Background Rating someone’s diet as a whole as opposed to rating individual food items could help to better inform people about their nutrition and its health properties, e.g. by considering possible deficiencies. The goal of this project was to develop an automated rating of shopping baskets based on their health properties that can be deployed on top of existing loyalty or digital shopping basket programs by retailers without knowing for how long a basket will last or how many people consume it.

Methods We developed a model that uses nutrient densities as opposed to absolute quantities based on self-reported food intake from the National Health and Nutrition Examination Survey (NHANES) as well as mortality follow-up data and conducted a validation against the Nutri-Score as well as the Alternate Healthy Eating Index (AHEI).

Results The model we obtained punishes consuming calories from sugar and saturated fats, high salt intake, as well as consuming calories from beverages. Furthermore, a penalty is applied to a nutrition that is deficient in protein, vitamin C, or iron. Fiber consumption is rewarded. The model showed a high degree of correlation with the Nutri-Score (Pearson correlation coefficient: 0.60) and the AHEI (Pearson correlation coefficient: -0.62 for the AHEI without the protective effect of moderate alcohol consumption and -0.60 with it).

Conclusions The proposed model is aligned with the recommendations formulated in nutritional guidelines, which is indicated by a high degree of correlation with the AHEI. Product-level profiling systems such as the Nutri-Score also exhibit a correlation with the model and can be used in combination.

S.M., A.N., D.F., and P.W. report employment at or consulting for dacadoo AG, a technology company that has business activity with retailers, including grocery stores. While the research presented herein is not patent protected, dacadoo intends to file 'GBS' as a trademark and commercialize GBSTM software and/or consulting services. The other authors declare no additional conflict of interest.

No external funding was received for this project.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study used openly available human data from NHANES (https://www.cdc.gov/nchs/nhanes/index.html)

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Disclosures: S.M., A.N., D.F., and P.W. report employment at or consulting for dacadoo AG, a technology company that has business activity with retailers, including grocery stores. While the research presented herein is not patent protected, dacadoo intends to file ‘GBS’ as a trademark and commercialize GBS™ software and/or consulting services. The other authors declare no additional conflict of interest.

Data availability: This paper contains information from the Open Food Facts (https://world.openfoodfacts.org/) and OFF-GBS (https://github.com/windisch-paul/OFF-GBS) databases, which are made available under the Open Database License (ODbL, https://opendatacommons.org/licenses/odbl/1-0/).

Funding: No external funding was received for this project.

This paper contains information from the Open Food Facts (https://world.openfoodfacts.org/) and OFF-GBS (https://github.com/windisch-paul/OFF-GBS) databases, which are made available under the Open Database License (ODbL, https://opendatacommons.org/licenses/odbl/1-0/).

https://world.openfoodfacts.org/

https://github.com/windisch-paul/OFF-GBS