Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore; Department of Radiology, Dalio Institute of Cardiovascular Imaging, NewYork-Presbyterian Hospital and the Weill Cornell Medicine, New York, United States.
Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore; Residential College 4, 8 College Avenue West, #02-16W, Education Resource Centre, Singapore 138608, Singapore.
J Neurosci Methods. 2018 Jul 15;305:105-116. doi: 10.1016/j.jneumeth.2018.05.009. Epub 2018 May 22.
Understanding disease progression of neurodegenerative diseases (NDs) is important for better prognosis and decisions on the appropriate course of treatment to slow down the disease progression.
We present here an innovative machine learning framework capable of (1) indicating the trajectory of disease progression by identifying relevant imaging biomarkers and (2) automated disease diagnosis. Self-Organizing Maps (SOM) have been used for data dimensionality reduction and to reveal potentially useful disease-specific biomarkers, regions of interest (ROIs). These ROIs have been used for automated disease diagnosis using Least Square Support Vector Machines (LS-SVM) and to delineate disease progression.
A multi-site, multi-scanner dataset containing 1316 MRIs was obtained from ADNI and PPMI. Identified biomarkers have been used to decipher (1) trajectory of disease progression and (2) identify clinically relevant ROIs. Furthermore, we have obtained a classification accuracy of 94.29 ± 0.08% and 95.37 ± 0.02% for distinguishing AD and PD from HC subjects respectively.
The goal of this study was fundamentally different from other machine learning based studies for automated disease diagnosis. We aimed to develop a method that has two-fold benefits (1) It can be used to understand pathology of neurodegenerative diseases and (2) It also achieves automated disease diagnosis.
In the absence of established disease biomarkers, clinical diagnosis is heavily prone to misdiagnosis. Being clinically relevant and readily adaptable in the current clinical settings, the developed framework could be a stepping stone to make machine learning based Clinical Decision Support System (CDSS) for neurodegenerative disease diagnosis a reality.
了解神经退行性疾病（NDs）的疾病进展对于改善预后和做出适当的治疗方案决策以减缓疾病进展非常重要。
我们在这里提出了一种创新的机器学习框架，能够（1）通过识别相关的成像生物标志物来指示疾病进展的轨迹，以及（2）实现自动疾病诊断。自组织映射（SOM）已被用于数据降维和揭示潜在有用的疾病特异性生物标志物、感兴趣区域（ROIs）。这些 ROI 已被用于使用最小二乘支持向量机（LS-SVM）进行自动疾病诊断，并描绘疾病进展。
从 ADNI 和 PPMI 获得了一个包含 1316 个 MRI 的多站点、多扫描仪数据集。已识别的生物标志物已被用于破译（1）疾病进展的轨迹，以及（2）识别临床相关的 ROI。此外，我们分别获得了区分 AD 和 PD 与 HC 受试者的分类准确率为 94.29±0.08%和 95.37±0.02%。
这项研究的目标与其他基于机器学习的自动疾病诊断研究从根本上不同。我们的目标是开发一种具有双重优势的方法：（1）它可用于了解神经退行性疾病的病理学，以及（2）它还可实现自动疾病诊断。
在没有既定疾病生物标志物的情况下，临床诊断容易出现误诊。由于具有临床相关性且易于适应当前临床环境，所开发的框架可以成为实现基于机器学习的神经退行性疾病诊断临床决策支持系统（CDSS）的一个起点。
