Supermarket Transaction Records In Dietary Evaluation: the STRIDE study: validation against self-reported dietary intake.

OBJECTIVE: Scalable methods are required for population dietary monitoring. The Supermarket Transaction Records In Dietary Evaluation (STRIDE) study compares dietary estimates from supermarket transactions with an online FFQ. DESIGN: Participants were recruited in four waves, accounting for seasonal dietary variation. Purchases were collected for 1 year during and 1 year prior to the study. Bland-Altman agreement and limits of agreement (LoA) were calculated for energy, sugar, fat, saturated fat, protein and sodium (absolute and relative). SETTING: This study was partnered with a large UK retailer. PARTICIPANTS: Totally, 1788 participants from four UK regions were recruited from the retailer's loyalty card customer database, according to breadth and frequency of purchases. Six hundred and eighty-six participants were included for analysis. RESULTS: The analysis sample were mostly female (72 %), with a mean age of 56 years (sd 13). The ratio of purchases to intakes varied depending on amounts purchased and consumed; purchases under-estimated intakes for smaller amounts on average, but over-estimated for larger amounts. For absolute measures, the LoA across households were wide, for example, for energy intake of 2000 kcal, purchases could under- or over-estimate intake by a factor of 5; values could be between 400 kcal and 10000 kcal. LoA for relative (energy-adjusted) estimates were smaller, for example, for 14 % of total energy from saturated fat, purchase estimates may be between 7 % and 27 %. CONCLUSIONS: Agreement between purchases and intake was highly variable, strongest for smaller loyal households and for relative values. For some customers, relative nutrient purchases are a reasonable proxy for dietary composition indicating utility in population-level dietary research.

Objectively measuring the association between the built environment and physical activity: a systematic review and reporting framework.

BACKGROUND: Objective measures of built environment and physical activity provide the opportunity to directly compare their relationship across different populations and spatial contexts. This systematic review synthesises the current body of knowledge and knowledge gaps around the impact of objectively measured built environment metrics on physical activity levels in adults (≥ 18 years). Additionally, this review aims to address the need for improved quality of methodological reporting to evaluate studies and improve inter-study comparability though the creation of a reporting framework. METHODS: A systematic search of the literature was conducted following the PRISMA guidelines. After abstract and full-text screening, 94 studies were included in the final review. Results were synthesised using an association matrix to show overall association between built environment and physical activity variables. Finally, the new PERFORM ('Physical and Environmental Reporting Framework for Objectively Recorded Measures') checklist was created and applied to the included studies rating them on their reporting quality across four key areas: study design and characteristics, built environment exposures, physical activity metrics, and the association between built environment and physical activity. RESULTS: Studies came from 21 countries and ranged from two days to six years in duration. Accelerometers and using geographic information system (GIS) to define the spatial extent of exposure around a pre-defined geocoded location were the most popular tools to capture physical activity and built environment respectively. Ethnicity and socio-economic status of participants were generally poorly reported. Moderate-to-vigorous physical activity (MVPA) was the most common metric of physical activity used followed by walking. Commonly investigated elements of the built environment included walkability, access to parks and green space. Areas where there was a strong body of evidence for a positive or negative association between the built environment and physical activity were identified. The new PERFORM checklist was devised and poorly reported areas identified, included poor reporting of built environment data sources and poor justification of method choice. CONCLUSIONS: This systematic review highlights key gaps in studies objectively measuring the built environment and physical activity both in terms of the breadth and quality of reporting. Broadening the variety measures of the built environment and physical activity across different demographic groups and spatial areas will grow the body and quality of evidence around built environment effect on activity behaviour. Whilst following the PERFORM reporting guidance will ensure the high quality, reproducibility, and comparability of future research.

The impact of body mass index on breast cancer incidence among women at increased risk: an observational study from the International Breast Intervention Studies.

