scholarly journals Large-scale Gradient Dysfunction of the Functional Connectome in Major Depression

2020 ◽  
Author(s):  
Mingrui Xia ◽  
Jin Liu ◽  
Xiaoyi Sun ◽  
Qing Ma ◽  
Xiaoqin Wang ◽  
...  
Keyword(s):  
Gene Expression ◽  
Cognitive Processing ◽  
Sensory Processing ◽  
Large Scale ◽  
Support Vector ◽  
Ion Binding ◽  
Healthy Controls ◽  
Learning Approaches ◽  
Imaging Data ◽  
Shed Light

AbstractMajor depressive disorder (MDD) is associated with coexisting disturbances in low-level sensory processing and high-order cognitive functions. However, the neurobiological mechanism underlying these phenotype deficits remains poorly understood. Here, we collect large-sample, multisite resting-state functional magnetic resonance imaging data (1,150 patients with MDD and 1,084 healthy controls) and postmortem gene expression data. We show downgraded and contracted connectome gradients that are mainly involved in primary sensory and transmodal regions in patients with MDD relative to healthy controls, leveraging an association with gene expression enriched in transsynaptic signaling and calcium ion binding. Machine learning approaches based on support vector regression suggest that the alterations of connectome gradients in patients significantly predict depressive symptoms. These results shed light on gradient dysfunction of the large-scale functional connectomes in MDD and consolidate the spectrum deficits of sensory and cognitive processing in this disorder.

Discriminative Analysis of Symptom Severity and Ultra-High Risk of Schizophrenia Using Intrinsic Functional Connectivity

2020 ◽  
Vol 30 (09) ◽  
pp. 2050047
Author(s):  
Lubin Wang ◽  
Xianbin Li ◽  
Yuyang Zhu ◽  
Bei Lin ◽  
Qijing Bo ◽  
...  
Keyword(s):  
High Risk ◽  
Functional Connectivity ◽  
Symptom Severity ◽  
Large Scale ◽  
Brain Networks ◽  
Brain Regions ◽  
Support Vector ◽  
Healthy Controls ◽  
Intrinsic Functional Connectivity ◽  
Ultra High Risk

Past studies have consistently shown functional dysconnectivity of large-scale brain networks in schizophrenia. In this study, we aimed to further assess whether multivariate pattern analysis (MVPA) could yield a sensitive predictor of patient symptoms, as well as identify ultra-high risk (UHR) stage of schizophrenia from intrinsic functional connectivity of whole-brain networks. We first combined rank-based feature selection and support vector machine methods to distinguish between 43 schizophrenia patients and 52 healthy controls. The constructed classifier was then applied to examine functional connectivity profiles of 18 UHR individuals. The classifier indicated reliable relationship between MVPA measures and symptom severity, with higher classification accuracy in more severely affected schizophrenia patients. The UHR subjects had classification scores falling between those of healthy controls and patients, suggesting an intermediate level of functional brain abnormalities. Moreover, UHR individuals with schizophrenia-like connectivity profiles at baseline presented higher rate of conversion to full-blown illness in the follow-up visits. Spatial maps of discriminative brain regions implicated increases of functional connectivity in the default mode network, whereas decreases of functional connectivity in the cerebellum, thalamus and visual areas in schizophrenia. The findings may have potential utility in the early diagnosis and intervention of schizophrenia.

scholarly journals Individualized prediction of illness course at the first psychotic episode: a support vector machine MRI study

2011 ◽  
Vol 42 (5) ◽  
pp. 1037-1047 ◽  
Author(s):  
J. Mourao-Miranda ◽  
A. A. T. S. Reinders ◽  
V. Rocha-Rego ◽  
J. Lappin ◽  
J. Rondina ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Support Vector ◽  
Psychotic Episode ◽  
Svm Classifier ◽  
Healthy Controls ◽  
Imaging Data ◽  
Healthy Individuals ◽  
First Psychotic Episode ◽  
Episodic Course ◽  
Individualized Prediction

