根据智能手机收集的行为模式进行个性化情绪预测
Brunilda Balliu1,2,3, Chris Douglas4, Darsol Seok5
1Departments of Computational Medicine, University of California Los Angeles, Los Angeles, USA. bballiu@ucla.edu.
NPJ digital medicine
|February 28, 2024
概括
智能手机的数字行为表型可以在几周前准确地预测抑郁情绪. 这项研究提供了一种经过验证的,可扩展的方法,用于在临床人群中持续监测心理健康.
科学领域:
- 数字精神病学数字精神病学
- 计算精神病学是一种计算精神病学.
- 行为科学是一种行为科学.
背景情况:
- 智能手机的数字行为现象型显示出推断抑郁情绪的前景.
- 现有研究面临复制性,临床相关性和验证的纵向抑郁测量方面的挑战.
研究的目的:
- 评估高质量的可行性,使用数字表型和验证的措施进行纵向情绪评估.
- 从连续的数字行为数据开发和验证一个模型来预测未来的抑郁情绪严重程度.
主要方法:
- 从183名抑郁症患者长度收集数据 (长达40周),将情绪的计算机自适应测试与智能手机传感器数据相结合.
- 应用立方线插值和异形模型用于个性化情绪预测.
- 与仅使用过去抑郁症严重程度的基线模型进行比较.
主要成果:
- 在预测抑郁症严重程度方面,预测准确度高 (R2 ≥80%),提前可达三周.
- 与基线模型相比,预测错误减少了65.7%.
- 获得高质量的纵向情绪评估和预测症状严重程度的可行性.
结论:
- 被动收集的数字行为数据可以准确,长期预测抑郁症状严重程度.
- 这种方法增强了未来精神病学研究的患者特异性行为措施.
- 数字表型为心理健康监测提供了一个可扩展和验证的工具.
相关概念视频
Traits, Mood, and Subjective Wellbeing
72
Subjective well-being (SWB) refers to an individual's self-evaluation of their overall life satisfaction, happiness, and fulfillment. This multifaceted construct is typically assessed by analyzing the balance of positive and negative emotions alongside perceptions of life satisfaction. Personality traits such as neuroticism and extraversion are strongly associated with variations in SWB, offering critical insights into the underlying mechanisms of emotional well-being.
Neuroticism and...
Neuroticism and...
72
Nonconscious Mimicry
4.6K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
4.6K
Traits and States
240
Personality traits represent consistent patterns in behavior, thoughts, and emotions, reflecting an individual's tendencies across various situations. For example, extraversion, a well-known trait, manifests in individuals as talkative, energetic, and enthusiastic behaviors. These traits are stable over time, offering a reliable framework for predicting how people might act in different contexts. However, they do not define every moment of an individual's life. In contrast to traits,...
240


