < 30), and class 2 obese individuals (30 ≤ BMI). By evaluating the performance of each model on the test set, we selected XGBoost as the best model and built the visualized obesity risk prediction system based on it. The system exhibited good predictive performance and interpretability, directly providing users with their obesity risk levels and determining corresponding intervention priorities. In conclusion, the developed obesity risk prediction system possesses high accuracy and interactivity, aiding physicians in formulating personalized health management plans and achieving comprehensive and accurate obesity management.

A growth curve model to estimate longitudinal effects of parental BMI on Indonesian children's growth patterns

The global surge in childhood obesity is also evident in Indonesia. Parental body mass index (BMI) values were found to be one of the major determinants of the increasing prevalence of childhood obesity. It is uncertain if parental BMI during their offspring's childhood significantly affects their children's BMI trajectories into adulthood. We aimed to investigate the influence of parental BMI Z-scores on BMI trajectories of Indonesian school-aged children, with a focus on sex-specific effects. This study utilized data from the Indonesian Family Life Survey and tracked the same respondents over four time points, from wave 2 (1997-1998) to wave 5 (2014-2015). The sample of this study consisted of children aged 5-12 years in wave 2 for whom height and weight data were available. We utilized a two-level growth curve model to account for the hierarchical structure of the data, with time nested within individual children. Fathers' BMI Z-scores in wave 2 had a pronounced influence (β = 0.31) on female children's BMI Z-scores compared to the influence of mothers' BMI Z-scores (β = 0.17). Mothers' BMI Z-scores in wave 2 showed a stronger positive association with male children's BMI Z-scores (β = 0.22) than did the father's BMI Z-scores (β = 0.19). A significant interaction of fathers' BMI Z-scores and years of follow-up was found for male children. As male children's BMI Z-scores increased by year, this effect was stronger in those whose fathers' BMI Z-scores were at a higher level. In conclusion, we found that parental BMI values profoundly influenced their children's BMI trajectories.

Does machine learning have a high performance to predict obesity among adults and older adults? A systematic review and meta-analysis

AIM

Machine learning may be a tool with the potential for obesity prediction. This study aims to review the literature on the performance of machine learning models in predicting obesity and to quantify the pooled results through a meta-analysis.

DATA SYNTHESIS

A systematic review and meta-analysis were conducted, including studies that used machine learning to predict obesity. Searches were conducted in October 2023 across databases including LILACS, Web of Science, Scopus, Embase, and CINAHL. We included studies that utilized classification models and reported results in the Area Under the ROC Curve (AUC) (PROSPERO registration: CRD42022306940), without imposing restrictions on the year of publication. The risk of bias was assessed using an adapted version of the Transparent Reporting of a multivariable prediction model for individual Prognosis or Diagnosis (TRIPOD). Meta-analysis was conducted using MedCalc software. A total of 14 studies were included, with the majority demonstrating satisfactory performance for obesity prediction, with AUCs exceeding 0.70. The random forest algorithm emerged as the top performer in obesity prediction, achieving an AUC of 0.86 (95%CI: 0.76-0.96; I2: 99.8%), closely followed by logistic regression with an AUC of 0.85 (95%CI: 0.75-0.95; I2: 99.6%). The least effective model was gradient boosting, with an AUC of 0.77 (95%CI: 0.71-0.82; I2: 98.1%).

CONCLUSION

Machine learning models demonstrated satisfactory predictive performance for obesity. However, future research should utilize more comparable data, larger databases, and a broader range of machine learning models.

Combination of Machine Learning Techniques to Predict Overweight/Obesity in Adults

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately.

Unraveling the Potential of Attentive Bi-LSTM for Accurate Obesity Prognosis: Advancing Public Health towards Sustainable Cities

The global prevalence of obesity presents a pressing challenge to public health and healthcare systems, necessitating accurate prediction and understanding for effective prevention and management strategies. This article addresses the need for improved obesity prediction models by conducting a comprehensive analysis of existing machine learning (ML) and deep learning (DL) approaches. This study introduces a novel hybrid model, Attention-based Bi-LSTM (ABi-LSTM), which integrates attention mechanisms with bidirectional Long Short-Term Memory (Bi-LSTM) networks to enhance interpretability and performance in obesity prediction. Our study fills a crucial gap by bridging healthcare and urban planning domains, offering insights into data-driven approaches to promote healthier living within urban environments. The proposed ABi-LSTM model demonstrates exceptional performance, achieving a remarkable accuracy of 96.5% in predicting obesity levels. Comparative analysis showcases its superiority over conventional approaches, with superior precision, recall, and overall classification balance. This study highlights significant advancements in predictive accuracy and positions the ABi-LSTM model as a pioneering solution for accurate obesity prognosis. The implications extend beyond healthcare, offering a precise tool to address the global obesity epidemic and foster sustainable development in smart cities.

