Joint Associations of Multiple Dietary Components With Cardiovascular Disease Risk: A Machine-Learning Approach

Advances in methods for characterizing dietary patterns: A scoping review

There is a growing focus on better understanding the complexity of dietary patterns and how they relate to health and other factors. Approaches that have not traditionally been applied to characterize dietary patterns, such as machine learning algorithms and latent class analysis methods, may offer opportunities to measure and characterize dietary patterns in greater depth than previously considered. However, there has not been a formal examination of how this wide range of approaches has been applied to characterize dietary patterns. This scoping review synthesized literature from 2005-2022 applying methods not traditionally used to characterize dietary patterns, referred to as novel methods. MEDLINE, CINAHL, and Scopus were searched using keywords including machine learning, latent class analysis, and least absolute shrinkage and selection operator (LASSO). Of 5274 records identified, 24 met the inclusion criteria. Twelve of 24 articles were published since 2020. Studies were conducted across 17 countries. Nine studies used approaches that have applications in machine learning to identify dietary patterns. Fourteen studies assessed associations between dietary patterns that were characterized using novel methods and health outcomes, including cancer, cardiovascular disease, and asthma. There was wide variation in the methods applied to characterize dietary patterns and in how these methods were described. The extension of reporting guidelines and quality appraisal tools relevant to nutrition research to consider specific features of novel methods may facilitate complete and consistent reporting and enable evidence synthesis to inform policies and programs aimed at supporting healthy dietary patterns.

The association between trace metals in both cancerous and non-cancerous tissues with the risk of liver and gastric cancer progression in northwest China

Liver cancer and gastric cancer have extremely high morbidity and mortality rates worldwide. It is well known that an increase or decrease in trace metals may be associated with the formation and development of a variety of diseases, including cancer. Therefore, this study aimed to evaluate the contents of aluminium (Al), arsenic (As), cadmium (Cd), cobalt (Co), chromium (Cr), copper (Cu), iron (Fe), manganese (Mn), nickel (Ni), lead (Pb), selenium (Se), and zinc (Zn) in cancerous liver and gastric tissues, compared to adjacent healthy tissues, and to investigate the relationship between trace metals and cancer progression. During surgery, multiple samples were taken from the cancerous and adjacent healthy tissues of patients with liver and gastric cancer, and trace metal levels within these samples were analysed using inductively coupled plasma mass spectrometry (ICP-MS). We found that concentrations of As, Cd, Co, Cr, Cu, Fe, Mn, Ni, Pb, Se, and Zn in tissues from patients with liver cancer were significantly lower than those in healthy controls (P < 0.05). Similarly, patients with gastric cancer also showed lower levels of Cd, Co, Cr, Mn, Ni, and Zn-but higher levels of Cu and Se-compared to the controls (P < 0.05). In addition, patients with liver and gastric cancers who had poorly differentiated tumours and positive lymph node metastases showed lower levels of trace metals (P < 0.05), although no significant changes in their concentrations were observed to correlate with sex, age, or body mass index (BMI). Logistic regression, principal component analysis (PCA), Bayesian kernel regression (BKMR), weighted quantile sum (WQS) regression, and quantile-based g computing (qgcomp) models were used to analyse the relationships between trace metal concentrations in liver and gastric cancer tissues and the progression of these cancers. We found that single or mixed trace metal levels were negatively associated with poor differentiation and lymph node metastasis in both liver and gastric cancer, and the posterior inclusion probability (PIP) of each metal showed that Cd contributed the most to poor differentiation and lymph node metastasis in both liver and gastric cancer (all PIP = 1.000). These data help to clarify the relationship between changes in trace metal levels in cancerous liver and gastric tissues and the progression of these cancers. Further research is warranted, however, to fully elucidate the mechanisms and causations underlying these findings.

"We adjusted for race": now what? A systematic review of utilization and reporting of race in American Journal of Epidemiology and Epidemiology, 2020-2021

Race is a social construct, commonly used in epidemiologic research to adjust for confounding. However, adjustment of race may mask racial disparities, thereby perpetuating structural racism. We conducted a systematic review of articles published in Epidemiology and American Journal of Epidemiology between 2020 and 2021 to (1) understand how race, ethnicity, and similar social constructs were operationalized, used, and reported; and (2) characterize good and poor practices of utilization and reporting of race data on the basis of the extent to which they reveal or mask systemic racism. Original research articles were considered for full review and data extraction if race data were used in the study analysis. We extracted how race was categorized, used-as a descriptor, confounder, or for effect measure modification (EMM)-and reported if the authors discussed racial disparities and systemic bias-related mechanisms responsible for perpetuating the disparities. Of the 561 articles, 299 had race data available and 192 (34.2%) used race data in analyses. Among the 160 US-based studies, 81 different racial categorizations were used. Race was most often used as a confounder (52%), followed by effect measure modifier (33%), and descriptive variable (12%). Fewer than 1 in 4 articles (22.9%) exhibited good practices (EMM along with discussing disparities and mechanisms), 63.5% of the articles exhibited poor practices (confounding only or not discussing mechanisms), and 13.5% were considered neither poor nor good practices. We discuss implications and provide 13 recommendations for operationalization, utilization, and reporting of race in epidemiologic and public health research.

