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.

Identifying non-traditional electronic datasets for population-level surveillance and prevention of cardiometabolic diseases: a scoping review protocol.

INTRODUCTION: Cardiometabolic diseases, including cardiovascular disease, obesity and diabetes, are leading causes of death and disability worldwide. Modern advances in population-level disease surveillance are necessary and may inform novel opportunities for precision public health approaches to disease prevention. Electronic data sources, such as social media and consumer rewards points systems, have expanded dramatically in recent decades. These non-traditional datasets may enhance traditional clinical and public health datasets and inform cardiometabolic disease surveillance and population health interventions. However, the scope of non-traditional electronic datasets and their use for cardiometabolic disease surveillance and population health interventions has not been previously reviewed. The primary objective of this review is to describe the scope of non-traditional electronic datasets, and how they are being used for cardiometabolic disease surveillance and to inform interventions. The secondary objective is to describe the methods, such as machine learning and natural language processing, that have been applied to leverage these datasets. METHODS AND ANALYSIS: We will conduct a scoping review following recommended methodology. Search terms will be based on the three central concepts of non-traditional electronic datasets, cardiometabolic diseases and population health. We will search EMBASE, MEDLINE, CINAHL, Scopus, Web of Science and Cochrane Library peer-reviewed databases and will also conduct a grey literature search. Articles published from 2000 to present will be independently screened by two reviewers for inclusion at abstract and full-text stages, and conflicts will be resolved by a separate reviewer. We will report this data as per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews. ETHICS AND DISSEMINATION: No ethics approval is required for this protocol and scoping review, as data will be used only from published studies with appropriate ethics approval. Results will be disseminated in a peer-reviewed publication.

Impact of disasters, including pandemics, on cardiometabolic outcomes across the life-course: a systematic review.

BACKGROUND: Disasters are events that disrupt the daily functioning of a community or society, and may increase long-term risk of adverse cardiometabolic outcomes, including cardiovascular disease, obesity and diabetes. The objective of this study was to conduct a systematic review to determine the impact of disasters, including pandemics, on cardiometabolic outcomes across the life-course. DESIGN: A systematic search was conducted in May 2020 using two electronic databases, EMBASE and Medline. All studies were screened in duplicate at title and abstract, and full-text level. Studies were eligible for inclusion if they assessed the association between a population-level or community disaster and cardiometabolic outcomes ≥1 month following the disaster. There were no restrictions on age, year of publication, country or population. Data were extracted on study characteristics, exposure (eg, type of disaster, region, year), cardiometabolic outcomes and measures of effect. Study quality was evaluated using the Joanna Briggs Institute critical appraisal tools. RESULTS: A total of 58 studies were included, with 24 studies reporting the effects of exposure to disaster during pregnancy/childhood and 34 studies reporting the effects of exposure during adulthood. Studies included exposure to natural (n=35; 60%) and human-made (n=23; 40%) disasters, with only three (5%) of these studies evaluating previous pandemics. Most studies reported increased cardiometabolic risk, including increased cardiovascular disease incidence or mortality, diabetes and obesity, but not all. Few studies evaluated the biological mechanisms or high-risk subgroups that may be at a greater risk of negative health outcomes following disasters. CONCLUSIONS: The findings from this study suggest that the burden of disasters extend beyond the known direct harm, and attention is needed on the detrimental indirect long-term effects on cardiometabolic health. Given the current COVID-19 pandemic, these findings may inform public health prevention strategies to mitigate the impact of future cardiometabolic risk. PROSPERO REGISTRATION NUMBER: CRD42020186074.

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.

"AI's gonna have an impact on everything in society, so it has to have an impact on public health": a fundamental qualitative descriptive study of the implications of artificial intelligence for public health.

BACKGROUND: Our objective was to determine the impacts of artificial intelligence (AI) on public health practice. METHODS: We used a fundamental qualitative descriptive study design, enrolling 15 experts in public health and AI from June 2018 until July 2019 who worked in North America and Asia. We conducted in-depth semi-structured interviews, iteratively coded the resulting transcripts, and analyzed the results thematically. RESULTS: We developed 137 codes, from which nine themes emerged. The themes included opportunities such as leveraging big data and improving interventions; barriers to adoption such as confusion regarding AI's applicability, limited capacity, and poor data quality; and risks such as propagation of bias, exacerbation of inequity, hype, and poor regulation. CONCLUSIONS: Experts are cautiously optimistic about AI's impacts on public health practice, particularly for improving disease surveillance. However, they perceived substantial barriers, such as a lack of available expertise, and risks, including inadequate regulation. Therefore, investment and research into AI for public health practice would likely be beneficial. However, increased access to high-quality data, research and education regarding the limitations of AI, and development of rigorous regulation are necessary to realize these benefits.