Machine learning techniques for the identification of risk factors associated with food insecurity among adults in Arab countries during the COVID-19 pandemic

BACKGROUND

A direct consequence of global warming, and strongly correlated with poor physical and mental health, food insecurity is a rising global concern associated with low dietary intake. The Coronavirus pandemic has further aggravated food insecurity among vulnerable communities, and thus has sparked the global conversation of equal food access, food distribution, and improvement of food support programs. This research was designed to identify the key features associated with food insecurity during the COVID-19 pandemic using Machine learning techniques. Seven machine learning algorithms were used in the model, which used a dataset of 32 features. The model was designed to predict food insecurity across ten Arab countries in the Gulf and Mediterranean regions. A total of 13,443 participants were extracted from the international Corona Cooking Survey conducted by 38 different countries during the COVID -19 pandemic.

RESULTS

The findings indicate that Jordanian, Palestinian, Lebanese, and Saudi Arabian respondents reported the highest rates of food insecurity in the region (15.4%, 13.7%, 13.7% and 11.3% respectively). On the other hand, Oman and Bahrain reported the lowest rates (5.4% and 5.5% respectively). Our model obtained accuracy levels of 70%-82% in all algorithms. Gradient Boosting and Random Forest techniques had the highest performance levels in predicting food insecurity (82% and 80% respectively). Place of residence, age, financial instability, difficulties in accessing food, and depression were found to be the most relevant features associated with food insecurity.

CONCLUSIONS

The ML algorithms seem to be an effective method in early detection and prediction of food insecurity and can profoundly aid policymaking. The integration of ML approaches in public health strategies could potentially improve the development of targeted and effective interventions to combat food insecurity in these regions and globally.

Setmelanotide optimization through fragment-growing, molecular docking in-silico method targeting MC4 receptor

Obesity has emerged as a global issue, but with the complex structures of multiple related important targets and their agonists or antagonists determined, the mechanism of ligand-protein interaction may offer new chances for developing new generation agonists anti-obesity. Based on the molecule surface of the cryo-EM protein structure 7AUE, we tried to replace D-Ala3 with D-Met in setmelanotide as the linker site for fragment-growing with De novo evolution. The simulation results indicate that the derivatives could improve the binding abilities with the melanocortin 4 receptor and the selectivity over the melanocortin 1 receptor. The improved selectivity of the newly designed derivatives is mainly due to the shape difference of the molecular surface at the orthosteric peptide-binding pocket between melanocortin 4 receptor and melanocortin 1 receptor. The new extended fragments could not only enhance the binding affinities but also function as a gripper to seize the pore, making it easier to balance and stabilize the other component of the new derivatives. Although it is challenging to synthesize the compounds designed in silico, this study may perhaps serve as a trigger for additional anti-obesity research.Communicated by Ramaswamy H. Sarma.

Age-specific risk factors for the prediction of obesity using a machine learning approach

