Underconsumption of dietary fiber is prevalent worldwide and is associated with multiple adverse health conditions. Despite the importance of fiber, the labeling of fiber content on packaged foods and beverages is voluntary in most countries, making it challenging for consumers and policy makers to monitor fiber consumption. Here, we developed a machine learning approach for automated and systematic prediction of fiber content using nutrient information commonly available on packaged products. An Australian packaged food dataset with known fiber content information was divided into training (n = 8986) and test datasets (n = 2455). Utilization of a k-nearest neighbors machine learning algorithm explained a greater proportion of variance in fiber content than an existing manual fiber prediction approach (R² = 0.84 vs. R² = 0.68). Our findings highlight the opportunity to use machine learning to efficiently predict the fiber content of packaged products on a large scale.

Unhealthy diets are underpinned by the over-consumption of packaged products. Data describing the ingredient composition of these products is limited. We sought to define the ingredients used in Australian packaged foods and beverages and assess associations between the number of ingredients and existing health indicators. Statements of ingredients were disaggregated, creating separate fields for each ingredient and sub-ingredient. Ingredients were categorised and the average number of ingredients per product was calculated. Associations between number of ingredients and both the nutrient-based Health Star Rating (HSR) and the NOVA level-of-processing classification were assessed. A total of 24,229 products, listing 233,113 ingredients, were included. Products had between 1 and 62 ingredients (median (Interquartile range (IQR)): 8 (3–14)). We identified 915 unique ingredients, which we organised into 17 major and 138 minor categories. ‘Additives’ were contained in the largest proportion of products (64.6%, (15,652/24,229)). The median number of ingredients per product was significantly lower in products with the optimum 5-star HSR (when compared to all other HSR score groups, p-value < 0.001) and significantly higher in products classified as ultra-processed (when compared to all other NOVA classification groups, p-value < 0.001). There is a strong relationship between the number of ingredients in a product and indicators of nutritional quality and level of processing.

Fiscal food policies can be used, among others, to minimize the burden of diet-related diseases. To inform the design of such policies in Australia, we used the large grocery-purchasing dataset NielsenIQ Homescan to estimate own-price elasticities and cross-price elasticities for 18 food categories. We found that households were most responsive to changes in price for non-sugar-sweetened beverages and sugar-sweetened beverages: a 10% increase in price was associated with reductions in demand of 15% and 12%, respectively. Additionally, an increase in the price of one category was associated with relatively small changes in the quantity demanded for other categories (that is, 92% of cross-price elasticities had an absolute value <0.2). There were small differences in own-price and cross-price elasticities across socioeconomic quintiles. These price elasticity estimates can be used to model the health and equity impacts of fiscal food policies in Australia.

Mandatory pregnancy warning labels are an important public health measure to signal the harms of drinking alcohol during pregnancy. Ensuring these labels are salient is critical to enhancing their effectiveness. On 31 July 2020, Australia mandated that alcoholic beverages labelled from 1 August 2023 display a pregnancy warning label. This study assessed uptake and placement of this warning on alcohol containers after the policy start date. Between August and November 2023, data collectors obtained images of 4026 unique alcoholic beverages available for sale across four major Australian alcohol retailers in Sydney (three physical stores and one online store). Product images were investigated to assess overall uptake of the mandatory pregnancy warning label and its placement on products (i.e., front, side, back, top, or bottom). Analyses were conducted overall and stratified across six alcohol product categories. Two-thirds (63 %) of products displayed the mandatory pregnancy warning label. Uptake was lowest for spirits (50 %), followed by wine (65 %), cider (79 %), premix drinks (79 %), beer (83 %), and other alcoholic beverages (e.g., sake and soju) (91 %). The mandatory pregnancy warning label was most commonly located on the back (88 %) and less commonly on the side (8 %), bottom (3 %), top (1 %), or front (0.3 %). To increase uptake of the mandatory pregnancy warning label, policymakers should consider mandating that all alcoholic beverages available for sale, not just products labelled from 1 August 2023, display the warning. Existing requirements could be revised to ensure that the label is more prominently displayed.

Regulations to restrict alcohol promotion and requirements for mandatory display of information about health risks associated with alcohol use have been minimal and hard-won in Australia. This study (i) outlines an approach to monitoring alcohol industry use of health messages on alcohol products and (ii) reports prevalence and nature of government-mandated health-related information and voluntary health messages on alcohol products. Images of 5,923 alcohol products sold in four large alcohol stores in Sydney were captured. Data were collected in-store and via web-scraping. Label content was extracted from the images. There was high compliance (97%-99%) with government-mandated requirements other than the pregnancy warning label (63%). Presence of voluntary health-related messages was common (65%), but typically present in the form of DrinkWise (an industry-led social aspects/public relations organisation) statements that are unlikely to be effective. This study provides a unique and systematic approach to examining alcohol industry compliance with government-mandated on-product information requirements and voluntary inclusion of other health-related messages. The results demonstrate the need for ongoing monitoring to enforce alcohol industry compliance with Australia's existing and future labelling regulations and to assess the industry's voluntary use of other forms of health messaging.