BackgroundTo date, magnetic resonance imaging (MRI) has made little impact on the diagnosis and monitoring of psychoses in individual patients. In this study, we used a support vector machine (SVM) whole-brain classification approach to predict future illness course at the individual level from MRI data obtained at the first psychotic episode.MethodOne hundred patients at their first psychotic episode and 91 healthy controls had an MRI scan. Patients were re-evaluated 6.2 years (s.d.=2.3) later, and were classified as having a continuous, episodic or intermediate illness course. Twenty-eight subjects with a continuous course were compared with 28 patients with an episodic course and with 28 healthy controls. We trained each SVM classifier independently for the following contrasts: continuous versus episodic, continuous versus healthy controls, and episodic versus healthy controls.ResultsAt baseline, patients with a continuous course were already distinguishable, with significance above chance level, from both patients with an episodic course (p=0.004, sensitivity=71, specificity=68) and healthy individuals (p=0.01, sensitivity=71, specificity=61). Patients with an episodic course could not be distinguished from healthy individuals. When patients with an intermediate outcome were classified according to the discriminating pattern episodic versus continuous, 74% of those who did not develop other episodes were classified as episodic, and 65% of those who did develop further episodes were classified as continuous (p=0.035).ConclusionsWe provide preliminary evidence of MRI application in the individualized prediction of future illness course, using a simple and automated SVM pipeline. When replicated and validated in larger groups, this could enable targeted clinical decisions based on imaging data.

scholarly journals An Exotic IWD - SVR Based Approach for Failure Prognostication in Cloud-Based Scientific Workflows

2021 ◽  
Author(s):  
Sridevi S ◽  
Jeevaa Katiravan Jeevaa Katiravan
Keyword(s):  
Large Scale ◽  
Performance Metrics ◽  
Prediction Models ◽  
Fault Tolerant ◽  
Scientific Workflow ◽  
Scientific Workflows ◽  
Support Vector ◽  
Learning Approaches ◽  
Task Failure ◽  
Proactive Measures

Abstract Scientific workflows deserve the emerging attention in sophisticated large-scale scientific problem-solving environments. Though a single task failure occurs in workflow based applications, due to its task dependency nature the reliability of the overall system will be affected drastically. Hence rather than reactive fault tolerant approaches, proactive measures are vital in scientific workflows. This work puts forth an attempt to concentrate on the exploration issue of structuring an Exotic Intelligent Water Drops - Support Vector Regression-based approach for task failure prognostication which facilitates proactive fault tolerance in scientific workflow applications. The failure prediction models in this study have been implemented through SVR-based machine learning approaches and its precision accuracy is optimized by IWDA and various performance metrics were evaluated. The experimental results prove that the proposed approach performs better compared with the other existing techniques.

scholarly journals Gene expression based inference of drug resistance in cancer

2021 ◽  
Author(s):  
Smriti Chawla ◽  
Anja Rockstroh ◽  
Melanie Lehman ◽  
Ellca Rather ◽  
Atishay Jain ◽  
...  
Keyword(s):  
Gene Expression ◽  
Drug Resistance ◽  
Cell Lines ◽  
Large Scale ◽  
Activity Patterns ◽  
The Cancer Genome Atlas ◽  
Learning Approaches ◽  
Expression Data ◽  
Sequencing Data ◽  
Pathway Activity

Inter and intra-tumoral heterogeneity are major stumbling blocks in the treatment of cancer and are responsible for imparting differential drug responses in cancer patients. Recently, the availability of large-scale drug screening datasets has provided an opportunity for predicting appropriate patient-tailored therapies by employing machine learning approaches. In this study, we report a predictive modeling approach to infer treatment response in cancers using gene expression data. In particular, we demonstrate the benefits of considering integrated chemogenomics approach, utilizing the molecular drug descriptors and pathway activity information as opposed to gene expression levels. We performed extensive validation of our approach on tissue-derived single-cell and bulk expression data. Further, we constructed several prostate cancer cell lines and xenografts, exposed to differential treatment conditions to assess the predictability of the outcomes. Our approach was further assessed on pan-cancer RNA-sequencing data from The Cancer Genome Atlas (TCGA) archives, as well as an independent clinical trial study describing the treatment journey of three melanoma patients. To summarise, we benchmarked the proposed approach on cancer RNA-seq data, obtained from cell lines, xenografts, as well as humans. We concluded that pathway-activity patterns in cancer cells are reasonably indicative of drug resistance, and therefore can be leveraged in personalized treatment recommendations.

scholarly journals Increased Homotopic Connectivity in the Prefrontal Cortex Modulated by Olanzapine Predicts Therapeutic Efficacy in Patients with Schizophrenia

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xiaoxiao Shan ◽  
Rongyuan Liao ◽  
Yangpan Ou ◽  
Yudan Ding ◽  
Feng Liu ◽  
...  
Keyword(s):  
Prefrontal Cortex ◽  
Support Vector ◽  
Individual Treatment ◽  
Antipsychotic Treatment ◽  
Individual Response ◽  
Healthy Controls ◽  
Imaging Data ◽  
Antipsychotic Therapy ◽  
Olanzapine Treatment ◽  
Schizophrenic Patients

