Mitigating underreported error in food frequency questionnaire data using a supervised machine learning method and error adjustment algorithm.
Error adjustment model
Food frequency questionnaire
Machine learning
Measurement error
Supervised learning
Underreporting
Journal
BMC medical informatics and decision making
ISSN: 1472-6947
Titre abrégé: BMC Med Inform Decis Mak
Pays: England
ID NLM: 101088682
Informations de publication
Date de publication:
09 09 2023
09 09 2023
Historique:
received:
30
11
2022
accepted:
08
08
2023
medline:
11
9
2023
pubmed:
10
9
2023
entrez:
9
9
2023
Statut:
epublish
Résumé
Food frequency questionnaires (FFQs) are one of the most useful tools for studying and understanding diet-disease relationships. However, because FFQs are self-reported data, they are susceptible to response bias, social desirability bias, and misclassification. Currently, several methods have been created to combat these issues by modelling the measurement error in diet-disease relationships. In this paper, a novel machine learning method is proposed to adjust for measurement error found in misreported data by using a random forest (RF) classifier to label the responses in the FFQ based on the input dataset and creating an algorithm that adjusts the measurement error. We demonstrate this method by addressing underreporting in selected FFQ responses. According to the results, we have high model accuracies ranging from 78% to 92% in participant collected data and 88% in simulated data. This shows that our proposed method of using a RF classifier and an error adjustment algorithm is efficient to correct most of the underreported entries in the FFQ dataset and could be used independent of diet-disease models. This could help nutrition researchers and other experts to use dietary data estimated by FFQs with less measurement error and create models from the data with minimal noise.
Sections du résumé
BACKGROUND
Food frequency questionnaires (FFQs) are one of the most useful tools for studying and understanding diet-disease relationships. However, because FFQs are self-reported data, they are susceptible to response bias, social desirability bias, and misclassification. Currently, several methods have been created to combat these issues by modelling the measurement error in diet-disease relationships.
METHOD
In this paper, a novel machine learning method is proposed to adjust for measurement error found in misreported data by using a random forest (RF) classifier to label the responses in the FFQ based on the input dataset and creating an algorithm that adjusts the measurement error. We demonstrate this method by addressing underreporting in selected FFQ responses.
RESULT
According to the results, we have high model accuracies ranging from 78% to 92% in participant collected data and 88% in simulated data.
CONCLUSION
This shows that our proposed method of using a RF classifier and an error adjustment algorithm is efficient to correct most of the underreported entries in the FFQ dataset and could be used independent of diet-disease models. This could help nutrition researchers and other experts to use dietary data estimated by FFQs with less measurement error and create models from the data with minimal noise.
Identifiants
pubmed: 37689645
doi: 10.1186/s12911-023-02262-9
pii: 10.1186/s12911-023-02262-9
pmc: PMC10492312
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Langues
eng
Sous-ensembles de citation
IM
Pagination
178Subventions
Organisme : NCATS NIH HHS
ID : UL1 TR002378
Pays : United States
Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
Kirkpatrick SI, Troiano RP, Barrett B, Cunningham C, Subar AF, Park Y, et al. Measurement error affecting web- and paper-based dietary assessment instruments: insights from the multi-cohort eating and activity study for understanding reporting error. Am J Epidemiol. 2022;191(6):1125–39.
doi: 10.1093/aje/kwac026
pubmed: 35136928
pmcid: 9393065
Alonso A, Yu B, Sun YV, Chen LY, Loehr LR, O’Neal WT, et al. Serum metabolomics and incidence of atrial fibrillation (from the Atherosclerosis Risk in Communities Study). Am J Cardiol. 2019;123(12):1955–61.
doi: 10.1016/j.amjcard.2019.03.017
pubmed: 30979411
pmcid: 6529276
Kipnis V, Midthune D, Freedman L, Bingham S, Day NE, Riboli E, et al. Bias in dietary-report instruments and its implications for nutritional epidemiology. Public Health Nutr. 2002;5(6A):915–23.
doi: 10.1079/PHN2002383
pubmed: 12633516
Kristal AR, Andrilla CH, Koepsell TD, Diehr PH, Cheadle A. Dietary assessment instruments are susceptible to intervention-associated response set bias. J Am Diet Assoc. 1998;98(1):40–3.
doi: 10.1016/S0002-8223(98)00012-1
pubmed: 9434649
Kipnis V, Midthune D, Freedman LS, Bingham S, Schatzkin A, Subar A, et al. Empirical evidence of correlated biases in dietary assessment instruments and its implications. Am J Epidemiol. 2001;153(4):394–403.
doi: 10.1093/aje/153.4.394
pubmed: 11207158
Aaby D, Siddique J. Effects of differential measurement error in self-reported diet in longitudinal lifestyle intervention studies. Int J Behav Nutr Phys Act. 2021;18(1):125.
doi: 10.1186/s12966-021-01184-x
pubmed: 34530859
pmcid: 8447716
Freedman LS, Midthune D, Carroll RJ, Kipnis V. A comparison of regression calibration, moment reconstruction and imputation for adjusting for covariate measurement error in regression. Stat Med. 2008;27(25):5195–216.
