Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Depression: Overview

Depression: Overview

Depression is a prevalent mental illness marked by persistent sadness and lack of interest in previously enjoyable activities. It can take several forms, including major depression, persistent depressive disorder, and bipolar I and II disorders. Symptoms range from emotional changes like chronic worry to physical changes like sleep disturbances and suicidal thoughts. From a neurobiological perspective, depression is believed to be triggered by abnormalities in the brain's prefrontal cortex,...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Optimizing Radiographic Diagnosis Through Signal-Balanced Convolutional Models.

Journal of imaging·2026

Same author

Classifying complex multimorbidity using latent class analysis and machine learning to generate insights into clustering of mental and cardiometabolic conditions.

PloS one·2025

Same author

Author Correction: Transforming healthcare through just, equitable and quality driven artificial intelligence solutions in South Asia.

NPJ digital medicine·2025

Same author

Transforming healthcare through just, equitable and quality driven artificial intelligence solutions in South Asia.

NPJ digital medicine·2025

Same author

Analyzing the Impact of Active Attack on the Performance of the AMCTD Protocol in Underwater Wireless Sensor Networks.

Sensors (Basel, Switzerland)·2023

Same author

Missing Link Prediction using Common Neighbor and Centrality based Parameterized Algorithm.

Scientific reports·2020

Search research articles

相关实验视频

Updated: Jan 18, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

可解释的AI用于从活动数据中检测抑郁症和严重程度分类:可解释框架的开发和评估研究.

Iftikhar Ahmed¹, Anushree Brahmacharimayum¹, Raja Hashim Ali¹

¹Department of Software Engineering, University of Europe for Applied Sciences, Germany, Potsdam, Germany.

JMIR mental health

|September 11, 2025

概括

这项研究开发了一个可解释的机器学习框架,使用可穿戴数据来检测抑郁症及其严重程度. 可解释的AI方法确定了关键预测因素,如年龄和活动模式,有助于早期心理健康干预.

关键词:

活动数据活动数据人工智能的人工智能是人工智能.抑郁抑郁症抑郁症抑郁症是一种可以解释的人工智能AI 机器学习是机器学习.心理健康心理健康

更多相关视频

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

相关实验视频

Last Updated: Jan 18, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

科学领域:

可穿戴技术和数字健康
机器学习在心理健康中的应用
可解释的人工智能 (XAI)

背景情况:

抑郁症影响全球2.8亿人,往往未被诊断出来,强调需要客观的检测方法.
可穿戴设备为数据驱动的抑郁症评估提供持续活动监测.
现有的机器学习模型与抑郁症亚型分类扎,缺乏临床透明度.

研究的目的:

开发和评估可解释的机器学习框架,用于抑郁症检测和严重程度分类.
利用可穿戴的行为图形数据来克服不平衡数据集和模型透明度的挑战.
在心理健康诊断中通过可解释的AI提高临床接受度.

主要方法:

应用自适应合成采样 (ADASYN) 来解决Depresjon数据集中的类不平衡问题.
从活动日志中提取统计特征 (例如,功率光谱密度平均值,自相关) 和人口统计数据.
评估了五种机器学习算法 (逻辑回归,SVM,随机森林,XGBoost,神经网络),使用标准性能指标,并使用SHAP和LIME进行解释.

主要成果:

XGBoost表现出卓越的性能,对二进制分类的准确率为84.94%,对多类严重性的准确率为85.91%.
沙普利添加式解释 (SHAP) 和局部可解释模型不可知解释 (LIME) 确定了功率光谱密度的平均值,年龄和自相关性作为重要的预测因素.
这些发现强调了昼夜节律中断在抑郁症中的作用,这是活动模式分析所表明的.

结论:

可解释的框架有效地区分了抑郁和非抑郁个体,并对抑郁症的严重程度进行了分类 (轻度与中度).
整合SHAP和LIME为预测驱动因素提供了透明,临床相关的见解.
可解释的人工智能对改善精神卫生保健中早期抑郁症检测和干预策略具有重大潜力.