Intersections of Educational Attainment, Indigenous Identity, and Race/Ethnicity Best Predicted Diet Quality Among Adults in Canada: A Conditional Random Forests Analysis - 20/01/26
, Martin J. Cooke, PhD 1, 2, Michael P. Wallace, PhD 3, Elena Neiterman, PhD 1, Dana Lee Olstad, PhD, RD 4Abstract |
Background |
Although it is well-known that diet quality varies according to multiple dimensions of socioeconomic position (SEP), much remains unknown about how these dimensions together shape diet quality. Given that diet quality associated with 1 SEP dimension (eg, income) can systematically differ across another dimension (eg, race and ethnicity), it is necessary to investigate diet quality across SEP intersections.
Objectives |
The aim of this study was to identify SEP intersections that best predicted lower and higher diet quality among adults in Canada.
Design |
Population-based data were from the cross-sectional 2015 Canadian Community Health Survey–Nutrition. Data were collected by interviewers who visited selected dwellings to collect household information and administer a general health questionnaire and a 24-hour dietary recall.
Participants/Setting |
Data from 13 617 adults aged 18 years and older living in Canada’s 10 provinces.
Main Outcome Measures |
Twenty-four–hour dietary recall data were used to assess diet quality based on the Healthy Eating Index-2015 (HEI-2015) score (range, 0 to 100).
Statistical Analyses Performed |
Conditional random forests, a supervised machine-learning technique, were used to identify 4 of 12 SEP indicators that best individually predicted HEI-2015 scores. The resulting 4 most important predictors were used to predict diet quality using all possible 2-way intersections.
Results |
The 4 most important intersectional predictors of HEI-2015 scores based on conditional random forest variable importance measures were (1) educational attainment and Indigenous identity and race/ethnicity, (2) educational attainment and household food insecurity, (3) educational attainment and sex/gender, and (4) household food insecurity and sex/gender. Among these 4 SEP intersections, individuals without a high school diploma living in a severely food-insecure household had the lowest (55.7), and individuals without a high school diploma identifying as Middle Eastern had the highest (64.5) predicted HEI-2015 scores.
Conclusions |
The SEP intersection defined by educational attainment and Indigenous identity and race/ethnicity was the most important predictor of diet quality among adults in Canada.
Le texte complet de cet article est disponible en PDF.Keywords : Intersectionality, Socioeconomic position, Diet quality, Machine learning, Public health
Plan
| STATEMENT OF POTENTIAL CONFLICT OF INTEREST No potential conflict of interest was reported by the authors. |
|
| FUNDING/SUPPORT N. Doan is supported by funding from the Canadian Research Data Centre Network Emerging Scholars Grant and the Ontario Graduate Scholarship. |
|
| ACKNOWLEDGEMENTS The authors are grateful to Patricia Newcombe-Welch, PhD, of the Southwestern Ontario Research Data Centre, for her technical and statistical support. |
|
| AUTHOR CONTRIBUTIONS Conceptualization: N. Doan, D. L. Olstad, M. J. Cooke; methodology: N. Doan, D. L. Olstad, M. J. Cooke, M. P. Wallace; writing – original draft preparation, N. Doan; writing – review and editing, N. Doan, D. L. Olstad, M. J. Cooke, M. P. Wallace, E. Neiterman; supervision, M. J. Cooke, D. L. Olstad. All authors reviewed and approved the submitted manuscript. |
Vol 126 - N° 2
Article 156207- février 2026 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?
