Detecting Depression and Predicting its Onset Using Longitudinal Symptoms Captured by Passive Sensing: A Machine Learning Approach With Robust Feature Selection
Detecting Depression and Predicting its Onset Using Longitudinal Symptoms Captured by Passive Sensing: A Machine Learning Approach With Robust Feature Selection
复制标题
DOI：
10.1145/3422821
复制
发表时间：
2021-01-01
影响因子：
3.7
通讯作者：
Dey, Anind K.
中科院分区：
文献类型：
--
作者：
Chikersal, Prerna;Doryab, Afsaneh;Dey, Anind K.
我们提出了一种机器学习方法，使用来自138名大学生的智能手机和健身跟踪器的数据来识别在学期末经历抑郁症状的学生和随着学期的推移抑郁症状恶化的学生。我们的新方法是一种特征提取技术，它允许我们从纵向数据中选择指示抑郁症状的有意义的特征。它使我们能够检测到学期后抑郁症状的存在，准确率为85.7%，以及症状严重程度的变化，准确率为85.4%。它还在学期结束前11-15周预测了这些结果，准确率为80%，为先发制人的干预留出了充足的时间。我们的工作对于使用纵向行为数据和有限的地面事实来检测健康结果具有重要意义。通过检测变化并在症状出现前几周预测症状，我们的工作对预防抑郁症也有意义。
We present a machine learning approach that uses data from smartphones and fitness trackers of 138 college students to identify students that experienced depressive symptoms at the end of the semester and students whose depressive symptoms worsened over the semester. Our novel approach is a feature extraction technique that allows us to select meaningful features indicative of depressive symptoms from longitudinal data. It allows us to detect the presence of post-semester depressive symptoms with an accuracy of 85.7% and change in symptom severity with an accuracy of 85.4%. It also predicts these outcomes with an accuracy of >80%, 11-15 weeks before the end of the semester, allowing ample time for pre-emptive interventions. Our work has significant implications for the detection of health outcomes using longitudinal behavioral data and limited ground truth. By detecting change and predicting symptoms several weeks before their onset, our work also has implications for preventing depression.