BACKGROUND: We investigated the association between body mass index (BMI) and breast cancer risk in women at increased risk of breast cancer receiving tamoxifen or anastrozole compared with placebo using data from the International Breast Cancer Intervention Studies [IBIS-I (tamoxifen) and IBIS-II (anastrozole)]. METHODS: Baseline BMI was calculated from nurse assessed height and weight measurements for premenopausal (n = 3138) and postmenopausal (n = 3731) women in IBIS-I and postmenopausal women in IBIS-II (n = 3787). The primary endpoint was any breast cancer event (invasive and ductal carcinoma in situ). We used Cox proportional hazards regression to calculate hazard ratios (HRs) for risk after adjustment for covariates. RESULTS: There were 582 (IBIS-I) and 248 (IBIS-II) breast cancer events [median follow-up = 16.2 years (IQR 14.4-17.7) and 10.9 years (IQR 8.8-13.0), respectively]. In adjusted analysis, women with a higher BMI had an increased breast cancer risk in both IBIS-I [HR = 1.06 per 5 kg/m2 (0.99-1.15), p = 0.114] and in IBIS-II [HR per 5 kg/m2 = 1.21 (1.09-1.35), p < 0.001]. In IBIS-I, the association between BMI and breast cancer risk was positive in postmenopausal women [adjusted HR per 5 kg/m2 = 1.14 (1.03-1.26), p = 0.01] but not premenopausal women [adjusted HR per 5 kg/m2 = 0.97 (0.86-1.09), p = 0.628]. There was no interaction between BMI and treatment group for breast cancer risk in either IBIS-I (p = 0.62) or IBIS-II (p = 0.55). CONCLUSIONS: Higher BMI is associated with greater breast cancer risk in postmenopausal women at increased risk of the disease, but no effect was observed in premenopausal women. The lack of interaction between BMI and treatment group on breast cancer risk suggests women are likely to experience benefit from preventive therapy regardless of their BMI. Trial registration Both trials were registered [IBIS-I: ISRCTN91879928 on 24/02/2006, retrospectively registered ( http://www.isrctn.com/ISRCTN91879928 ); IBIS-II: ISRCTN31488319 on 07/01/2005, retrospectively registered ( http://www.isrctn.com/ISRCTN31488319 )].

Understanding Barriers to Novel Data Linkages: Topic Modeling of the Results of the LifeInfo Survey.

BACKGROUND: Novel consumer and lifestyle data, such as those collected by supermarket loyalty cards or mobile phone exercise tracking apps, offer numerous benefits for researchers seeking to understand diet- and exercise-related risk factors for diseases. However, limited research has addressed public attitudes toward linking these data with individual health records for research purposes. Data linkage, combining data from multiple sources, provides the opportunity to enhance preexisting data sets to gain new insights. OBJECTIVE: The aim of this study is to identify key barriers to data linkage and recommend safeguards and procedures that would encourage individuals to share such data for potential future research. METHODS: The LifeInfo Survey consulted the public on their attitudes toward sharing consumer and lifestyle data for research purposes. Where barriers to data sharing existed, participants provided unstructured survey responses detailing what would make them more likely to share data for linkage with their health records in the future. The topic modeling technique latent Dirichlet allocation was used to analyze these textual responses to uncover common thematic topics within the texts. RESULTS: Participants provided responses related to sharing their store loyalty card data (n=2338) and health and fitness app data (n=1531). Key barriers to data sharing identified through topic modeling included data safety and security, personal privacy, requirements of further information, fear of data being accessed by others, problems with data accuracy, not understanding the reason for data linkage, and not using services that produce these data. We provide recommendations for addressing these issues to establish the best practice for future researchers interested in using these data. CONCLUSIONS: This study formulates a large-scale consultation of public attitudes toward this kind of data linkage, which is an important first step in understanding and addressing barriers to participation in research using novel consumer and lifestyle data.

Evidence from big data in obesity research: international case studies.

