一种可解释的基于机器学习的方法来预测ADHD中神经反的治疗反应.
1Department of Biomedical Engineering and Medical Physics, School of Medicine, Shahid Beheshti University of Medical Sciences , Tehran, Iran.
Scientific reports
|December 4, 2025
概括
这项研究开发了一个可解释的AI框架来预测注意力缺陷多动症 (ADHD) 治疗反应. 该模型仅使用七个关键特征实现了88.3%的准确性,从而实现了个性化的ADHD干预.
科学领域:
- 神经科学是一个神经科学.
- 人工智能的人工智能
- 医疗信息学 医疗信息学
背景情况:
- 注意缺陷多动症 (ADHD) 是一种复杂的神经发育障碍,由于其异质性,需要个性化治疗.
- 现有的ADHD治疗反应预测模型往往缺乏透明度,阻碍了临床信任和采用.
- 早期和有效的干预对于减轻未经治疗的多动症的长期影响至关重要.
研究的目的:
- 引入一种新的,可解释的机器学习框架,用于预测ADHD患者的神经反治疗反应.
- 通过提供对治疗预测的透明和临床可操作的见解来增强个性化的ADHD干预.
- 通过使用先进的特征选择和可解释性技术,确定神经反治疗反应的关键预测特征.
主要方法:
- 利用来自TDBRAIN数据库的72名多动症患者的数据集,包括78个特征 (人口,行为,NEO-FFI).
- 采用分层特征选择方法:初始统计选,然后使用四种减少方法进行序列前选择 (SFS).
- 使用五个分类器 (随机森林,SVM,物流回归,ANN,自适应提升) 开发和评估预测模型,并使用SHAP值来解释可解释性.
主要成果:
- 一种分层的特征选择方法,最终在SFS中,确定了七个最佳特征,这些特征显著提高了随机森林模型的准确性,达到88.3%±6.8%.
- 关键预测特征包括特定的NEO-FFI问题和教育水平,七个SFS特征中的五个被SHAP值确定为非常重要的.
- 可解释的人工智能框架提供了全球特征重要性和本地解释,展示了模型的一致性并突出了关键的预测因素.
结论:
- 开发的透明机器学习框架实现了ADHD神经反治疗反应的高预测性能,超过了之前的研究.
- 该模型的可解释性促进了信任,并支持针对ADHD干预的个性化,数据驱动的医疗决策.
- 这种方法超越了"黑子"的预测,提供了临床上可行的见解,以定制神经反疗法以适应个体ADHD患者.
更多相关视频
10:02Event Related Potentials ERPs and other EEG Based Methods for Extracting Biomarkers of Brain Dysfunction: Examples from Pediatric Attention Deficit/Hyperactivity Disorder ADHD
Published on: March 12, 2020
16.6K
05:19Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
Published on: July 7, 2023
3.2K
相关概念视频
01:21Drugs Affecting Neurotransmitter Release or Uptake
Certain drugs can affect how neurotransmitters called catecholamines, are released or taken back up in the adrenergic neuron. They can have different effects on the body's sympathetic transmission. Reserpine, a natural compound found in the Rauwolfia shrub, blocks a transporter called vesicular monoamine transporter (VMAT), which leads to a buildup of catecholamines in the cell and reduces sympathetic transmission. Another drug called guanethidine works in multiple ways, including blocking...
01:30Attention-Deficit/Hyperactivity Disorder
Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by persistent inattention, hyperactivity, and impulsivity. It affects approximately 5-8% of children globally, with around 60-70% of cases persisting into adulthood. ADHD has significant implications for educational attainment, social interactions, and occupational success.
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings.
Diagnostic Criteria and Symptoms
To diagnose ADHD, symptoms must manifest before age 12 and be evident across multiple settings.