Application of the deep learning algorithm in nutrition research - using serum pyridoxal 5'-phosphate as an example

Chaoran Ma; Qipin Chen; Diane C Mitchell; Muzi Na; Katherine L Tucker; Xiang Gao

doi:10.1186/s12937-022-00793-x

Application of the deep learning algorithm in nutrition research - using serum pyridoxal 5'-phosphate as an example

Nutr J. 2022 Jun 10;21(1):38. doi: 10.1186/s12937-022-00793-x.

Authors

Chaoran Ma^#¹, Qipin Chen^#², Diane C Mitchell³, Muzi Na³, Katherine L Tucker⁴, Xiang Gao⁵

Affiliations

¹ Channing Division of Network Medicine, Brigham and Women's Hospital and Harvard Medical School, Boston, MA, USA.
² Department of Mathematics, The Pennsylvania State University, University Park, State College, PA, USA.
³ Department of Nutritional Sciences, The Pennsylvania State University, University Park, State College, PA, USA.
⁴ Department of Biomedical & Nutritional Sciences, The University of Massachusetts at Lowell, Lowell, MA, USA.
⁵ Department of Nutrition and Food Hygiene, School of Public Health, Fudan University, 130 Dongan Rd, Shanghai, China. xiang_gao@fudan.edu.cn.

^# Contributed equally.

Abstract

Background: Multivariable linear regression (MLR) models were previously used to predict serum pyridoxal 5'-phosphate (PLP) concentration, the active coenzyme form of vitamin B6, but with low predictability. We developed a deep learning algorithm (DLA) to predict serum PLP based on dietary intake, dietary supplements, and other potential predictors.

Methods: This cross-sectional analysis included 3778 participants aged ≥20 years in the National Health and Nutrition Examination Survey (NHANES) 2007-2010, with completed information on studied variables. Dietary intake and supplement use were assessed with two 24-hour dietary recalls. We included potential predictors for serum PLP concentration in the models, including dietary intake and supplement use, sociodemographic variables (age, sex, race-ethnicity, income, and education), lifestyle variables (smoking status and physical activity level), body mass index, medication use, blood pressure, blood lipids, glucose, and C-reactive protein. We used a 4-hidden-layer deep neural network to predict PLP concentration, with 3401 (90%) participants for training and 377 (10%) participants for test using random sampling. We obtained outputs after sending the features of the training set and conducting forward propagation. We then constructed a loss function based on the distances between outputs and labels and optimized it to find good parameters to fit the training set. We also developed a prediction model using MLR.

Results: After training for 10⁵ steps with the Adam optimization method, the highest R² was 0.47 for the DLA and 0.18 for the MLR model in the test dataset. Similar results were observed in the sensitivity analyses after we excluded supplement-users or included only variables identified by stepwise regression models.

Conclusions: DLA achieved superior performance in predicting serum PLP concentration, relative to the traditional MLR model, using a nationally representative sample. As preliminary data analyses, the current study shed light on the use of DLA to understand a modifiable lifestyle factor.

Keywords: Deep learning; Dietary pattern; Multivariable linear regression; NHANES; Pyridoxal 5′-phosphate; Vitamin B6.

MeSH terms

Cross-Sectional Studies
Deep Learning*
Humans
Nutrition Surveys
Phosphates
Pyridoxal Phosphate

Substances

Phosphates
Pyridoxal Phosphate