BACKGROUND/OBJECTIVE: Obesity is thought to be the product of over 100 different factors, interacting as a complex system over multiple levels. Understanding the drivers of obesity requires considerable data, which are challenging, costly and time-consuming to collect through traditional means. Use of 'big data' presents a potential solution to this challenge. Big data is defined by Delphi consensus as: always digital, has a large sample size, and a large volume or variety or velocity of variables that require additional computing power (Vogel et al. Int J Obes. 2019). 'Additional computing power' introduces the concept of big data analytics. The aim of this paper is to showcase international research case studies presented during a seminar series held by the Economic and Social Research Council (ESRC) Strategic Network for Obesity in the UK. These are intended to provide an in-depth view of how big data can be used in obesity research, and the specific benefits, limitations and challenges encountered. METHODS AND RESULTS: Three case studies are presented. The first investigated the influence of the built environment on physical activity. It used spatial data on green spaces and exercise facilities alongside individual-level data on physical activity and swipe card entry to leisure centres, collected as part of a local authority exercise class initiative. The second used a variety of linked electronic health datasets to investigate associations between obesity surgery and the risk of developing cancer. The third used data on tax parcel values alongside data from the Seattle Obesity Study to investigate sociodemographic determinants of obesity in Seattle. CONCLUSIONS: The case studies demonstrated how big data could be used to augment traditional data to capture a broader range of variables in the obesity system. They also showed that big data can present improvements over traditional data in relation to size, coverage, temporality, and objectivity of measures. However, the case studies also encountered challenges or limitations; particularly in relation to hidden/unforeseen biases and lack of contextual information. Overall, despite challenges, big data presents a relatively untapped resource that shows promise in helping to understand drivers of obesity.

Rapid, quantitative therapeutic screening for Alzheimer's enzymes enabled by optimal signal transduction with transistors.

We show that commercially sourced n-channel silicon field-effect transistors (nFETs) operating above their threshold voltage with closed loop feedback to maintain a constant channel current allow a pH readout resolution of (7.2 ± 0.3) × 10-3 at a bandwidth of 10 Hz, or ≈3-fold better than the open loop operation commonly employed by integrated ion-sensitive field-effect transistors (ISFETs). We leveraged the improved nFET performance to measure the change in solution pH arising from the activity of a pathological form of the kinase Cdk5, an enzyme implicated in Alzheimer's disease, and showed quantitative agreement with previous measurements. The improved pH resolution was realized while the devices were operated in a remote sensing configuration with the pH sensing element off-chip and connected electrically to the FET gate terminal. We compared these results with those measured by using a custom-built dual-gate 2D field-effect transistor (dg2DFET) fabricated with 2D semi-conducting MoS2 channels and a signal amplification of 8. Under identical solution conditions the nFET performance approached the dg2DFETs pH resolution of (3.9 ± 0.7) × 10-3. Finally, using the nFETs, we demonstrated the effectiveness of a custom polypeptide, p5, as a therapeutic agent in restoring the function of Cdk5. We expect that the straight-forward modifications to commercially sourced nFETs demonstrated here will lower the barrier to widespread adoption of these remote-gate devices and enable sensitive bioanalytical measurements for high throughput screening in drug discovery and precision medicine applications.

Validation of the Oxford WebQ Online 24-Hour Dietary Questionnaire Using Biomarkers.

The Oxford WebQ is an online 24-hour dietary questionnaire that is appropriate for repeated administration in large-scale prospective studies, including the UK Biobank study and the Million Women Study. We compared the performance of the Oxford WebQ and a traditional interviewer-administered multiple-pass 24-hour dietary recall against biomarkers for protein, potassium, and total sugar intake and total energy expenditure estimated by accelerometry. We recruited 160 participants in London, United Kingdom, between 2014 and 2016 and measured their biomarker levels at 3 nonconsecutive time points. The measurement error model simultaneously compared all 3 methods. Attenuation factors for protein, potassium, total sugar, and total energy intakes estimated as the mean of 2 applications of the Oxford WebQ were 0.37, 0.42, 0.45, and 0.31, respectively, with performance improving incrementally for the mean of more measures. Correlation between the mean value from 2 Oxford WebQs and estimated true intakes, reflecting attenuation when intake is categorized or ranked, was 0.47, 0.39, 0.40, and 0.38, respectively, also improving with repeated administration. These correlations were similar to those of the more administratively burdensome interviewer-based recall. Using objective biomarkers as the standard, the Oxford WebQ performs well across key nutrients in comparison with more administratively burdensome interviewer-based 24-hour recalls. Attenuation improves when the average value is taken over repeated administrations, reducing measurement error bias in assessment of diet-disease associations.

Creating a long-term future for big data in obesity research.

Big data are part of the future in obesity research. The ESRC funded Strategic Network for Obesity has together generated a series of papers, published in the International Journal for Obesity illustrating various aspects of their utility, in particular relating to the large social and environmental drivers of obesity. This article is the final part of the series and reflects upon progress to date and identifies four areas that require attention to promote the continued role of big data in research. We additionally include a 'getting started with big data' checklist to encourage more obesity researchers to engage with alternative data resources.

