When two heads are better than one: nutritional epidemiology meets machine learning

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.

Development of machine learning prediction models to explore nutrients predictive of cardiovascular disease using Canadian linked population-based data

Machine learning may improve use of observational data to understand the nutritional epidemiology of cardiovascular disease (CVD) through better modelling of non-linearity, non-additivity, and dietary complexity. Our objective was to develop machine learning prediction models for exploring how nutrients are related to CVD risk and to evaluate their predictive performance. We established a population-based cohort from the Canadian Community Health Survey and measured CVD incidence and mortality from 2004 to 2018 using administrative databases of national hospital discharges and deaths. Predictors included 61 nutrition variables and fourteen socioeconomic, demographic, psychological, and behavioural variables. Conditional inference forest models were interpreted and evaluated by permutation feature importance, accumulated local effects, and predictive discrimination and calibration. A total of 12 130 individuals were included in the study. Use of supplements, caffeine, and alcohol were the most important nutrition variables for prediction of CVD. Supplement use was associated with decreased risk, caffeine was associated with increasing risk, and alcohol had a u-shaped association with risk. The model had an out-of-sample c-statistic of 0.821 (95% confidence interval = 0.801-0.842). Exploratory findings included both known and novel associations and predictive performance was competitive, suggesting that further application of machine learning to nutritional epidemiology may help elucidate risks and improve predictive models. Novelty: Machine learning prediction models were developed for CVD using dietary data. Models were interpreted with interpretable machine learning techniques, revealing diverse associations between diet and CVD. Models achieved comparable or superior predictive performance to existing CVD risk prediction models.

Perspective: Big Data and Machine Learning Could Help Advance Nutritional Epidemiology

The field of nutritional epidemiology faces challenges posed by measurement error, diet as a complex exposure, and residual confounding. The objective of this perspective article is to highlight how developments in big data and machine learning can help address these challenges. New methods of collecting 24-h dietary recalls and recording diet could enable larger samples and more repeated measures to increase statistical power and measurement precision. In addition, use of machine learning to automatically classify pictures of food could become a useful complimentary method to help improve precision and validity of dietary measurements. Diet is complex due to thousands of different foods that are consumed in varying proportions, fluctuating quantities over time, and differing combinations. Current dietary pattern methods may not integrate sufficient dietary variation, and most traditional modeling approaches have limited incorporation of interactions and nonlinearity. Machine learning could help better model diet as a complex exposure with nonadditive and nonlinear associations. Last, novel big data sources could help avoid unmeasured confounding by offering more covariates, including both omics and features derived from unstructured data with machine learning methods. These opportunities notwithstanding, application of big data and machine learning must be approached cautiously to ensure quality of dietary measurements, avoid overfitting, and confirm accurate interpretations. Greater use of machine learning and big data would also require substantial investments in training, collaborations, and computing infrastructure. Overall, we propose that judicious application of big data and machine learning in nutrition science could offer new means of dietary measurement, more tools to model the complexity of diet and its relations with diseases, and additional potential ways of addressing confounding.