Centre for Medical Image Computing, University College London, Gower Street, WC1E 6BT, London, UK.
Neuroimage. 2012 Apr 15;60(3):1880-9. doi: 10.1016/j.neuroimage.2012.01.062. Epub 2012 Jan 16.
Understanding the progression of neurological diseases is vital for accurate and early diagnosis and treatment planning. We introduce a new characterization of disease progression, which describes the disease as a series of events, each comprising a significant change in patient state. We provide novel algorithms to learn the event ordering from heterogeneous measurements over a whole patient cohort and demonstrate using combined imaging and clinical data from familial Alzheimer's and Huntington's disease cohorts. Results provide new detail in the progression pattern of these diseases, while confirming known features, and give unique insight into the variability of progression over the cohort. The key advantage of the new model and algorithms over previous progression models is that they do not require a priori division of the patients into clinical stages. The model and its formulation extend naturally to a wide range of other diseases and developmental processes and accommodate cross-sectional and longitudinal input data.
了解神经退行性疾病的进展对于准确和早期的诊断和治疗计划至关重要。我们引入了一种新的疾病进展描述方法，将疾病描述为一系列事件，每个事件都包含患者状态的重大变化。我们提供了新的算法，从整个患者队列的异质测量中学习事件排序，并使用来自家族性阿尔茨海默病和亨廷顿病队列的组合成像和临床数据进行了演示。结果为这些疾病的进展模式提供了新的细节，同时确认了已知特征，并深入了解了队列中进展的可变性。与以前的进展模型相比，新模型和算法的主要优势在于它们不需要预先将患者分为临床阶段。该模型及其公式自然适用于广泛的其他疾病和发育过程，并适应横断面和纵向输入数据。