Validity of an online 24-h recall tool (myfood24) for dietary assessment in population studies: comparison with biomarkers and standard interviews.

BACKGROUND: Online dietary assessment tools can reduce administrative costs and facilitate repeated dietary assessment during follow-up in large-scale studies. However, information on bias due to measurement error of such tools is limited. We developed an online 24-h recall (myfood24) and compared its performance with a traditional interviewer-administered multiple-pass 24-h recall, assessing both against biomarkers. METHODS: Metabolically stable adults were recruited and completed the new online dietary recall, an interviewer-based multiple pass recall and a suite of reference measures. Longer-term dietary intake was estimated from up to 3 × 24-h recalls taken 2 weeks apart. Estimated intakes of protein, potassium and sodium were compared with urinary biomarker concentrations. Estimated total sugar intake was compared with a predictive biomarker and estimated energy intake compared with energy expenditure measured by accelerometry and calorimetry. Nutrient intakes were also compared to those derived from an interviewer-administered multiple-pass 24-h recall. RESULTS: Biomarker samples were received from 212 participants on at least one occasion. Both self-reported dietary assessment tools led to attenuation compared to biomarkers. The online tools resulted in attenuation factors of around 0.2-0.3 and partial correlation coefficients, reflecting ranking intakes, of approximately 0.3-0.4. This was broadly similar to the more administratively burdensome interviewer-based tool. Other nutrient estimates derived from myfood24 were around 10-20% lower than those from the interviewer-based tool, with wide limits of agreement. Intraclass correlation coefficients were approximately 0.4-0.5, indicating consistent moderate agreement. CONCLUSIONS: Our findings show that, whilst results from both measures of self-reported diet are attenuated compared to biomarker measures, the myfood24 online 24-h recall is comparable to the more time-consuming and costly interviewer-based 24-h recall across a range of measures.

How has big data contributed to obesity research? A review of the literature.

There has been growing interest in the potential of 'big data' to enhance our understanding in medicine and public health. Although there is no agreed definition of big data, accepted critical components include greater volume, complexity, coverage and speed of availability. Much of these data are 'found' (as opposed to 'made'), in that they have been collected for non-research purposes, but could include valuable information for research. The aim of this paper is to review the contribution of 'found' data to obesity research to date, and describe the benefits and challenges encountered. A narrative review was conducted to identify and collate peer-reviewed research studies. Database searches conducted up to September 2017 found original studies using a variety of data types and sources. These included: retail sales, transport, geospatial, commercial weight management data, social media, and smartphones and wearable technologies. The narrative review highlights the variety of data uses in the literature: describing the built environment, exploring social networks, estimating nutrient purchases or assessing the impact of interventions. The examples demonstrate four significant ways in which 'found' data can complement conventional 'made' data: firstly, in moving beyond constraints in scope (coverage, size and temporality); secondly, in providing objective, quantitative measures; thirdly, in reaching hard-to-access population groups; and lastly in the potential for evaluating real-world interventions. Alongside these opportunities, 'found' data come with distinct challenges, such as: ethical and legal questions around access and ownership; commercial sensitivities; costs; lack of control over data acquisition; validity; representativeness; finding appropriate comparators; and complexities of data processing, management and linkage. Despite widespread recognition of the opportunities, the impact of 'found' data on academic obesity research has been limited. The merit of such data lies not in their novelty, but in the benefits they could add over and above, or in combination with, conventionally collected data.

Can big data solve a big problem? Reporting the obesity data landscape in line with the Foresight obesity system map.

