Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

OBJECTIVE: Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features. METHODS: Late-life depression patients (medicated post-recruitment) (n = 33) and older non-depressed individuals (n = 35) were recruited. Their demographics and cognitive ability scores were recorded, and brain characteristics were acquired using multi-modal magnetic resonance imaging pretreatment. Linear and nonlinear learning methods were tested for estimating accurate prediction models. RESULTS: A learning method called alternating decision trees estimated the most accurate prediction models for late-life depression diagnosis (87.27% accuracy) and treatment response (89.47% accuracy). The diagnosis model included measures of age, Mini-mental state examination score, and structural imaging (e.g. whole brain atrophy and global white mater hyperintensity burden). The treatment response model included measures of structural and functional connectivity. CONCLUSIONS: Combinations of multi-modal imaging and/or non-imaging measures may help better predict late-life depression diagnosis and treatment response. As a preliminary observation, we speculate that the results may also suggest that different underlying brain characteristics defined by multi-modal imaging measures-rather than region-based differences-are associated with depression versus depression recovery because to our knowledge this is the first depression study to accurately predict both using the same approach. These findings may help better understand late-life depression and identify preliminary steps toward personalized late-life depression treatment.

Studying depression using imaging and machine learning methods.

Depression is a complex clinical entity that can pose challenges for clinicians regarding both accurate diagnosis and effective timely treatment. These challenges have prompted the development of multiple machine learning methods to help improve the management of this disease. These methods utilize anatomical and physiological data acquired from neuroimaging to create models that can identify depressed patients vs. non-depressed patients and predict treatment outcomes. This article (1) presents a background on depression, imaging, and machine learning methodologies; (2) reviews methodologies of past studies that have used imaging and machine learning to study depression; and (3) suggests directions for future depression-related studies.

Association of small vessel ischemic white matter changes with BOLD fMRI imaging in the elderly.

White matter hyperintensities (WMHs) are often identified on T2-weighted magnetic resonance (MR) images in the elderly. The WMHs are generally associated with small vessel ischemic or pre-ischemic changes. However, the association of WMHs with blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI) signal is understudied. In this study, we evaluate how the BOLD signal change is related to the presence of WMHs in the elderly. Data were acquired as part of a study of late-life depression and included elderly individuals with and without major depression. The subjects were pooled because the presence of depression was not significantly associated with task-related BOLD changes, task performance, and WMH distribution. A whole brain voxel-wise regression analysis revealed a significant negative correlation between WMH burden and BOLD signal change during finger-tapping in the parietal white matter. Our observation that WMHs are associated with a significant diminution of the BOLD signal change underscores the importance of considering cerebrovascular burden when interpreting fMRI studies in the elderly. The mechanism underlying the association of WMH and BOLD signal change remains unclear: the association may be mediated by changes in neural activation, changes in coupling between neuronal activity and hemodynamics, or, perhaps, secondary to the effect of the ischemic changes on the sensitivity of the T2* BOLD MR signal.