Disentangling Disease Heterogeneity with Max-Margin Multiple Hyperplane Classifier
There is ample evidence for the heterogeneous nature of diseases. For example, Alzheimer’s Disease, Schizophrenia and Autism Spectrum Disorder are typical disease examples that are characterized by high clinical heterogeneity, and likely by heterogeneity
- PDF / 664,046 Bytes
- 8 Pages / 439.363 x 666.131 pts Page_size
- 67 Downloads / 250 Views
Abstract. There is ample evidence for the heterogeneous nature of diseases. For example, Alzheimer’s Disease, Schizophrenia and Autism Spectrum Disorder are typical disease examples that are characterized by high clinical heterogeneity, and likely by heterogeneity in the underlying brain phenotypes. Parsing this heterogeneity as captured by neuroimaging studies is important both for better understanding of disease mechanisms, and for building subtype-specific classifiers. However, few existing methodologies tackle this problem in a principled machine learning framework. In this work, we developed a novel non-linear learning algorithm for integrated binary classification and subpopulation clustering. Non-linearity is introduced through the use of multiple linear hyperplanes that form a convex polytope that separates healthy controls from pathologic samples. Disease heterogeneity is disentangled by implicitly clustering pathologic samples through their association to single linear sub-classifiers. We show results of the proposed approach from an imaging study of Alzheimer’s Disease, which highlight the potential of the proposed approach to map disease heterogeneity in neuroimaging studies.
1
Introduction
Brain disorders often assume a heterogeneous clinical presentation: Autism Spectrum Disorder (ASD) encompasses neurodevelopmental disorders characterized by deficits in social communication and repetitive behaviors [5]; Schizophrenia can be subdivided into distinct groups by separating its symptomatology to discrete symptom domains [2]; Alzheimer’s Disease (AD) can be separated into three subtypes on the basis of the distribution of neurofibrillary tangles [8]; and Mild Cognitive Impairment (MCI) may be further classified based on the type of specific cognitive impairment [11]. Disentangling disease heterogeneity may greatly contribute to our understanding and lead to more accurate diagnosis, prognosis and targeted treatment. However, most commonly used neuroimaging analysis approaches assume a single unifying pathophysiological process and perform a monistic analysis to identify it. These approaches aim to either identify voxels that characterize group differences through mass-univariate statistical techniques [1], or reveal patterns of c Springer International Publishing Switzerland 2015 N. Navab et al. (Eds.): MICCAI 2015, Part I, LNCS 9349, pp. 702–709, 2015. DOI: 10.1007/978-3-319-24553-9_86
Disentangling Disease Heterogeneity
703
variability through high-dimensional pattern classification analysis, towards categorizing population with respect to the underlying pathology [10]. Thus, the heterogeneity of the disease is completely ignored. Contrarily, few research efforts have been focused on revealing the inherent disease heterogeneity. These methods can mainly be classified into two groups. The first class assumes an a priori subdivision of the diseased samples into coherent groups, based on independent criteria, and opts to identify group-level anatomical differences using univariate statistical methods [7, 12]. Th
Data Loading...