Machine Learning is a powerful tool to discover hidden information and relationships in various data-driven research fields. Obesity is an extremely complex topic, involving biological, physiological, psychological, and environmental factors. One successful approach to the topic is machine learning frameworks, which can reveal complex and essential risk factors of obesity. Over the last two decades, the obese population (BMI of above 23) in Korea has grown. The purpose of this study is to identify risk factors that predict obesity using machine learning classifiers and identify the algorithm with the best accuracy among classifiers used for obesity prediction. This work will allow people to assess obesity risk from blood tests and blood pressure data based on the KNHANES, which used data constructed by the annual survey. Our data include a total of 21,100 participants (male 10,000 and female 11,100). We assess obesity prediction by utilizing six machine learning algorithms. We explore age- and gender-specific risk factors of obesity for adults (19-79 years old). Our results highlight the four most significant features in all age-gender groups for predicting obesity: triglycerides, ALT (SGPT), glycated hemoglobin, and uric acid. Our findings show that the risk factors for obesity are sensitive to age and gender under different machine learning algorithms. Performance is highest for the 19-39 age group of both genders, with over 70% accuracy and AUC, while the 60-79 age group shows around 65% accuracy and AUC. For the 40-59 age groups, the proposed algorithm achieved over 70% in AUC, but for the female participants, it achieved lower than 70% accuracy. For all classifiers and age groups, there is no big difference in the accuracy ratio when the number of features is more than six; however, the accuracy ratio decreased in the female 19-39 age group.

Predicting Childhood Obesity Based on Single and Multiple Well-Child Visit Data Using Machine Learning Classifiers

Childhood obesity is a public health concern in the United States. Consequences of childhood obesity include metabolic disease and heart, lung, kidney, and other health-related comorbidities. Therefore, the early determination of obesity risk is needed and predicting the trend of a child's body mass index (BMI) at an early age is crucial. Early identification of obesity can lead to early prevention. Multiple methods have been tested and evaluated to assess obesity trends in children. Available growth charts help determine a child's current obesity level but do not predict future obesity risk. The present methods of predicting obesity include regression analysis and machine learning-based classifications and risk factor (threshold)-based categorizations based on specific criteria. All the present techniques, especially current machine learning-based methods, require longitudinal data and information on a large number of variables related to a child's growth (e.g., socioeconomic, family-related factors) in order to predict future obesity-risk. In this paper, we propose three different techniques for three different scenarios to predict childhood obesity based on machine learning approaches and apply them to real data. Our proposed methods predict obesity for children at five years of age using the following three data sets: (1) a single well-child visit, (2) multiple well-child visits under the age of two, and (3) multiple random well-child visits under the age of five. Our models are especially important for situations where only the current patient information is available rather than having multiple data points from regular spaced well-child visits. Our models predict obesity using basic information such as birth BMI, gestational age, BMI measures from well-child visits, and gender. Our models can predict a child's obesity category (normal, overweight, or obese) at five years of age with an accuracy of 89%, 77%, and 89%, for the three application scenarios, respectively. Therefore, our proposed models can assist healthcare professionals by acting as a decision support tool to aid in predicting childhood obesity early in order to reduce obesity-related complications, and in turn, improve healthcare.

Applications of Artificial Intelligence to Obesity Research: Scoping Review of Methodologies

BACKGROUND

Obesity is a leading cause of preventable death worldwide. Artificial intelligence (AI), characterized by machine learning (ML) and deep learning (DL), has become an indispensable tool in obesity research.

OBJECTIVE

This scoping review aimed to provide researchers and practitioners with an overview of the AI applications to obesity research, familiarize them with popular ML and DL models, and facilitate the adoption of AI applications.

METHODS

We conducted a scoping review in PubMed and Web of Science on the applications of AI to measure, predict, and treat obesity. We summarized and categorized the AI methodologies used in the hope of identifying synergies, patterns, and trends to inform future investigations. We also provided a high-level, beginner-friendly introduction to the core methodologies to facilitate the dissemination and adoption of various AI techniques.

RESULTS

We identified 46 studies that used diverse ML and DL models to assess obesity-related outcomes. The studies found AI models helpful in detecting clinically meaningful patterns of obesity or relationships between specific covariates and weight outcomes. The majority (18/22, 82%) of the studies comparing AI models with conventional statistical approaches found that the AI models achieved higher prediction accuracy on test data. Some (5/46, 11%) of the studies comparing the performances of different AI models revealed mixed results, indicating the high contingency of model performance on the data set and task it was applied to. An accelerating trend of adopting state-of-the-art DL models over standard ML models was observed to address challenging computer vision and natural language processing tasks. We concisely introduced the popular ML and DL models and summarized their specific applications in the studies included in the review.

CONCLUSIONS

This study reviewed AI-related methodologies adopted in the obesity literature, particularly ML and DL models applied to tabular, image, and text data. The review also discussed emerging trends such as multimodal or multitask AI models, synthetic data generation, and human-in-the-loop that may witness increasing applications in obesity research.

