生态瞬间评估和机器学习用于预测性和性别少数群体个人中自杀想法
Chang Lei1,2, Diyang Qu1,2, Kunxu Liu1,2
1Vanke School of Public Health, Tsinghua University, Beijing, China.
JAMA network open
|September 11, 2023
概括
在性和性别少数群体中,日常情绪波动和压力事件可以预测自杀想法. 使用生态瞬间评估 (EMA) 的机器学习模型对早期自杀风险识别有希望.
科学领域:
- 心理健康 心理健康
- 精神病学是一个精神病学.
- 公共卫生 公共卫生
背景情况:
- 自杀是一种重要的全球健康问题,不成比例地影响性和性别少数群体 (SGM) 人口.
- 虽然研究了慢性压力因素,但日常经历对SGM个体自杀思想的预测影响需要进一步调查.
研究的目的:
- 评估日常情绪波动和压力事件对SGM个体短期和长期自杀思想的预测能力.
- 为了比较不同的机器学习方法在预测自杀想法方面的有效性.
主要方法:
- 一项涉及103名中国18-29岁SGM个体的诊断研究.
- 每天两次收集25天的情绪和压力数据,跨越三个中国农历新年浪潮.
- 机器学习模型 (基线,生态瞬间评估 (EMA) 和组合) 用于预测自杀念头在数据收集后的1,3,8个月.
主要成果:
- 在1个月的随访期内,EMA方法显示出对自杀念头的优异预测 (AUC=0.80),并在3个月和8个月后表现稍好一些.
- 最准确的预测是在农历新年期间实现的,AUC为0.77 (1个月),0.74 (3个月) 和0.72 (8个月).
- 自杀念头的患病率从基线 (18.4%) 增加到8个月的随访 (31.1%).
结论:
- 每天的背景因素显著影响SGM个体的自杀想法.
- 机器学习,特别是EMA,可以识别有风险的个人.
- 研究结果支持开发个性化,基于过程的SGM自杀风险早期预防计划.
相关概念视频
01:18Steps in Outbreak Investigation
152
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
152
01:27Ethnic Identity within a Larger Culture
58
Adolescents from ethnic minority backgrounds face a multifaceted journey in forming their identities, shaped by the intersections of cultural expectations and personal exploration. For these adolescents, identity formation involves not only typical developmental challenges but also navigating the perceptions and attitudes of the majority culture. As they grow, adolescents in ethnic minority groups often become increasingly aware of stereotypes, social biases, and discrimination, all of which...
58