Predicting Cardiovascular Disease Mortality: Leveraging Machine Learning for Comprehensive Assessment of Health and Nutrition Variables

Cardiovascular disease (CVD) is one of the primary causes of death around the world. This study aimed to identify risk factors associated with CVD mortality using data from the National Health and Nutrition Examination Survey (NHANES). We created three models focusing on dietary data, non-diet-related health data, and a combination of both. Machine learning (ML) models, particularly the random forest algorithm, demonstrated robust consistency across health, nutrition, and mixed categories in predicting death from CVD. Shapley additive explanation (SHAP) values showed age, systolic blood pressure, and several other health factors as crucial variables, while fiber, calcium, and vitamin E, among others, were significant nutritional variables. Our research emphasizes the importance of comprehensive health evaluation and dietary intake in predicting CVD mortality. The inclusion of nutrition variables improved the performance of our models, underscoring the utility of dietary intake in ML-based data analysis. Further investigation using large datasets with recurring dietary recalls is necessary to enhance the effectiveness and interpretability of such models.

Interrogating Components of 2 Diet Quality Indices in Pregnancy using a Supervised Statistical Mixtures Approach

BACKGROUND

The Healthy Eating Index (HEI)-2015 and Alternative Healthy Eating Index (AHEI)-2010 evaluate diet holistically in pregnancy. However, it remains unclear how individual index components interact to contribute to health.

OBJECTIVES

To evaluate associations of HEI-2015 and AHEI-2010 components with gestational length using traditional and novel statistical methods in a prospective cohort.

METHODS

Pregnant women completed a 3-mo food-frequency questionnaire (FFQ) at median 13 wk gestation to calculate the HEI-2015 or AHEI-2010. Covariate-adjusted linear regression models evaluated associations of HEI-2015 and AHEI-2010 total scores and individual components (one at a time and simultaneously adjusted) with gestational length. Covariate-adjusted weighted quantile sum regression models evaluated 1) associations of HEI-2015 or AHEI-2010 components as mixtures with gestational length and 2) contributions of components to these associations.

RESULTS

Each 10-point increase in HEI-2015 and AHEI-2010 total score was associated with 0.11 (95% CI: -0.05, 0.27) and 0.14 (95% CI: 0.00, 0.28) wk longer gestation, respectively. In individual or simultaneously adjusted HEI-2015 models, higher intakes of seafood/plant proteins, total protein foods, greens/beans, and saturated fats but lower intakes of added sugars and refined grains were associated with longer gestational length. For the AHEI-2010, higher intake of nuts/legumes and lower intake of sugar-sweetened beverages (SSBs)/fruit juice were associated with longer gestational length. Jointly, 10% increases in HEI-2015 or AHEI-2010 mixtures were associated with 0.17 (95% CI: 0.001, 0.34) and 0.18 (95% CI: 0.05, 0.30) wk longer gestational length, respectively. Seafood/plant protein, total protein foods, dairy, greens/beans, and added sugars were the largest contributors to the HEI-2015 mixture. Nuts/legumes, SSBs/fruit juice, sodium, and DHA/EPA were the largest contributors to the AHEI-2010 mixture. Associations were less precise but consistent in women with spontaneous labors.

CONCLUSIONS

Compared to traditional methods, associations of diet index mixtures with gestational length were more robust and identified unique contributors. Additional studies could consider interrogating these statistical approaches using other dietary indices and health outcomes.

Leveraging Machine Learning Techniques to Forecast Chronic Total Occlusion before Coronary Angiography

BACKGROUND

Chronic total occlusion (CTO) remains the most challenging procedure in coronary artery disease (CAD) for interventional cardiology. Although some clinical risk factors for CAD have been identified, there is no personalized prognosis test available to confidently identify patients at high or low risk for CTO CAD. This investigation aimed to use a machine learning algorithm for clinical features from clinical routine to develop a precision medicine tool to predict CTO before CAG.

METHODS

Data from 1473 CAD patients were obtained, including 1105 in the training cohort and 368 in the testing cohort. The baseline clinical characteristics were collected. Univariate and multivariate logistic regression analyses were conducted to identify independent risk factors that impact the diagnosis of CTO. A CTO predicting model was established and validated based on the independent predictors using a machine learning algorithm. The area under the curve (AUC) was used to evaluate the model.