Predicting Overweight and Obesity Status Among Malaysian Working Adults With Machine Learning or Logistic Regression: Retrospective Comparison Study

BACKGROUND

Overweight or obesity is a primary health concern that leads to a significant burden of noncommunicable disease and threatens national productivity and economic growth. Given the complexity of the etiology of overweight or obesity, machine learning (ML) algorithms offer a promising alternative approach in disentangling interdependent factors for predicting overweight or obesity status.

OBJECTIVE

This study examined the performance of 3 ML algorithms in comparison with logistic regression (LR) to predict overweight or obesity status among working adults in Malaysia.

METHODS

Using data from 16,860 participants (mean age 34.2, SD 9.0 years; n=6904, 41% male; n=7048, 41.8% with overweight or obesity) in the Malaysia's Healthiest Workplace by AIA Vitality 2019 survey, predictor variables, including sociodemographic characteristics, job characteristics, health and weight perceptions, and lifestyle-related factors, were modeled using the extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) algorithms, as well as LR, to predict overweight or obesity status based on a BMI cutoff of 25 kg/m².

RESULTS

The area under the receiver operating characteristic curve was 0.81 (95% CI 0.79-0.82), 0.80 (95% CI 0.79-0.81), 0.80 (95% CI 0.78-0.81), and 0.78 (95% CI 0.77-0.80) for the XGBoost, RF, SVM, and LR models, respectively. Weight satisfaction was the top predictor, and ethnicity, age, and gender were also consistent predictor variables of overweight or obesity status in all models.

CONCLUSIONS

Based on multi-domain online workplace survey data, this study produced predictive models that identified overweight or obesity status with moderate to high accuracy. The performance of both ML-based and logistic regression models were comparable when predicting obesity among working adults in Malaysia.

IoT Framework for a Decision-Making System of Obesity and Overweight Extrapolation among Children, Youths, and Adults

Approximately 30% of the global population is suffering from obesity and being overweight, which is approximately 2.1 billion people worldwide. The ratio is expected to surpass 40% by 2030 if the current balance continues to grow. The global pandemic due to COVID-19 will also impact the predicted obesity rates. It will cause a significant increase in morbidity and mortality worldwide. Multiple chronic diseases are associated with obesity and several threat elements are associated with obesity. Various challenges are involved in the understanding of risk factors and the ratio of obesity. Therefore, diagnosing obesity in its initial stages might significantly increase the patient’s chances of effective treatment. The Internet of Things (IoT) has attained an evolving stage in the development of the contemporary environment of healthcare thanks to advancements in information and communication technologies. Therefore, in this paper, we thoroughly investigated machine learning techniques for making an IoT-enabled system. In the first phase, the proposed system analyzed the performances of random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), logistic regression (LR), and naïve Bayes (NB) algorithms on the obesity dataset. The second phase, on the other hand, introduced an IoT-based framework that adopts a multi-user request system by uploading the data to the cloud for the early diagnosis of obesity. The IoT framework makes the system available to anyone (and everywhere) for precise obesity categorization. This research will help the reader understand the relationships among risk factors with weight changes and their visualizations. Furthermore, it also focuses on how existing datasets can help one study the obesity nature and which classification and regression models perform well in correspondence to others.

Obesity Risk-Factor Variation Based on Island Clusters: A Secondary Analysis of Indonesian Basic Health Research 2018

Obesity has become a rising global health problem affecting quality of life for adults. The objective of this study is to describe the prevalence of obesity in Indonesian adults based on the cluster of islands. The study also aims to identify the risk factors of obesity in each island cluster. This study analyzes the secondary data of Indonesian Basic Health Research 2018. Data for this analysis comprised 618,910 adults (≥18 years) randomly selected, proportionate to the population size throughout Indonesia. We included 20 variables for the socio-demographic and obesity-related risk factors for analysis. The obesity status was defined using Body Mass Index (BMI) ≥ 25 kg/m². Our current study defines 7 major island clusters as the unit analysis consisting of 34 provinces in Indonesia. Descriptive analysis was conducted to determine the characteristics of the population and to calculate the prevalence of obesity within the provinces in each of the island clusters. Multivariate logistic regression analyses to calculate the odds ratios (ORs) was performed using SPSS version 27. The study results show that all the island clusters have at least one province with an obesity prevalence above the national prevalence (35.4%). Six out of twenty variables, comprising four dietary factors (the consumption of sweet food, high-salt food, meat, and carbonated drinks) and one psychological factor (mental health disorders), varied across the island clusters. In conclusion, there was a variation of obesity prevalence of the provinces within and between island clusters. The variation of risk factors found in each island cluster suggests that a government rethink of the current intervention strategies to address obesity is recommended.

