Application of a new dietary pattern analysis method in nutritional epidemiology
Abstract Background Diet plays an important role in chronic disease, and the use of dietary pattern analysis has grown rapidly as a way of deconstructing the complexity of nutritional intake and its relation to health. Pattern analysis methods, such as principal component analysis (PCA), have been u...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-10-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-018-0585-8 |
| _version_ | 1798045336468455424 |
|---|---|
| author | Fengqing Zhang Tinashe M. Tapera Jiangtao Gou |
| author_facet | Fengqing Zhang Tinashe M. Tapera Jiangtao Gou |
| author_sort | Fengqing Zhang |
| collection | DOAJ |
| description | Abstract Background Diet plays an important role in chronic disease, and the use of dietary pattern analysis has grown rapidly as a way of deconstructing the complexity of nutritional intake and its relation to health. Pattern analysis methods, such as principal component analysis (PCA), have been used to investigate various dimensions of diet. Existing analytic methods, however, do not fully utilize the predictive potential of dietary assessment data. In particular, these methods are often suboptimal at predicting clinically important variables. Methods We propose a new dietary pattern analysis method using the advanced LASSO (Least Absolute Shrinkage and Selection Operator) model to improve the prediction of disease-related risk factors. Despite the potential advantages of LASSO, this is the first time that the model has been adapted for dietary pattern analysis. Hence, the systematic evaluation of the LASSO model as applied to dietary data and health outcomes is highly innovative and novel. Using Food Frequency Questionnaire data from NHANES 2005–2006, we apply PCA and LASSO to identify dietary patterns related to cardiovascular disease risk factors in healthy US adults (n = 2609) after controlling for confounding variables (e.g., age and BMI). Both analyses account for the sampling weights. Model performance in terms of prediction accuracy is evaluated using an independent test set. Results PCA yields 10 principal components (PCs) that together account for 65% of the variation in the data set and represent distinct dietary patterns. These PCs are then used as predictors in a regression model to predict cardiovascular disease risk factors. We find that LASSO better predicts levels of triglycerides, LDL cholesterol, HDL cholesterol, and total cholesterol (adjusted R 2 = 0.861, 0.899, 0.890, and 0.935 respectively) than does the traditional, linear-regression-based, dietary pattern analysis method (adjusted R 2 = 0.163, 0.005, 0.235, and 0.024 respectively) when the latter is applied to components derived from PCA. Conclusions The proposed method is shown to be an appropriate and promising statistical means of deriving dietary patterns predictive of cardiovascular disease risk. Future studies, involving different diseases and risk factors, will be necessary before LASSO’s broader usefulness in nutritional epidemiology can be established. |
| first_indexed | 2024-04-11T23:19:01Z |
| format | Article |
| id | doaj.art-7a89c983b9e14e7fb4c8dfe3bdd5f59a |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-04-11T23:19:01Z |
| publishDate | 2018-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-7a89c983b9e14e7fb4c8dfe3bdd5f59a2022-12-22T03:57:30ZengBMCBMC Medical Research Methodology1471-22882018-10-0118111010.1186/s12874-018-0585-8Application of a new dietary pattern analysis method in nutritional epidemiologyFengqing Zhang0Tinashe M. Tapera1Jiangtao Gou2Department of Psychology, Drexel UniversityDepartment of Psychology, Drexel UniversityDepartment of Biostatistics and Bioinformatics, Fox Chase Cancer Center, Temple University Health SystemAbstract Background Diet plays an important role in chronic disease, and the use of dietary pattern analysis has grown rapidly as a way of deconstructing the complexity of nutritional intake and its relation to health. Pattern analysis methods, such as principal component analysis (PCA), have been used to investigate various dimensions of diet. Existing analytic methods, however, do not fully utilize the predictive potential of dietary assessment data. In particular, these methods are often suboptimal at predicting clinically important variables. Methods We propose a new dietary pattern analysis method using the advanced LASSO (Least Absolute Shrinkage and Selection Operator) model to improve the prediction of disease-related risk factors. Despite the potential advantages of LASSO, this is the first time that the model has been adapted for dietary pattern analysis. Hence, the systematic evaluation of the LASSO model as applied to dietary data and health outcomes is highly innovative and novel. Using Food Frequency Questionnaire data from NHANES 2005–2006, we apply PCA and LASSO to identify dietary patterns related to cardiovascular disease risk factors in healthy US adults (n = 2609) after controlling for confounding variables (e.g., age and BMI). Both analyses account for the sampling weights. Model performance in terms of prediction accuracy is evaluated using an independent test set. Results PCA yields 10 principal components (PCs) that together account for 65% of the variation in the data set and represent distinct dietary patterns. These PCs are then used as predictors in a regression model to predict cardiovascular disease risk factors. We find that LASSO better predicts levels of triglycerides, LDL cholesterol, HDL cholesterol, and total cholesterol (adjusted R 2 = 0.861, 0.899, 0.890, and 0.935 respectively) than does the traditional, linear-regression-based, dietary pattern analysis method (adjusted R 2 = 0.163, 0.005, 0.235, and 0.024 respectively) when the latter is applied to components derived from PCA. Conclusions The proposed method is shown to be an appropriate and promising statistical means of deriving dietary patterns predictive of cardiovascular disease risk. Future studies, involving different diseases and risk factors, will be necessary before LASSO’s broader usefulness in nutritional epidemiology can be established.http://link.springer.com/article/10.1186/s12874-018-0585-8Dietary pattern analysisLASSOPrincipal component analysisCardiovascular diseaseFood-frequency questionnaireNHANES |
| spellingShingle | Fengqing Zhang Tinashe M. Tapera Jiangtao Gou Application of a new dietary pattern analysis method in nutritional epidemiology BMC Medical Research Methodology Dietary pattern analysis LASSO Principal component analysis Cardiovascular disease Food-frequency questionnaire NHANES |
| title | Application of a new dietary pattern analysis method in nutritional epidemiology |
| title_full | Application of a new dietary pattern analysis method in nutritional epidemiology |
| title_fullStr | Application of a new dietary pattern analysis method in nutritional epidemiology |
| title_full_unstemmed | Application of a new dietary pattern analysis method in nutritional epidemiology |
| title_short | Application of a new dietary pattern analysis method in nutritional epidemiology |
| title_sort | application of a new dietary pattern analysis method in nutritional epidemiology |
| topic | Dietary pattern analysis LASSO Principal component analysis Cardiovascular disease Food-frequency questionnaire NHANES |
| url | http://link.springer.com/article/10.1186/s12874-018-0585-8 |
| work_keys_str_mv | AT fengqingzhang applicationofanewdietarypatternanalysismethodinnutritionalepidemiology AT tinashemtapera applicationofanewdietarypatternanalysismethodinnutritionalepidemiology AT jiangtaogou applicationofanewdietarypatternanalysismethodinnutritionalepidemiology |