BACKGROUND: Obesity research at a population level is multifaceted and complex. This has been characterised in the UK by the Foresight obesity systems map, identifying over 100 variables, across seven domain areas which are thought to influence energy balance, and subsequent obesity. Availability of data to consider the whole obesity system is traditionally lacking. However, in an era of big data, new possibilities are emerging. Understanding what data are available can be the first challenge, followed by an inconsistency in data reporting to enable adequate use in the obesity context. In this study we map data sources against the Foresight obesity system map domains and nodes and develop a framework to report big data for obesity research. Opportunities and challenges associated with this new data approach to whole systems obesity research are discussed. METHODS: Expert opinion from the ESRC Strategic Network for Obesity was harnessed in order to develop a data source reporting framework for obesity research. The framework was then tested on a range of data sources. In order to assess availability of data sources relevant to obesity research, a data mapping exercise against the Foresight obesity systems map domains and nodes was carried out. RESULTS: A reporting framework was developed to recommend the reporting of key information in line with these headings: Background; Elements; Exemplars; Content; Ownership; Aggregation; Sharing; Temporality (BEE-COAST). The new BEE-COAST framework was successfully applied to eight exemplar data sources from the UK. 80% coverage of the Foresight obesity systems map is possible using a wide range of big data sources. The remaining 20% were primarily biological measurements often captured by more traditional laboratory based research. CONCLUSIONS: Big data offer great potential across many domains of obesity research and need to be leveraged in conjunction with traditional data for societal benefit and health promotion.

Is adolescent body mass index and waist circumference associated with the food environments surrounding schools and homes? A longitudinal analysis.

BACKGROUND: There has been considerable interest in the role of access to unhealthy food options as a determinant of weight status. There is conflict across the literature as to the existence of such an association, partly due to the dominance of cross-sectional study designs and inconsistent definitions of the food environment. The aim of our study is to use longitudinal data to examine if features of the food environment are associated to measures of adolescent weight status. METHODS: Data were collected from secondary schools in Leeds (UK) and included measurements at school years 7 (ages 11/12), 9 (13/14), and 11 (15/16). Outcome variables, for weight status, were standardised body mass index and standardised waist circumference. Explanatory variables included the number of fast food outlets, supermarkets and 'other retail outlets' located within a 1 km radius of an individual's home or school, and estimated travel route between these locations (with a 500 m buffer). Multi-level models were fit to analyse the association (adjusted for confounders) between the explanatory and outcome variables. We also examined changes in our outcome variables between each time period. RESULTS: We found few associations between the food environment and measures of adolescent weight status. Where significant associations were detected, they mainly demonstrated a positive association between the number of amenities and weight status (although effect sizes were small). Examining changes in weight status between time periods produced mainly non-significant or inconsistent associations. CONCLUSIONS: Our study found little consistent evidence of an association between features of the food environment and adolescent weight status. It suggests that policy efforts focusing on the food environment may have a limited effect at tackling the high prevalence of obesity if not supported by additional strategies.

Examining the validity and utility of two secondary sources of food environment data against street audits in England.

BACKGROUND: Secondary data containing the locations of food outlets is increasingly used in nutrition and obesity research and policy. However, evidence evaluating these data is limited. This study validates two sources of secondary food environment data: Ordnance Survey Points of Interest data (POI) and food hygiene data from the Food Standards Agency (FSA), against street audits in England and appraises the utility of these data. METHODS: Audits were conducted across 52 Lower Super Output Areas in England. All streets within each Lower Super Output Area were covered to identify the name and street address of all food outlets therein. Audit-identified outlets were matched to outlets in the POI and FSA data to identify true positives (TP: outlets in both the audits and the POI/FSA data), false positives (FP: outlets in the POI/FSA data only) and false negatives (FN: outlets in the audits only). Agreement was assessed using positive predictive values (PPV: TP/(TP + FP)) and sensitivities (TP/(TP + FN)). Variations in sensitivities and PPVs across environment and outlet types were assessed using multi-level logistic regression. Proprietary classifications within the POI data were additionally used to classify outlets, and agreement between audit-derived and POI-derived classifications was assessed. RESULTS: Street audits identified 1172 outlets, compared to 1100 and 1082 for POI and FSA respectively. PPVs were statistically significantly higher for FSA (0.91, CI: 0.89-0.93) than for POI (0.86, CI: 0.84-0.88). However, sensitivity values were not different between the two datasets. Sensitivity and PPVs varied across outlet types for both datasets. Without accounting for this, POI had statistically significantly better PPVs in rural and affluent areas. After accounting for variability across outlet types, FSA had statistically significantly better sensitivity in rural areas and worse sensitivity in rural middle affluence areas (relative to deprived). Audit-derived and POI-derived classifications exhibited substantial agreement (p < 0.001; Kappa = 0.66, CI: 0.63-0.70). CONCLUSIONS: POI and FSA data have good agreement with street audits; although both datasets had geographic biases which may need to be accounted for in analyses. Use of POI proprietary classifications is an accurate method for classifying outlets, providing time savings compared to manual classification of outlets.