Using Machine Learning to Predict Obesity Based on Genome-Wide and Epigenome-Wide Gene-Gene and Gene-Diet Interactions

Obesity is associated with many chronic diseases that impair healthy aging and is governed by genetic, epigenetic, and environmental factors and their complex interactions. This study aimed to develop a model that predicts an individual's risk of obesity by better characterizing these complex relations and interactions focusing on dietary factors. For this purpose, we conducted a combined genome-wide and epigenome-wide scan for body mass index (BMI) and up to three-way interactions among 402,793 single nucleotide polymorphisms (SNPs), 415,202 DNA methylation sites (DMSs), and 397 dietary and lifestyle factors using the generalized multifactor dimensionality reduction (GMDR) method. The training set consisted of 1,573 participants in exam 8 of the Framingham Offspring Study (FOS) cohort. After identifying genetic, epigenetic, and dietary factors that passed statistical significance, we applied machine learning (ML) algorithms to predict participants' obesity status in the test set, taken as a subset of independent samples (n = 394) from the same cohort. The quality and accuracy of prediction models were evaluated using the area under the receiver operating characteristic curve (ROC-AUC). GMDR identified 213 SNPs, 530 DMSs, and 49 dietary and lifestyle factors as significant predictors of obesity. Comparing several ML algorithms, we found that the stochastic gradient boosting model provided the best prediction accuracy for obesity with an overall accuracy of 70%, with ROC-AUC of 0.72 in test set samples. Top predictors of the best-fit model were 21 SNPs, 230 DMSs in genes such as CPT1A, ABCG1, SLC7A11, RNF145, and SREBF1, and 26 dietary factors, including processed meat, diet soda, French fries, high-fat dairy, artificial sweeteners, alcohol intake, and specific nutrients and food components, such as calcium and flavonols. In conclusion, we developed an integrated approach with ML to predict obesity using omics and dietary data. This extends our knowledge of the drivers of obesity, which can inform precision nutrition strategies for the prevention and treatment of obesity. Clinical Trial Registration: [www.ClinicalTrials.gov], the Framingham Heart Study (FHS), [NCT00005121].

Regional disparities in postnatal care among mothers aged 15-49 years old: An analysis of the Indonesian Demographic and Health Survey 2017

Background: In Indonesia, maternal mortality remains high, significantly 61.59% occur in the postnatal period. Postnatal care (PNC) provision is a critical intervention between six hours and 42 days after childbirth and is the primary strategy to reduce maternal mortality rates. However, underutilisation of PNC in Indonesia still remains high, and limited studies have shown the regional disparities of PNC in Indonesia. Methods: This study aims to explore the gaps between regions in PNC service for mothers who have had live births during the last five years in Indonesia. This study was a secondary data analysis study using the Indonesian Demographic and Health Survey (IDHS) in 2017. A total of 13,901 mothers aged 15-49 years having had live births within five years were included. Chi-squared test and binary logistic regression were performed to determine regional disparities in PNC. Results: Results indicated that the prevalence of PNC service utilisation among mothers aged 15-49 years was 70.94%. However, regional gaps in the utilisation of PNC service were indicated. Mothers in the Central of Indonesia have used PNC services 2.54 times compared to mothers in the Eastern of Indonesia (OR = 2.54; 95% CI = 1.77-3.65, p<0.001). Apart from the region, other variables have a positive relationship with PNC service, including wealth quintile, accessibility health facilities, age of children, childbirth order, mother's education, maternal occupation, spouse's age, and spouse's education. Conclusion: The results suggest the need for national policy focuses on service equality, accessible, and reliable implementation to improve postnatal care utilisation among mothers to achieve the maximum results for the Indonesian Universal Health Coverage plan.