Young Alexandra L, Vogel Jacob W, Aksman Leon M, Wijeratne Peter A, Eshaghi Arman, Oxtoby Neil P, Williams Steven C R, Alexander Daniel C
Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, United Kingdom.
Centre for Medical Image Computing, University College London, London, United Kingdom.
Front Artif Intell. 2021 Aug 12;4:613261. doi: 10.3389/frai.2021.613261. eCollection 2021.
Subtype and Stage Inference (SuStaIn) is an unsupervised learning algorithm that uniquely enables the identification of subgroups of individuals with distinct pseudo-temporal disease progression patterns from cross-sectional datasets. SuStaIn has been used to identify data-driven subgroups and perform patient stratification in neurodegenerative diseases and in lung diseases from continuous biomarker measurements predominantly obtained from imaging. However, the SuStaIn algorithm is not currently applicable to discrete ordinal data, such as visual ratings of images, neuropathological ratings, and clinical and neuropsychological test scores, restricting the applicability of SuStaIn to a narrower range of settings. Here we propose 'Ordinal SuStaIn', an ordinal version of the SuStaIn algorithm that uses a scored events model of disease progression to enable the application of SuStaIn to ordinal data. We demonstrate the validity of Ordinal SuStaIn by benchmarking the performance of the algorithm on simulated data. We further demonstrate that Ordinal SuStaIn out-performs the existing continuous version of SuStaIn (Z-score SuStaIn) on discrete scored data, providing much more accurate subtype progression patterns, better subtyping and staging of individuals, and accurate uncertainty estimates. We then apply Ordinal SuStaIn to six different sub-scales of the Clinical Dementia Rating scale (CDR) using data from the Alzheimer's disease Neuroimaging Initiative (ADNI) study to identify individuals with distinct patterns of functional decline. Using data from 819 ADNI1 participants we identified three distinct CDR subtype progression patterns, which were independently verified using data from 790 ADNI2 participants. Our results provide insight into patterns of decline in daily activities in Alzheimer's disease and a mechanism for stratifying individuals into groups with difficulties in different domains. Ordinal SuStaIn is broadly applicable across different types of ratings data, including visual ratings from imaging, neuropathological ratings and clinical or behavioural ratings data.
亚型和阶段推断（SuStaIn）是一种无监督学习算法，它能够从横断面数据集中唯一地识别出具有不同伪时间疾病进展模式的个体亚组。SuStaIn已被用于从主要通过成像获得的连续生物标志物测量中识别数据驱动的亚组，并在神经退行性疾病和肺部疾病中进行患者分层。然而，SuStaIn算法目前不适用于离散有序数据，如图像的视觉评分、神经病理学评分以及临床和神经心理学测试分数，这限制了SuStaIn在更窄范围内的适用性。在此，我们提出“有序SuStaIn”，这是SuStaIn算法的有序版本，它使用疾病进展的计分事件模型，使SuStaIn能够应用于有序数据。我们通过在模拟数据上对算法性能进行基准测试，证明了有序SuStaIn的有效性。我们进一步证明，在离散计分数据上，有序SuStaIn优于现有的连续版本的SuStaIn（Z分数SuStaIn），能提供更准确的亚型进展模式、更好的个体亚型划分和分期，以及准确的不确定性估计。然后，我们使用来自阿尔茨海默病神经影像倡议（ADNI）研究的数据，将有序SuStaIn应用于临床痴呆评定量表（CDR）的六个不同子量表，以识别功能衰退模式不同的个体。利用来自819名ADNI1参与者的数据，我们识别出三种不同的CDR亚型进展模式，并使用来自790名ADNI2参与者的数据进行了独立验证。我们的结果为阿尔茨海默病日常活动衰退模式提供了见解，并为将个体分层为不同领域有困难的群体提供了一种机制。有序SuStaIn广泛适用于不同类型的评分数据，包括来自成像的视觉评分、神经病理学评分以及临床或行为评分数据。
