预测麻醉症类型1中国患者的抑郁症:一种机器学习方法
Mengmeng Wang1, Huanhuan Wang1,2, Zhaoyan Feng1
1Division of Sleep Medicine, Peking University People's Hospital, Beijing, People's Republic of China.
Nature and science of sleep
|September 25, 2024
概括
机器学习模型可以预测1型麻醉症 (NT1) 患者的抑郁. 支持矢量机模型表现出最佳性能,识别了早期干预的关键预测因素.
科学领域:
- 神经学 神经学
- 精神病学是一个精神病学.
- 计算医学是一种计算医学.
背景情况:
- 抑郁症是1型麻醉症 (NT1) 中普遍存在的并发症.
- 准确预测抑郁症对于NT1患者的有效管理至关重要.
- 机器学习 (ML) 为识别预测因素提供了新的方法.
研究的目的:
- 确定预测中国NT1患者抑郁症的因素.
- 评估ML模型在NT1的抑郁症预测中的有效性.
- 开发一个基于数据的工具,用于个性化风险评估.
主要方法:
- 通过ICSD-3标准诊断的203名无药物NT1患者 (5-61岁) 被招募.
- 使用经过验证的尺度 (CES-DC/SDS,ESS/ESS-CHAD,BIS-11) 评估抑郁症,嗜睡和冲动性.
- 使用后勤回归 (LR),随机森林 (RF) 和支持矢量机器 (SVM) 模型进行预测,评估AUC,准确性,精度,回忆,F1和DCA的性能.
主要成果:
- 后勤回归确定了幻觉和运动冲动性作为NT1.中的显著抑郁预测因素.
- 支持矢量机 (SVM) 获得了最高的性能:AUC 0.653,准确度 0.659,灵敏度 0.727,F1得分 0.696.
- SVM有效地整合了与睡眠相关的和心理社会数据进行预测.
结论:
- ML模型,特别是SVM,显示出在NT1患者中预测抑郁症的巨大潜力.
- 这些发现支持开发个性化,数据驱动的工具,用于抑郁症风险分层.
- 建议在多种不同人群中进行进一步验证,并包含额外的心理变量,以提高预测准确度.
相关概念视频
01:07Narcolepsy
94
Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.
94
01:24Sleep-Wake Cycles
1.2K
Sleep is an essential physiological process vital to maintaining overall well-being. The reticular activating system (RAS), a network of neurons in the brainstem, regulates wakefulness and sleep. While it may seem passive, sleep consists of distinct cycles, each with its unique characteristics and functions. Two key sleep phases are non-rapid eye movement (NREM) and rapid eye movement (REM).
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
1.2K