RESULTS

The CTO prediction model was developed with the training cohort using the machine learning algorithm. Eight variables were confirmed as 'important': gender (male), neutrophil percentage (NE%), hematocrit (HCT), total cholesterol (TC), high-density lipoprotein cholesterol (HDL), ejection fraction (EF), troponin I (TnI), and N-terminal pro-B-type natriuretic peptide (NT-proBNP). The model achieved good concordance indices of 0.724 and 0.719 in the training and testing cohorts, respectively.

CONCLUSIONS

An easy-to-use tool to predict CTO in patients with CAD was developed and validated. More research with larger cohorts are warranted to improve the prediction model, which can support clinician decisions on the early discerning CTO in CAD patients.

Joint Associations of Food Groups with All-Cause and Cause-Specific Mortality in the Mr. OS and Ms. OS Study: A Prospective Cohort

Despite continuous growth in dietary pattern research, the relative importance of each dietary component in the overall pattern and their joint effects on mortality risk have not been examined adequately. We explored the individual and joint associations of multiple food groups with all-cause and cause-specific mortality (cardiovascular disease (CVD) or cancer), by analyzing data from a cohort of 3995 Hong Kong Chinese older adults in the Mr. Osteoporosis (OS) and Ms. OS Study. Cox proportional hazards models were used to examine the associations of food groups with mortality risk. The individual and joint contribution of food groups to mortality risk has been quantified by a machine learning approach, i.e., the Quantile G-Computation. When comparing the highest with the lowest quartile of intake, dark green and leafy vegetables (hazard ratio (HR) = 0.82, 95% confidence interval (CI) = 0.70 to 0.96, Ptrend = 0.049), fruit (HR = 0.79, 95% CI = 0.68 to 0.93, Ptrend = 0.006), legumes (HR = 0.75, 95% CI = 0.63 to 0.87, Ptrend = 0.052), mushroom and fungi (HR = 0.76, 95% CI = 0.65 to 0.88, Ptrend = 0.023), soy and soy products (HR = 0.77, 95% CI = 0.66 to 0.90, Ptrend = 0.143), and whole grains (HR = 0.76, 95% CI = 0.65 to 0.89, Ptrend = 0.008) were inversely associated with all-cause mortality. Legume intake was associated with a lower risk of CVD mortality, while fruit, nuts, soy and soy products were associated with a lower risk of cancer mortality. From the Quantile G-Computation, whole grains, legumes, fruits, mushroom and fungi, soy and soy products had a higher relative weighting on mortality risk, and the joint effect of food groups was inversely associated with the mortality risk due to all-causes (HR = 0.39, 95% CI = 0.27 to 0.55), CVD (HR = 0.78, 95% CI = 0.67 to 0.91), and cancer (HR = 0.31, 95% CI = 0.15 to 0.65). From a sex-stratified analysis, most associations between food groups (whole grains, legumes, fruits, mushroom and fungi, soy and soy products) and mortality risk remained significant among men. In conclusion, whole grains, legumes, fruits, mushroom and fungi, soy and soy products were the main contributors to a reduction in mortality risk, and their joint effects were stronger than individual food groups. Moreover, the sex-specific association of sweets and desserts with cancer mortality may be worth further investigation.

Manganese Exposure and Metabolic Syndrome: A Systematic Review and Meta-Analysis

Manganese (Mn) is an essential element acting as a co-factor of superoxide dismutase, and it is potentially beneficial for cardiometabolic health by reducing oxidative stress. Although some studies have examined the relationship between Mn and metabolic syndrome (MetS), no systematic review and meta-analysis has been presented to summarize the evidence. Therefore, the present review examined the association between dietary and environmental Mn exposure, and MetS risk. A total of nine cross-sectional studies and three case-control studies were included, which assessed Mn from diet, serum, urine, and whole blood. The association of the highest Mn level from diet (three studies, odds ratio (OR): 0.83, 95% confidence interval (C.I.) = 0.57, 1.21), serum (two studies, OR: 0.87, 95% C.I. = 0.66, 1.14), urine (two studies, OR: 0.84, 95% C.I. = 0.59, 1.19), and whole blood (two studies, OR: 0.92, 95% C.I. = 0.53, 1.60) were insignificant, but some included studies have suggested a non-linear relationship of urinary and blood Mn with MetS, and higher dietary Mn may associate with a lower MetS risk in some of the included studies. While more evidence from prospective cohorts is needed, future studies should use novel statistical approaches to evaluate relative contribution of Mn on MetS risk along with other inter-related exposures.