在巴西一个大型社区样本中,使用机器学习技术进行自杀风险分类
Thiago Henrique Roza1, Gabriel de Souza Seibel2, Mariana Recamonde-Mendoza3
1Department of Psychiatry, Universidade Federal do Paraná (UFPR), Curitiba, PR, Brazil; Laboratory of Molecular Psychiatry, Centro de Pesquisa Experimental (CPE) and Centro de Pesquisa Clínica (CPC), Hospital de Clínicas de Porto Alegre (HCPA), Porto Alegre, RS, Brazil; Graduate Program in Psychiatry and Behavioral Sciences, Department of Psychiatry, Faculty of Medicine, Universidade Federal do Rio Grande do Sul (UFRGS), Porto Alegre, RS, Brazil.
机器学习模型有效地识别了巴西常见精神障碍患者的自杀风险增加. 抑郁症症状是关键预测因素,使潜在的早期干预措施能够预防自杀.
科学领域:
- 精神病学是一个精神病学.
- 机器学习 机器学习
- 公共卫生 公共卫生
背景情况:
- 自杀是可以预防的结果,但准确的预测仍然具有挑战性.
- 常见的精神障碍与增加自杀风险有关.
- 早期识别有风险的个体对于预防性干预至关重要.
研究的目的:
- 开发和评估机器学习分类器,以识别增加的自杀风险.
- 分析临床和社会人口统计数据,以预测巴西人口中自杀风险.
- 为了确定分类自杀风险的最相关的特征.
主要方法:
- 利用了巴西社区样本中4039名成年参与者的基线临床和社会人口统计数据.
- 开发和比较机器学习模型,包括弹性网,随机森林,天真贝叶斯和整体方法.
- 使用诸如AUC ROC (接收器操作特征曲线下的面积),灵敏度和特异性等指标评估模型性能.
主要成果:
- 1120名参与者 (27.7%) 显示自杀风险增加.
- 随机森林模型实现了最高的AUC ROC (0.814),其次是天真湾 (0.798) 和弹性网 (0.773).
- 与抑郁症症状相关的特征在分类增加自杀风险方面影响最大.
结论:
- 机器学习模型在研究人群中对自杀风险增加的分类方面表现良好.
- 开发的模型可以帮助早期识别那些自杀风险较高的人.
- 这些发现支持针对常见精神障碍实施有针对性的预防性干预.
更多相关视频
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
相关概念视频
Cancer Survival Analysis
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Kaplan-Meier Approach
Assumptions of Survival Analysis
Comparing the Survival Analysis of Two or More Groups
Relative Risk
