在精神病医疗记录中的机器学习:创伤注释的黄金标准方法
Bruce Atwood1, Eben Holderness1,2, Marc Verhagen2
1Psychosis Neurobiology Laboratory, McLean Hospital, Belmont, MA.
medRxiv : the preprint server for health sciences
|March 31, 2025
概括
研究人员从精神病学电子健康记录创建了一个黄金标准数据集,用于训练机器学习模型. 这一数据集有助于检测症状,物质使用和创伤,推进精神病医疗保健.
科学领域:
- 计算语言学 计算语言学
- 精神病医疗保健 精神病医疗保健 精神病医疗保健
- 机器学习 机器学习
背景情况:
- 精神病学电子健康记录 (EHR) 是复杂且无结构的,这给机器学习 (ML) 应用带来了挑战.
- 准确识别临床信息,如创伤,对于理解疾病异质性和精神疾病治疗至关重要.
研究的目的:
- 开发一个黄金标准,公开可用的数据集,注释精神病学EHRs.
- 为创伤事件的注释制定临床信息的指导方针.
- 证明数据集对训练ML模型来检测症状,物质使用和创伤的实用性.
主要方法:
- 编制了200个叙事重重的精神病学EHR的语料库.
- 与临床专家和计算语言学家一起开发了一个详细的注释方案.
- 对创伤相关事件和临床信息进行了注释,实现了高的注释者间一致性 (跨度为0.715,属性为0.874).
主要成果:
- 创建了第一个黄金标准数据集,用于标记精神病EHR中的创伤特征.
- 实现了高的注释者间协议,表明可靠的注释.
- 开发了0.76 (跨度) 和0.82 (属性) 的微F1得分的ML模型,证明了预测可靠性.
结论:
- 建立的黄金标准数据集适合在精神病医疗保健中训练ML模型.
- 该数据集有助于在电子健康记录中检测症状,物质使用和创伤.
- 该资源将促进ML应用,以了解精神疾病异质性和治疗影响.
相关概念视频
01:27Post-traumatic Stress Disorder
24
Post-traumatic stress disorder (PTSD) is a psychiatric condition that arises following exposure to traumatic events such as natural disasters, forced displacement, or severe accidents. It significantly impairs individuals' ability to cope with daily activities and disrupts their emotional and psychological equilibrium.
Symptoms and Behavioral Manifestations
A spectrum of distressing symptoms characterizes PTSD. Recurrent flashbacks, where individuals involuntarily relive traumatic events,...
Symptoms and Behavioral Manifestations
A spectrum of distressing symptoms characterizes PTSD. Recurrent flashbacks, where individuals involuntarily relive traumatic events,...
24
01:20Traumatic Memory
52
Emotionally traumatic events often lead to memories that are exceptionally vivid and enduring, sometimes persisting with remarkable clarity throughout an individual's life. A classic example of this phenomenon is a person who survives a car accident. Even years later, they may recall every detail of the event with startling accuracy — the screeching of the tires, the jarring impact, and the acrid smell of burning rubber. Such vividness contrasts sharply with how an individual...
52