doi: 10.1002/sim.3361
pubmed: 18680172
pmcid: 2676235
Agogo GO. A zero-augmented generalized gamma regression calibration to adjust for covariate measurement error: a case of an episodically consumed dietary intake: a zero-augmented generalized gamma regression calibration to adjust for measurement error. Biom J. 2017;59(1):94–109.
doi: 10.1002/bimj.201600043
pubmed: 27704599
Agogo GO, van der Voet H, van’t Veer P, Ferrari P, Leenders M, Muller DC, et al. Use of two-part regression calibration model to correct for measurement error in episodically consumed foods in a single-replicate study design: EPIC case study. PLoS One. 2014;9(11):e113160.
doi: 10.1371/journal.pone.0113160
pubmed: 25402487
pmcid: 4234679
Grech A, Hasick M, Gemming L, Rangan A. Energy misreporting is more prevalent for those of lower socio-economic status and is associated with lower reported intake of discretionary foods. Br J Nutr. 2021;125(11):1291–8.
doi: 10.1017/S0007114520003621
pubmed: 32943124
Tooze JA, Subar AF, Thompson FE, Troiano R, Schatzkin A, Kipnis V. Psychosocial predictors of energy underreporting in a large doubly labeled water study. Am J Clin Nutr. 2004;79(5):795–804.
doi: 10.1093/ajcn/79.5.795
pubmed: 15113717
Heitmann BL, Lissner L. Can adverse effects of dietary fat intake be overestimated as a consequence of dietary fat underreporting? Public Health Nutr. 2005;8(8):1322–7.
doi: 10.1079/PHN2005750
pubmed: 16372929
Becker W, Welten D. Under-reporting in dietary surveys – implications for development of food-based dietary guidelines. Public Health Nutr. 2001;4(2b):683–7.
doi: 10.1079/PHN2001154
pubmed: 11683562
Johansson G, Wikman A, Ahrén AM, Hallmans G, Johansson I. Underreporting of energy intake in repeated 24-hour recalls related to gender, age, weight status, day of interview, educational level, reported food intake, smoking habits and area of living. Public Health Nutr. 2001;4(4):919–27.
doi: 10.1079/PHN2001124
pubmed: 11527517
Krebs-Smith SM, Graubard BI, Kahle LL, Subar AF, Cleveland LE, Ballard-Barbash R. Low energy reporters vs others: a comparison of reported food intakes. Eur J Clin Nutr. 2000;54(4):281–7.
doi: 10.1038/sj.ejcn.1600936
pubmed: 10745278
Lafay L, Mennen L, Basdevant A, Charles MA, Borys JM, Eschwège E, et al. Does energy intake underreporting involve all kinds of food or only specific food items? Results from the Fleurbaix Laventie Ville Santé (FLVS) study. Int J Obes Relat Metab Disord J Int Assoc Study Obes. 2000;24(11):1500–6.
doi: 10.1038/sj.ijo.0801392
Tabassum R, Cunningham L, Stephens E, Sturdivant K, Martin G, Brigham K, et al. A longitudinal study of health improvement in the Atlanta CHDWB Wellness Cohort. J Pers Med. 2014;4(4):489–507.
doi: 10.3390/jpm4040489
pubmed: 25563459
pmcid: 4282885
Boeckner LS, Pullen CH, Walker SN, Abbott GW, Block T. Use and reliability of the world wide web version of the block health habits and history questionnaire with older rural women. J Nutr Educ Behav. 2002;34:S20–4.
doi: 10.1016/S1499-4046(06)60307-2
pubmed: 12047825
Subar AF, Freedman LS, Tooze JA, Kirkpatrick SI, Boushey C, Neuhouser ML, et al. Addressing current criticism regarding the value of self-report dietary data. J Nutr. 2015;145(12):2639–45.
doi: 10.3945/jn.115.219634
pubmed: 26468491
pmcid: 4656907
Streppel MT, de Vries JH, Meijboom S, Beekman M, de Craen AJ, Slagboom PE, et al. Relative validity of the food frequency questionnaire used to assess dietary intake in the Leiden Longevity Study. Nutr J. 2013;12(1):75.
doi: 10.1186/1475-2891-12-75
pubmed: 23758629
pmcid: 3680188
Kulkarni V, Sinha P. Random forest classifiers: A survey and future research directions. Int J Adv Comput. 2013;36:1144–53.
Reščič N, Eftimov T, KoroušićSeljak B, Luštrek M. Optimising an FFQ using a machine learning pipeline to teach an efficient nutrient intake predictive model. Nutrients. 2020;12(12):3789.
doi: 10.3390/nu12123789
pubmed: 33321959
pmcid: 7764455
Agogo GO, Muoka AK. A three-part regression calibration to handle excess zeroes, skewness and heteroscedasticity in adjusting for measurement error in dietary intake data. J Appl Stat. 2022;49(4):884–901.
doi: 10.1080/02664763.2020.1845622
pubmed: 35707818