Identifying depression in the National Health and Nutrition Examination Survey data using a deep learning algorithm

Oh, Jihoon; Yun, Kyongsik; Maoz, Uri; Kim, Tae-Suk; Chae, Jeong‐Ho

doi:10.1016/j.jad.2019.06.034

Cited by 54 publications

(36 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have effectively predicted psychiatric diseases such as depression using large scale data. Similar to our study, one research team has predicted patients of depression in the general population with an AUC of 0.89 using a deep learning technique based on K-NHANES (16). In addition, another group has predicted the response of patients with major depressive disorder to selective serotonin reuptake inhibitors with an AUC of 0.82 by deep learning (40).…”

Section: Discussionsupporting

confidence: 61%

“…Recently, deep learning has been actively used to screen and predict psychiatric diseases based on these predictors (15). A recent study has effectively identified patients with depression based on data of a large-scale survey from the United States, the National Health and Nutrition Examination Survey (16). Another study has also identified anxious and depressive participants using socio-demographic, occupational, and healthrelated information (17).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES

et al. 2021

Self Cite

View full text Add to dashboard Cite

Purpose: The number of patients with alcohol-related problems is steadily increasing. A large-scale survey of alcohol-related problems has been conducted. However, studies that predict hazardous drinkers and identify which factors contribute to the prediction are limited. Thus, the purpose of this study was to predict hazardous drinkers and the severity of alcohol-related problems of patients using a deep learning algorithm based on a large-scale survey data.Materials and Methods: Datasets of National Health and Nutrition Examination Survey of South Korea (K-NHANES), a nationally representative survey for the entire South Korean population, were used to train deep learning and conventional machine learning algorithms. Datasets from 69,187 and 45,672 participants were used to predict hazardous drinkers and the severity of alcohol-related problems, respectively. Based on the degree of contribution of each variable to deep learning, it was possible to determine which variable contributed significantly to the prediction of hazardous drinkers.Results: Deep learning showed the higher performance than conventional machine learning algorithms. It predicted hazardous drinkers with an AUC (Area under the receiver operating characteristic curve) of 0.870 (Logistic regression: 0.858, Linear SVM: 0.849, Random forest classifier: 0.810, K-nearest neighbors: 0.740). Among 325 variables for predicting hazardous drinkers, energy intake was a factor showing the greatest contribution to the prediction, followed by carbohydrate intake. Participants were classified into Zone I, Zone II, Zone III, and Zone IV based on the degree of alcohol-related problems, showing AUCs of 0.881, 0.774, 0.853, and 0.879, respectively.Conclusion: Hazardous drinking groups could be effectively predicted and individuals could be classified according to the degree of alcohol-related problems using a deep learning algorithm. This algorithm could be used to screen people who need treatment for alcohol-related problems among the general population or hospital visitors.

show abstract

Section: Discussionsupporting

confidence: 61%

Section: Introductionmentioning

confidence: 99%

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The NHANES and K-NHANES are nationwide surveys that assess the health and nutritional status of the general population in each country. We recently analyzed the NHANES and K-NHANES datasets and classified depression (20). This two-year cross-sectional survey addresses complex, multistage, stratified sampling of the entire population.…”

Section: Datasets and Covariatesmentioning

confidence: 99%

Association Between Macronutrients Intake and Depression in the United States and South Korea

Yun

Chae

et al. 2020

Front. Psychiatry

Self Cite

View full text Add to dashboard Cite

Although the risk for depression appears to be related to daily dietary habits, how the proportion of major macronutrients affects the occurrence of depression remains largely unknown. This study aims to estimate the association between macronutrients (i.e., carbohydrate, protein, fat) and depression through national survey datasets from the United States and South Korea. Association between the prevalence of depression and each macronutrient was measured from 60,935 participants from the National Health and Nutrition Examination Survey (NHANES) and 15,700 participants from the South Korea NHANES (K-NHANES) databases. When the proportion of calories intake by protein increased by 10%, the prevalence of depression was significantly reduced both in the United States [Odds Ratio, OR (95% CI), 0.621 (0.530-0.728)] and South ]. An association between carbohydrate intake and the prevalence of depression was seen in the United States [1.194 (1.116-1.277)], but not in South Korea. Fat intake was not significantly associated with depression in either country. Subsequent analysis showed that the low protein intake groups had significantly higher risk for depression than the normal protein intake groups in both the United States [1.648 (1.179-2.304)] and South ]. In the daily diet of macronutrients, the proportion of protein intake is significantly associated with the prevalence of depression. These associations were more prominent in adults with insufficient protein intake, and the pattern of association between macronutrients and depression in Asian American and South Korean populations were similar. Our findings suggest that the proportion of macronutrients intake in everyday life may be related to the occurrence of depression.

show abstract

“…Because the device is always connected to the network, data points cannot be lost and the generated data can be automatically saved and configured for later analysis. Future machine learning-based analysis will allow us to predict cholesterol levels and calculate a patient's risk of metabolic disease [16,17].…”

Section: Resultsmentioning

confidence: 99%

Smartphone-Based Point-of-Care Cholesterol Blood Test Performance Evaluation Compared with a Clinical Diagnostic Laboratory Method

et al. 2019

Self Cite

View full text Add to dashboard Cite

Featured Application: Faster, more convenient point-of-care cholesterol blood test.Abstract: Managing blood cholesterol levels is important for the treatment and prevention of diabetes, cardiovascular disease, and obesity. An easy-to-use, portable cholesterol blood test could accelerate more frequent testing by patients and at-risk populations. We aim to evaluate the performance of smartphone-based point-of-care cholesterol blood tests compared to that of hospital-grade laboratory tests. We used smartphone systems that are already familiar to many people. Because smartphone systems can be carried around everywhere, blood can be measured easily and frequently. We compared the results of cholesterol tests with those of existing clinical diagnostic laboratory methods. We found that smartphone-based point-of-care lipid blood tests were as accurate as hospital-grade laboratory tests (N = 116, R > 0.97, p < 0.001 for all three cholesterol blood tests, i.e., total cholesterol, high density lipoprotein, and triglyceride). Our system could be useful for those who need to manage blood cholesterol levels to motivate them to track and control their behavior.

show abstract

Identifying depression in the National Health and Nutrition Examination Survey data using a deep learning algorithm

Cited by 54 publications

References 34 publications

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES

Association Between Macronutrients Intake and Depression in the United States and South Korea

Smartphone-Based Point-of-Care Cholesterol Blood Test Performance Evaluation Compared with a Clinical Diagnostic Laboratory Method

Contact Info

Product

Resources

About