Supermarket top-up of Healthy Start vouchers increases fruit and vegetable purchases in low-income households.

Stark, widening health and income inequalities in the United Kingdom underpin the need for increased support for low-income families to access affordable and nutritious foods. Using anonymised supermarket loyalty card transaction records, this study aimed to assess how an additional Healthy Start voucher (HSV) top-up of £2, redeemable only against fruit and vegetables (FVs), was associated with FV purchases among at-risk households. Transaction and redemption records from 150 loyalty card-holding households, living in northern England, who had engaged with the top-up scheme, were analysed to assess the potential overall population impact. Using a pre-post study design, 133 of these households' records from 2021 were compared with equivalent time periods in 2019 and 2020. Records were linked to product, customer and store data, permitting comparisons using Wilcoxon matched-pairs sign-ranked tests and relationships assessed with Spearman's Rho. These analyses demonstrated that 0.9 more portions of FV per day per household were purchased during the scheme compared to the 2019 baseline (p = 0.0017). The percentage of FV weight within total baskets also increased by 1.6 percentage points (p = 0.0242), although the proportional spend on FV did not change. During the scheme period, FV purchased was higher by 0.4 percentage points (p = 0.0012) and 1.6 percentage points (p = 0.0062) according to spend and weight, respectively, in top-up redeeming baskets compared to non-top-up redeeming baskets with at least one FV item and was associated with 5.5 more HSV 'Suggested' FV portions (p < 0.0001). The median weight of FV purchased increased from 41.83 kg in 2019 to 54.14 kg in 2021 (p = 0.0017). However, top-up vouchers were only redeemed on 9.1% of occasions where FV were purchased. In summary, this study provides novel data showing that safeguarding funds exclusively for FV can help to increase access to FV in low-income households. These results yield important insights to inform public policy aimed at levelling up health inequalities.

Impact on purchasing behaviour of implementing 'junk free checkouts': A pre-post study.

In 2015, Tesco Express convenience stores implemented a healthy checkouts initiative; products high in fat, salt or sugar were removed from in-queue areas. We compare purchasing of less healthy foods before and after its introduction. Tesco provided store-level sales data (n = 1151) for Express stores in England over two 8-week periods, May-July 2014 and 2015. Paired t-tests examined if spending on less healthy foods (biscuits, cakes, crisps and confectionery), as a proportion of total spend, changed between 2015 and 2014. Analyses were repeated for the quantity of less healthy products sold. Compliance was measured through unannounced store visits (n = 41). Complete sales data were available for 1101 stores (96%). Mean overall spend increased in 2015 compared with 2014 (£666 079.70 [SD 406 385.00] vs. £653 786.59 [SD 447 580.77]; p < 0.001). The proportion of total spend from less healthy foods decreased in 2015 versus 2014 (8.03% [SD 2.07] vs. 8.21% [SD 2.17]; p < 0.001). Confectionery accounted for the largest proportion of less healthy product spend, showing the biggest reduction (3.91% [SD 1.16] in 2015 vs. 4.12% [SD 1.24] in 2014; p < 0.001). Results were similar for quantity of less healthy products sold. Like-for-like sales data from major supermarkets revealed spend on less healthy products rose across the UK over this period. Thirty-nine per cent of stores were fully compliant. In conclusion, following implementation of Tesco's healthier checkouts initiative, there was a small reduction in sales of less healthy foods, largely accounted for by confectionery products. These findings suggest that removal of less healthy products from checkouts might lead to healthier purchasing behaviour. However, store compliance was poor, suggesting scope for improvement.

A systematic review of supermarket automated electronic sales data for population dietary surveillance.

