使用机器学习预测精神分裂症的缓解 - - 评估样本大小和预测器过度包含的影响
Fredrik Hieronymus1,2, Magnus Hieronymus3, Axel Sjöstedt1
1Institute of Neuroscience and Physiology, University of Gothenburg, Gothenburg, Sweden.
Acta psychiatrica Scandinavica
|September 10, 2025
概括
机器学习可以从小的数据集中预测精神分裂症的结果,但只有在排除无信息预测因素的情况下. 谨慎的特征选择对于精神病学研究中可概括的结果至关重要.
科学领域:
- 精神病学是一个精神病学.
- 机器学习 机器学习
- 计算神经科学是一种神经科学.
背景情况:
- 机器学习研究的风险是过度匹配和糟糕的概括性,与许多与训练案例相关的预测因素.
- 以前的研究表明,试验异质性限制了精神分裂症结果的预测.
- 另一个解释是预测因子的过度包含导致了低的概括性.
研究的目的:
- 调查预测因素纳入对机器学习模型对精神分裂症预测结果概括性的影响.
- 评估监督学习模型的性能,使用不同数量的培训案例和预测器集.
- 确定预测因子过度包容性,而不是异质性,是否解释了精神分裂症预测模型的普遍性差.
主要方法:
- 使用的阳性和阴性综合征量表 (PANSS) 项目数据,年龄,性别和治疗分配来自18项试验.
- 训练了五个监督学习模型,以预测4周后的症状缓解.
- 通过各种培训案例和模拟的非信息预测因素进行了敏感性分析,包括对模拟数据的分析.
主要成果:
- 只有384个培训案例实现了比机会更好的预测 (BAC 0.60).
- 随着更多的训练案例 (BAC 0.63),模型性能得到了改善,并且在没有安慰剂对照的未见试验中 (BAC 0.68) 更高.
- 包括不信息预测因素在内,预测性能大大下降;可能需要更大的样本大小来区分弱和不信息预测因素.
结论:
- 监督学习模型可以从小的数据集预测精神分裂症的结果,如果最小化了无信息预测因素.
- 缺乏高预测性模型表明,临床试验数据可能缺乏对结果的强有力的线性预测因素.
- 未来的机器学习分析应优先确定预测能力较弱的特征,以提高可概括性.
更多相关视频
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
8.6K
10:46A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
11.0K
相关概念视频
Psychological and Sociocultural Causes of Schizophrenia
482
Schizophrenia, a complex psychiatric disorder, has been historically misunderstood. Early psychological theories attributed its origins to childhood trauma and unresponsive parenting. However, contemporary research largely rejects these notions, favoring the vulnerability-stress hypothesis. This model proposes that individuals with a genetic predisposition to schizophrenia may develop the disorder following exposure to significant environmental stressors. Notably, studies on high-risk...
482
Survival Tree
390
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
390
Steps in Outbreak Investigation
494
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:
494
Regression Toward the Mean
6.9K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.9K
