相关实验视频

Updated: Jul 14, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

早期亨廷顿病的预后丰富:用于临床试验的可解释的机器学习方法

Mohsen Ghofrani-Jahromi¹, Govinda R Poudel², Adeel Razi¹

¹Turner Institute for Brain and Mental Health, Monash University, Clayton VIC3800, Australia.

NeuroImage. Clinical

|August 14, 2024

概括

使用脑成像和遗传数据的机器学习模型改善了临床试验中的亨廷顿病 (HD) 分层. 这种方法提高了预后的准确性,并有助于选择个性化的治疗方法,以治疗HD基因扩张载体.

科学领域:

神经科学是一个神经科学.
生物医学工程生物医学工程
遗传学遗传学是一个

背景情况:

亨廷顿病 (HD) 临床试验通常使用遗传负荷和临床分数进行招募,忽视体内脑成像标记物.
机器学习 (ML) 可以利用多式联络生物标志物来改善疾病预后和分层.
将ML模型定制为HD基因扩张载体可以提高分层的有效性.

研究的目的:

为了提高亨廷顿病患者的分层,以便进行更有效的临床试验.
开发 ML 模型,整合多种生物标志物,以提高 HD 的预后准确性.

主要方法:

利用了451名亨廷顿病 (HD) 基因扩张的个体的数据.
应用全脑分片对纵向脑部扫描,测量横向心室扩大超过3年.
使用遗传负载,认知/运动分数和脑成像特征训练随机森林回归模型;开发了一个简化的分层模型.

主要成果:

将脑成像特征与遗传和临床数据相结合,模型误差减少了24% (平均绝对误差为530 mm3/年).
该分层模型在区分中度和快速进展者 (83%的精度,80%的回忆) 中实现了81%的交叉验证准确性.

结论:

根据心室膨胀率验证了ML在分层HD个体中的有效性.
在疾病特异性模型上训练的疾病特异性模型提供了比使用健康对照的人更准确的预后方法.
该方法可以改善临床试验招募,个体评估和个性化HD治疗选择.

关键词:

生物标志物生物标志物临床试验临床试验亨廷顿氏病是亨廷顿氏病的一种疾病.机器学习机器学习神经成像是一种神经成像.分层分层是指分层的分层.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

相关概念视频

Pharmacogenomics: Identification of New Drug Targets

Pharmacogenomics: Identification of New Drug Targets

Advances in genomics have profoundly influenced drug discovery by increasing both the speed and accuracy of pharmaceutical development. Pharmacogenomics, which examines how genetic variation influences drug response, facilitates the identification of novel therapeutic targets and enables patient stratification for personalized treatment. These strategies contribute to improved drug efficacy, minimized adverse effects, and more efficient clinical trial design.Mapping genetic differences...

Huntington Disease l: Introduction

Huntington Disease l: Introduction

Huntington disease or HD is a progressive, fatal neurodegenerative disorder inherited in an autosomal dominant pattern.PathophysiologyIt is caused by expansion of the CAG trinucleotide repeat in the HTT gene on chromosome 4 (4p16.3), producing an abnormal huntingtin protein with an expanded polyglutamine tract. This misfolded protein disrupts cellular function, leading to neuronal death. Normal alleles have ≤26 repeats, 27–35 are intermediate (risk of expansion), 36–39 show reduced penetrance,...