CONTEXT: Most dietary assessment methods are limited by self-report biases, how long they take for participants to complete, and cost of time for dietitians to extract content. Electronically recorded, supermarket-obtained transactions are an objective measure of food purchases, with reduced bias and improved timeliness and scale. OBJECTIVE: The use, breadth, context, and utility of electronic purchase records for dietary research is assessed and discussed in this systematic review. DATA SOURCES: Four electronic databases (MEDLINE, EMBASE, PsycINFO, Global Health) were searched. Included studies used electronically recorded supermarket transactions to investigate the diet of healthy, free-living adults. DATA EXTRACTION: Searches identified 3422 articles, of which 145 full texts were retrieved and 72 met inclusion criteria. Study quality was assessed using the National Institutes of Health Quality Assessment Tool for Observational Cohort and Cross-Sectional Studies. DATA ANALYSIS: Purchase records were used in observational studies, policy evaluations, and experimental designs. Nutrition outcomes included dietary patterns, nutrients, and food category sales. Transactions were linked to nutrient data from retailers, commercial data sources, and national food composition databases. CONCLUSION: Electronic sales data have the potential to transform dietary assessment and worldwide understanding of dietary behavior. Validation studies are warranted to understand limits to agreement and extrapolation to individual-level diets. SYSTEMATIC REVIEW REGISTRATION: PROSPERO registration no. CRD42018103470.

Predicting Food Safety Compliance for Informed Food Outlet Inspections: A Machine Learning Approach.

Consumer food environments have transformed dramatically in the last decade. Food outlet prevalence has increased, and people are eating food outside the home more than ever before. Despite these developments, national spending on food control has reduced. The National Audit Office report that only 14% of local authorities are up to date with food business inspections, exposing consumers to unknown levels of risk. Given the scarcity of local authority resources, this paper presents a data-driven approach to predict compliance for newly opened businesses and those awaiting repeat inspections. This work capitalizes on the theory that food outlet compliance is a function of its geographic context, namely the characteristics of the neighborhood within which it sits. We explore the utility of three machine learning approaches to predict non-compliant food outlets in England and Wales using openly accessible socio-demographic, business type, and urbanness features at the output area level. We find that the synthetic minority oversampling technique alongside a random forest algorithm with a 1:1 sampling strategy provides the best predictive power. Our final model retrieves and identifies 84% of total non-compliant outlets in a test set of 92,595 (sensitivity = 0.843, specificity = 0.745, precision = 0.274). The originality of this work lies in its unique and methodological approach which combines the use of machine learning with fine-grained neighborhood data to make robust predictions of compliance.

Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach.

The increasing ubiquity of smartphone data, with greater spatial and temporal coverage than achieved by traditional study designs, have the potential to provide insight into habitual physical activity patterns. This study implements and evaluates the utility of both K-means clustering and agglomerative hierarchical clustering methods in identifying weekly and yearlong physical activity behaviour trends. Characterising the demographics and choice of activity type within the identified clusters of behaviour. Across all seven clusters of seasonal activity behaviour identified, daylight saving was shown to play a key role in influencing behaviour, with increased activity in summer months. Investigation into weekly behaviours identified six clusters with varied roles, of weekday versus weekend, on the likelihood of meeting physical activity guidelines. Preferred type of physical activity likewise varied between clusters, with gender and age strongly associated with cluster membership. Key relationships are identified between weekly clusters and seasonal activity behaviour clusters, demonstrating how short-term behaviours contribute to longer-term activity patterns. Utilising unsupervised machine learning, this study demonstrates how the volume and richness of secondary app data can allow us to move away from aggregate measures of physical activity to better understand temporal variations in habitual physical activity behaviour.

Socio-demographic determinants of physical activity and app usage from smartphone data.

The increasing ubiquity of smartphones provides a potential new data source to capture physical activity behaviours. Though not designed as a research tool, these secondary data have the potential to capture a large population over a more extensive spatial area and with longer temporality than current methods afford. This paper uses one such secondary data source from a commercial app designed to incentivise activity. We explore the new insights these data provide, alongside the sociodemographic profile of those using physical activity apps, to gain insight into both physical activity behaviour and determinants of app usage in order to evaluate the suitability of the app in providing insights into the physical activity of the population. We find app usage to be higher in females, those aged 25-50, and users more likely to live in areas where a higher proportion of the population are of a lower socioeconomic status. We ascertain longer-term patterns of app usage with increasing age and more male users reaching physical activity guideline recommendations despite longer daily activity duration recorded by female users. Additionally, we identify key weekly and seasonal trends in physical activity. This is one of the first studies to utilise a large volume of secondary physical activity app data to co-investigate usage alongside activity behaviour captured.