Lee Chiyoung, Kim Yeri, Kim Seoyoung, Whooley Mary, Kim Heewon
The University of Arizona College of Nursing, Tucson, Arizona, United States of America.
Global School of Media, College of IT, Soongsil University, Seoul, Korea.
PLoS One. 2025 Sep 5;20(9):e0324169. doi: 10.1371/journal.pone.0324169. eCollection 2025.
Deep neural networks have achieved significant performance breakthroughs across a range of tasks. For diagnosing depression, there has been increasing attention on estimating depression status from personal medical data. However, the neural networks often act as black boxes, making it difficult to discern the individual effects of each input component. To alleviate this problem, we proposed a deep-learning-based generalized additive model called DeepGAM to improve the interpretability of depression diagnosis. We utilized the baseline cross-sectional data from the Heart and Soul Study to achieve our study's aim. DeepGAM incorporates additive functions based on a neural network that learns to discern the positive and negative impacts of the values of individual components. The network architecture and the objective function are designed to constrain and regularize the output values for interpretability. Moreover, we used a direct-through estimator (STE) to select important features using gradient descent. The STE enables machine learning models to maintain their performance using a few features and interpretable function visualizations. DeepGAM achieved the highest AUC (0.600) and F1-score (0.387), outperforming neural networks and IGANN. The five features selected via STE performed comparably to 99 features and surpassed traditional methods such as Lasso and Boruta. Additionally, analyses highlighted DeepGAM's interpretability and performance on public datasets. In conclusion, DeepGAM with STE demonstrated accurate and interpretable performance in predicting depression compared to existing machine learning methods.
深度神经网络在一系列任务中取得了显著的性能突破。对于抑郁症诊断，人们越来越关注从个人医疗数据中评估抑郁状态。然而，神经网络常常像黑匣子一样，难以辨别每个输入组件的个体影响。为了缓解这个问题，我们提出了一种基于深度学习的广义相加模型，称为深度广义相加模型（DeepGAM），以提高抑郁症诊断的可解释性。我们利用了来自“心灵研究”的基线横断面数据来实现我们的研究目标。深度广义相加模型结合了基于神经网络的相加函数，该网络学习辨别各个组件值的正面和负面影响。网络架构和目标函数的设计是为了约束和规范输出值以实现可解释性。此外，我们使用直通估计器（STE）通过梯度下降来选择重要特征。直通估计器使机器学习模型能够使用少量特征和可解释的函数可视化来保持其性能。深度广义相加模型实现了最高的曲线下面积（AUC）（0.600）和F1分数（0.387），优于神经网络和集成梯度人工神经网络（IGANN）。通过直通估计器选择的五个特征与99个特征的表现相当，并且超过了诸如套索回归和博鲁塔算法等传统方法。此外，分析突出了深度广义相加模型在公共数据集上的可解释性和性能。总之，与现有的机器学习方法相比，带有直通估计器（STE）的深度广义相加模型在预测抑郁症方面表现出准确且可解释的性能。
