NOVA Through Two Lenses: From Nutrients to Food Processing Classification in Finland's National Food Database
- 1University of Helsinki
Abstract
Ultra-processed food (UPF) intake has been linked to adverse health outcomes. However, NOVA processing groups are hard to assign consistently, and many national food composition databases do not include them. Nutrient-based classification models could fill this gap, but their performance across countries and databases is uncertain. FoodProX is a machine-learning classifier that predicts NOVA groups and a continuous food-processing score (FPro) from nutrient composition. To test whether such models transfer across databases, we retrained it on 182,344 mostly European Open Food Facts products. We evaluated it on 45,526 held-out Open Food Facts products and, without retraining, on 2,971 NOVA-labelled foods from a US database (FNDDS). We then applied it to the Finnish national food composition database (Fineli), which has no NOVA labels. Four-class accuracy was 0.855 on held-out products and 0.763 in FNDDS, with errors concentrated at the NOVA 3/4 boundary. UPFs were identified well, with precision-recall performance of 0.940 and 0.964, respectively (on a 0--1 scale), well above the chance levels of 0.463 and 0.711. On the same items, our FPro scores ranked foods similarly to those of the originally released US-trained FoodProX (Spearman {rho} = 0.81 in FNDDS and 0.79 in Fineli), although our scores were lower on average. Sodium and sugars were the strongest predictors. Low fibre and iron also pushed predictions towards NOVA 4. In Fineli, the model assigned 55.9% of the 4,092 scored items to NOVA 4. We found no earlier NOVA or FPro annotations for this database. Nutrient-based models are most reliable for detecting ultra-processing and ranking processing intensity, and less reliable for assigning all four NOVA groups. Experts also agree poorly when assigning NOVA groups, so part of this difficulty may lie in the NOVA definitions themselves.
Related
- Development of a comprehensive database of markers of ultra-processing to identify ultra-processed food in the UK according to the Nova classification
- Surgical management of urolithiasis in france from 2016 to 2022: epidemiological data from the national PMSI database
- Incidence and Risk of Trigger Finger Following Carpal Tunnel Release: A Propensity-Matched Cohort Study Using a National Database
- Prevalence, causes, and predictors of 30-day readmissions after acute myocardial infarction with ventricular arrhythmias: a cohort study using the 2016–2017 national readmissions database
- Prediction of Long‐Term Prognosis in Patients With Hepatocellular Carcinoma Using the National Clinical Database Risk Calculator
BibTeX
@misc{janbesaraei2026nova,
title = {{NOVA Through Two Lenses: From Nutrients to Food Processing Classification in Finland's National Food Database}},
author = {S. Nedaei Janbesaraei and A. Kanyamibwa and A. Horstmann},
howpublished = {medRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.26.26366503},
url = {https://www.medrxiv.org/content/10.64898/2026.10.26.26366503v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - NOVA Through Two Lenses: From Nutrients to Food Processing Classification in Finland's National Food Database
AU - S. Nedaei Janbesaraei
AU - A. Kanyamibwa
AU - A. Horstmann
PY - 2026
DA - 2026/10/26
PB - medRxiv
DO - 10.64898/2026.10.26.26366503
UR - https://www.medrxiv.org/content/10.64898/2026.10.26.26366503v1
AB - Ultra-processed food (UPF) intake has been linked to adverse health outcomes. However, NOVA processing groups are hard to assign consistently, and many national food composition databases do not include them. Nutrient-based classification models could fill this gap, but their performance across countries and databases is uncertain. FoodProX is a machine-learning classifier that predicts NOVA groups and a continuous food-processing score (FPro) from nutrient composition. To test whether such models transfer across databases, we retrained it on 182,344 mostly European Open Food Facts products. We evaluated it on 45,526 held-out Open Food Facts products and, without retraining, on 2,971 NOVA-labelled foods from a US database (FNDDS). We then applied it to the Finnish national food composition database (Fineli), which has no NOVA labels. Four-class accuracy was 0.855 on held-out products and 0.763 in FNDDS, with errors concentrated at the NOVA 3/4 boundary. UPFs were identified well, with precision-recall performance of 0.940 and 0.964, respectively (on a 0--1 scale), well above the chance levels of 0.463 and 0.711. On the same items, our FPro scores ranked foods similarly to those of the originally released US-trained FoodProX (Spearman {rho} = 0.81 in FNDDS and 0.79 in Fineli), although our scores were lower on average. Sodium and sugars were the strongest predictors. Low fibre and iron also pushed predictions towards NOVA 4. In Fineli, the model assigned 55.9% of the 4,092 scored items to NOVA 4. We found no earlier NOVA or FPro annotations for this database. Nutrient-based models are most reliable for detecting ultra-processing and ranking processing intensity, and less reliable for assigning all four NOVA groups. Experts also agree poorly when assigning NOVA groups, so part of this difficulty may lie in the NOVA definitions themselves.
ER -