Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression

Sato, João Ricardo; Moll, Jorge; Green, Sophie M.; Deakin, Bill; Thomaz, Carlos Eduardo; Zahn, Roland

doi:10.1016/j.pscychresns.2015.07.001

Cited by 52 publications

(19 citation statements)

References 15 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, brain representations relevant for performance and clinical outcomes may often be distributed across multiple regions and networks. If so, models that integrate contributions from different brain areas will likely be required for accurate prediction 24,58,135 .…”

Section: Future Directions: Toward a Next Generation Of Translationalmentioning

confidence: 99%

Building better biomarkers: brain models in translational neuroimaging

et al. 2017

View full text Add to dashboard Cite

Despite its great promise, neuroimaging has yet to substantially impact clinical practice and public health. However, a developing synergy between emerging analysis techniques and data-sharing initiatives has the potential to transform the role of neuroimaging in clinical applications. We review the state of translational neuroimaging and outline an approach to developing brain signatures that can be shared, tested in multiple contexts and applied in clinical settings. The approach rests on three pillars: (i) the use of multivariate pattern-recognition techniques to develop brain signatures for clinical outcomes and relevant mental processes; (ii) assessment and optimization of their diagnostic value; and (iii) a program of broad exploration followed by increasingly rigorous assessment of generalizability across samples, research contexts and populations. Increasingly sophisticated models based on these principles will help to overcome some of the obstacles on the road from basic neuroscience to better health and will ultimately serve both basic and applied goals.

show abstract

Section: Future Directions: Toward a Next Generation Of Translationalmentioning

confidence: 99%

Building better biomarkers: brain models in translational neuroimaging

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Researchers have discovered disruptions of FCN in neuropsychiatric diseases, such as Alzheimer's disease (Greicius, Srivastava, Reiss, & Menon, ; Wang et al, ), mild cognitive impair (MCI) (Bai et al, ; Das et al, ), depression (Greicius et al, ; Yang et al, ), autism spectrum disorder (ASD) (Anderson et al, ; Assaf et al, ; Cheng, Rolls, Gu, Zhang, & Feng, ; Ebisch et al, ), and schizophrenia (Wang, Xia, et al, ). On the other hand, machine learning techniques have been proven to be very effective in identifying biomarkers for brain disease diagnosis based on FCN (Chen, Zhang, et al, ; Jiang, Zhang, & Zhu, ; Khazaee, Ebrahimzadeh & Babajani‐Feremi, ; Sato et al, ; Wee, Yap, Zhang, Wang, & Shen, ; Zhang, Hu, Ma, & Xu, ). Here, we focus on exploring biomarkers from FCN for ASD diagnosis using state‐of‐the‐art machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Enhancing the representation of functional connectivity networks by fusing multi‐view information for autism spectrum disorder diagnosis

Huang

Liu

Jin

et al. 2018

Human Brain Mapping

View full text Add to dashboard Cite

Functional connectivity network provides novel insights on how distributed brain regions are functionally integrated, and its deviations from healthy brain have recently been employed to identify biomarkers for neuropsychiatric disorders. However, most of brain network analysis methods utilized features extracted only from one functional connectivity network for brain disease detection and cannot provide a comprehensive representation on the subtle disruptions of brain functional organization induced by neuropsychiatric disorders. Inspired by the principles of multi‐view learning which utilizes information from multiple views to enhance object representation, we propose a novel multiple network based framework to enhance the representation of functional connectivity networks by fusing the common and complementary information conveyed in multiple networks. Specifically, four functional connectivity networks corresponding to the four adjacent values of regularization parameter are generated via a sparse regression model with group constraint ( l2,1‐norm), to enhance the common intrinsic topological structure and limit the error rate caused by different views. To obtain a set of more meaningful and discriminative features, we propose using a modified version of weighted clustering coefficients to quantify the subtle differences of each group‐sparse network at local level. We then linearly fuse the selected features from each individual network via a multi‐kernel support vector machine for autism spectrum disorder (ASD) diagnosis. The proposed framework achieves an accuracy of 79.35%, outperforming all the compared single network methods for at least 7% improvement. Moreover, compared with other multiple network methods, our method also achieves the best performance, that is, with at least 11% improvement in accuracy.

show abstract

“…Current studies are often limited by focus on single biomarkers or other predictors as a basis for intervention allocation. However, we need more advanced statistical modeling techniques, such as machine learning (Sato et al, 2015 ), and should aim to translate identified disease mechanisms into molecular blood-based biomarker combinations (e.g., Chan et al, 2014 ) to combine different biological variables to predict disorder vulnerability and treatment responses. At the same time, the need for innovative pilot studies in single centers to develop and test novel hypotheses remains.…”

Section: Methodological Challenges and Directionsmentioning

confidence: 99%

Investigating biological traces of traumatic stress in changing societies: challenges and directions from the ESTSS Task Force on Neurobiology

Thomaes

Kloet

Wilker

et al. 2016

European Journal of Psychotraumatology

View full text Add to dashboard Cite

Traumatic stress can have severe consequences for both mental and physical health. Furthermore, both psychological and biological traces of trauma increase as a function of accumulating traumatic experiences. Neurobiological research may aid in limiting the impact of traumatic stress, by leading to advances in preventive and treatment interventions. To promote the possibility for clinical implementation of novel research findings, this brief review describes timely conceptual and methodological challenges and directions in neurobiological trauma research on behalf of the Task Force “Neurobiology of Traumatic Stress” of the European Society for Traumatic Stress Studies (ESTSS). The most important conceptual challenges are the heterogeneity of disorders and existence of subtypes across diagnostic categories: differential latent profiles and trajectories regarding symptom expression and neural correlates are being unraveled; however, similar latent classes’ approaches for treatment response and neurobiological data remain scarce thus far. The key to improving the efficacy of currently available preventive interventions and treatments for trauma-related disorders lies in a better understanding and characterization of individual differences in response to trauma and interventions. This could lead to personalized treatment strategies for trauma-related disorders, based on objective information indicating whether individuals are expected to benefit from them. The most important methodological challenge identified here is the need for large consortia and meta-analyses or, rather, mega-analyses on existent data as a first step. In addition, large multicenter studies, combining novel methods for repeated sampling with more advanced statistical modeling techniques, such as machine learning, should aim to translate identified disease mechanisms into molecular blood-based biomarker combinations to predict disorder vulnerability and treatment responses.

show abstract

Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression

Cited by 52 publications

References 15 publications

Building better biomarkers: brain models in translational neuroimaging

Building better biomarkers: brain models in translational neuroimaging

Enhancing the representation of functional connectivity networks by fusing multi‐view information for autism spectrum disorder diagnosis

Investigating biological traces of traumatic stress in changing societies: challenges and directions from the ESTSS Task Force on Neurobiology

Contact Info

Product

Resources

About