基于SHAP的可解释机器学习分析奖励相关的神经连接,以预测青春期前的易怒性
Faith M Wariri1, Johanna C Walker2, Jillian Lee Wiggins2,3
1Department of Computer Science and Engineering, School of Computing, College of Engineering, University of Connecticut, Storrs, CT, USA.
Neuroimage. Reports
|February 2, 2026
概括
青春期前的易怒与奖励处理期间大脑连接的改变有关. 可解释的深度学习模型确定了特定的神经模式,区分了儿童的持续高易怒和低易怒.
科学领域:
- 神经科学是一个神经科学.
- 发展心理学 发展心理学
- 计算精神病学是一种计算精神病学.
背景情况:
- 青春期前的易怒性预测了未来的精神病理学,并与改变的奖励处理有关.
- 刺激性背后的神经生物学机制在很大程度上仍然不清楚.
- 深度学习 (DL) 在预测神经发育问题方面表现有前途,但往往缺乏可解释性.
研究的目的:
- 将优化预测与可解释性整合起来,使用DL来表征易怒的神经机制.
- 在青春期前,确定与持续高易怒 (PHI) 与持续低易怒 (PLI) 相关的功能连接 (FC) 模式.
- 为了利用沙普利增量解释 (SHAP) 来理解易怒的非线性大脑行为关系.
主要方法:
- 基于任务的功能磁共振成像 (fMRI) 数据来自大量青春期前的样本 (N=1934).
- 在奖励预期期间训练了三个DL分类器 (ANN,RF,XGBoost) 来区分使用FC的PHI和PLI.
- 在杏仁体/腹状条纹体种子和皮层/皮下区域之间评估了FC,使用SHAP来确定特征的重要性.
主要成果:
- 人工神经网络 (ANN) 实现了最高的预测准确性 (AUC=0.73).
- SHAP分析发现了特定的FC模式,使PHI与PLI有所区别.
- contralateral FC 的增加和 ipsilateral FC 的减少 (桃体除外) 预测了 PHI.
结论:
- 研究结果强调了奖励和情绪调节电路在持续性易怒的相互作用.
- 可解释的DL可以改善易怒性预测,并加深对其神经支的理解.
- 特定的功能性大脑连接性改变与青春期前持续的易怒性有关.
更多相关视频
相关概念视频
Irritable Bowel Syndrome I: Introduction
1.0K
Irritable Bowel Syndrome (IBS) is characterized by functional disturbances in the gastrointestinal system, presenting a cluster of symptoms without evident structural or biochemical abnormalities. It primarily affects the large intestine and may cause abdominal pain, bloating, excessive gas, diarrhea, constipation, or both.
IBS is a chronic condition that can persist over a long period or recur frequently.
The pathogenesis of IBS involves a complex interplay of the following factors:
Altered...
IBS is a chronic condition that can persist over a long period or recur frequently.
The pathogenesis of IBS involves a complex interplay of the following factors:
Altered...
1.0K
Machines
579
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. One example of a machine is the cutting plier, which is used to cut wires by applying forces to its handles. When equal and opposite forces are exerted on the handles of the cutting plier, they cause the cutting edges to come together and apply equal and opposite reaction forces on the wire, which are greater than the applied forces.
A free-body diagram of the...
A free-body diagram of the...
579
Predicting Molecular Geometry
45.8K
VSEPR Theory for Determination of Electron Pair Geometries
45.8K
Machines: Problem Solving II
668
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
668
Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K
Dietary Connections
61.9K
In biological systems, most metabolic pathways are interconnected. The cellular respiration processes that convert glucose to ATP—such as glycolysis, pyruvate oxidation, and the citric acid cycle—tie into those that break down other organic compounds. As a result, various foods—from apples to cheese to guacamole—end up as ATP. In addition to carbohydrates, food also contains proteins and lipids—such as cholesterol and fats. All of these organic compounds are used...
61.9K


