Department of Psychiatry, Seoul St. Mary's Hospital, The Catholic University of Korea, College of Medicine, 222 Banpo-Daero, Seocho-Gu, Seoul 06591, Republic of Korea.
Computation and Neural Systems, California Institute of Technology, Pasadena, CA 91125, USA; Bio-Inspired Technologies and Systems, Jet Propulsion Laboratory, California Institute of Technology, Pasadena, CA 91109, USA.
J Affect Disord. 2019 Oct 1;257:623-631. doi: 10.1016/j.jad.2019.06.034. Epub 2019 Jul 4.
As depression is the leading cause of disability worldwide, large-scale surveys have been conducted to establish the occurrence and risk factors of depression. However, accurately estimating epidemiological factors leading up to depression has remained challenging. Deep-learning algorithms can be applied to assess the factors leading up to prevalence and clinical manifestations of depression.
Customized deep-neural-network and machine-learning classifiers were assessed using survey data from 19,725 participants from the NHANES database (from 1999 through 2014) and 4949 from the South Korea NHANES (K-NHANES) database in 2014.
A deep-learning algorithm showed area under the receiver operating characteristic curve (AUCs) of 0.91 and 0.89 for detecting depression in NHANES and K-NHANES, respectively. The deep-learning algorithm trained with serial datasets (NHANES, from 1999 to 2012), predicted the prevalence of depression in the following two years of data (NHANES, 2013 and 2014) with an AUC of 0.92. Machine learning classifiers trained with NHANES could further predict depression in K-NHANES. There, logistic regression had the highest performance (AUC, 0.77) followed by deep learning algorithm (AUC, 0.74).
Deep neural-networks managed to identify depression well from other health and demographic factors in both the NHANES and K-NHANES datasets. The deep-learning algorithm was also able to predict depression relatively well on new data set-cross temporally and cross nationally. Further research can delineate the clinical implications of machine learning and deep learning in detecting disease prevalence and progress as well as other risk factors for depression and other mental illnesses.
抑郁症是全球导致残疾的主要原因，因此进行了大规模调查以确定抑郁症的发生和风险因素。然而，准确评估导致抑郁症的流行病学因素仍然具有挑战性。深度学习算法可用于评估导致抑郁症患病率和临床表现的因素。
使用来自 NHANES 数据库（1999 年至 2014 年）的 19725 名参与者和 2014 年韩国 NHANES（K-NHANES）数据库的 4949 名参与者的调查数据，评估定制的深度神经网络和机器学习分类器。
深度学习算法在 NHANES 和 K-NHANES 中分别显示出 0.91 和 0.89 的接收者操作特征曲线下面积（AUCs），用于检测抑郁症。使用系列数据集（NHANES，1999 年至 2012 年）训练的深度学习算法，在随后两年的数据（NHANES，2013 年和 2014 年）中预测抑郁症的患病率，AUC 为 0.92。使用 NHANES 训练的机器学习分类器可以进一步预测 K-NHANES 中的抑郁症。在这里，逻辑回归的表现最佳（AUC，0.77），其次是深度学习算法（AUC，0.74）。
深度神经网络成功地从 NHANES 和 K-NHANES 数据集中的其他健康和人口统计学因素中识别出抑郁症。深度学习算法也能够在新数据集（跨时间和跨国家）上相对较好地预测抑郁症。进一步的研究可以描绘机器学习和深度学习在检测疾病患病率和进展以及其他抑郁症和其他精神疾病的风险因素方面的临床意义。
