机器学习模型用于识别临床上显著的焦虑在短期失眠使用加速度计
Leqin Fang1,2,3, Weixiong Zeng4, Shuqiong Zheng1,2,3
1Department of Psychiatry, Sleep Medicine Center, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Depression and anxiety
|May 21, 2025
概括
临床显著焦虑 (CSA) 在短期失眠中加剧睡眠问题. 使用加速度计数据的机器学习模型有效地识别CSA,而昼夜节律特征是关键预测因素.
科学领域:
- 睡眠医学 睡眠医学
- 人工智能的人工智能
- 精神病学是一个精神病学.
背景情况:
- 临床显著焦虑 (CSA) 经常与短期失眠同时发生.
- 了解焦虑和睡眠参数之间的相互作用对于有效治疗至关重要.
研究的目的:
- 研究CSA与短期失眠中的主观/客观睡眠参数之间的关系.
- 开发机器学习 (ML) 模型,使用加速度计数据来识别CSA.
- 探索加速度计特征在识别失眠患者焦虑的实用性.
主要方法:
- 205名患有短期失眠的参与者被分为有 (N=33) 和没有 (N=172) CSA.的组.
- 线性回归分析了加速度计特征,CSA和睡眠问题之间的相互作用效应.
- 构建了多个ML模型 (4个特征集,8个算法);SHAP值评估了特征的重要性.
主要成果:
- CSA与更严重的主观睡眠问题有关.
- 在焦虑,体育活动持续时间和失眠严重程度 (P<0.05) 之间发现了显著的相互作用.
- 焦虑和日间稳定性与睡眠卫生相互作用 (P<0.01).
- 使用平日加速度计数据的XGBoost模型实现了0.777的CSA识别AUC.
- SHAP分析强调了昼夜节律特征的重要性.
结论:
- 机器学习有效地利用复杂的加速度计数据来识别短期失眠中的CSA.
- 加速度计衍生的特征,特别是昼夜节律指标,对于检测焦虑是有价值的.
- 基于SHAP的可视化为临床决策提供实用,个性化的见解.
相关概念视频
01:27Insomnia
78
Insomnia is a prevalent sleep disorder characterized by difficulty falling asleep, frequent awakenings during the night, and waking up too early without being able to return to sleep. People with insomnia often experience these disruptions at least three nights a week for at least one month. Chronic insomnia, which lasts for at least three months, can lead to increased anxiety, which in turn can worsen sleep difficulties, creating a cycle of sleeplessness and stress.
Multiple factors contribute...
Multiple factors contribute...
78
01:19Management of Insomnia
229
The sleep cycle, an integral part of human health, consists of several stages with distinct characteristics and functions. It begins with a transition from wakefulness to sleep, known as the light sleep phase, followed by the restorative deep sleep phase, essential for physical recovery and growth. The cycle concludes with the Rapid Eye Movement (REM) phase, characterized by high brain activity and vivid dreaming. Insomnia, a prevalent sleep disorder, involves difficulty falling asleep, staying...
229