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

Abstract

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.

Machine learning model for depression based on heavy metals among aging people: A study with National Health and Nutrition Examination Survey 2017–2018

“…The world depression survey conducted in 17 countries found that on average, 1 in 20 people had depression. By 2020, the global disease burden might increase by 5.7%, becoming the second largest disease after ischemic heart disease ( 4 ).…”

Time perspective and family history of alcohol dependence moderate the effect of depression on alcohol dependence: A study in Chinese psychiatric clinics

“…Even though R 2 was small, it revealed a significant contribution to the model. Meanwhile, one study that had included 325 variables in 69,187 participants, and implemented deep learning to predict outcome variables (Kim et al, 2021 ). This result suggests that the use of a larger dataset, the inclusion of more predictors, and the implementation of more advanced algorithms will be valuable in future studies.…”

Artificial Intelligence and Precision Nutrition

“…Machine learning is a type of AI, and it can be altered after exposure to novel data sets and “learn” without new programming (3). In addition, deep learning has been involved in the prediction of certain diseases (5,6).…”