Background. Previous studies have revealed the abnormalities in homotopic connectivity in schizophrenia. However, the relationship of these deficits to antipsychotic treatment in schizophrenia remains unclear. This study explored the effects of antipsychotic therapy on brain homotopic connectivity and whether the homotopic connectivity of these regions might predict individual treatment response in schizophrenic patients. Methods. A total of 21 schizophrenic patients and 20 healthy controls were scanned by the resting-state functional magnetic resonance imaging. The patients received olanzapine treatment and were scanned at two time points. Voxel-mirrored homotopic connectivity (VMHC) and pattern classification techniques were applied to analyze the imaging data. Results. Schizophrenic patients presented significantly decreased VMHC in the temporal and inferior frontal gyri, medial prefrontal cortex (MPFC), and motor and low-level sensory processing regions (including the fusiform gyrus and cerebellum lobule VI) relative to healthy controls. The VMHC in the superior/middle MPFC was significantly increased in the patients after eight weeks of treatment. Support vector regression (SVR) analyses revealed that VMHC in the superior/middle MPFC at baseline can predict the symptomatic improvement of the positive and negative syndrome scale after eight weeks of treatment. Conclusions. This study demonstrated that olanzapine treatment may normalize decreased homotopic connectivity in the superior/middle MPFC in schizophrenic patients. The VMHC in the superior/middle MPFC may predict individual response for antipsychotic therapy. The findings of this study conduce to the comprehension of the therapy effects of antipsychotic medications on homotopic connectivity in schizophrenia.

Machine Learning Approach to Differentiation of Peripheral Schwannomas and Neurofibromas: A Multi-Center Study

2021 ◽  
Author(s):  
Michael Zhang ◽  
Elizabeth Tong ◽  
Sam Wong ◽  
Forrest Hamrick ◽  
Maryam Mohammadzadeh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Clinical Features ◽  
Nearest Neighbor ◽  
Motor Deficit ◽  
Support Vector ◽  
Spontaneous Pain ◽  
Learning Approaches ◽  
Imaging Data ◽  
K Nearest Neighbor

Abstract Background Non-invasive differentiation between schwannomas and neurofibromas is important for appropriate management, preoperative counseling, and surgical planning, but has proven difficult using conventional imaging. The objective of this study was to develop and evaluate machine learning approaches for differentiating peripheral schwannomas from neurofibromas. Methods We assembled a cohort of schwannomas and neurofibromas from 3 independent institutions and extracted high-dimensional radiomic features from gadolinium-enhanced, T1-weighted MRI using the PyRadiomics package on Quantitative Imaging Feature Pipeline. Age, sex, neurogenetic syndrome, spontaneous pain, and motor deficit were recorded. We evaluated the performance of 6 radiomics-based classifier models with and without clinical features and compared model performance against human expert evaluators. Results 107 schwannomas and 59 neurofibroma were included. The primary models included both clinical and imaging data. The accuracy of the human evaluators (0.765) did not significantly exceed the no-information rate (NIR), whereas the Support Vector Machine (0.929), Logistic Regression (0.929), and Random Forest (0.905) classifiers exceeded the NIR. Using the method of DeLong, the AUC for the Logistic Regression (AUC=0.923) and K Nearest Neighbor (AUC=0.923) classifiers was significantly greater than the human evaluators (AUC=0.766; p = 0.041). Conclusions The radiomics-based classifiers developed here proved to be more accurate and had a higher AUC on the ROC curve than expert human evaluators. This demonstrates that radiomics using routine MRI sequences and clinical features can aid in differentiation of peripheral schwannomas and neurofibromas.

scholarly journals Tree Kernels for Semantic Role Labeling

2008 ◽  
Vol 34 (2) ◽  
pp. 193-224 ◽  
Author(s):  
Alessandro Moschitti ◽  
Daniele Pighin ◽  
Roberto Basili
Keyword(s):  
Language Processing ◽  
Large Scale ◽  
Kernel Functions ◽  
Feature Representation ◽  
Training Data ◽  
Support Vector ◽  
Feature Engineering ◽  
Semantic Role ◽  
Learning Approaches ◽  
Semantic Role Labeling

The availability of large scale data sets of manually annotated predicate-argument structures has recently favored the use of machine learning approaches to the design of automated semantic role labeling (SRL) systems. The main research in this area relates to the design choices for feature representation and for effective decompositions of the task in different learning models. Regarding the former choice, structural properties of full syntactic parses are largely employed as they represent ways to encode different principles suggested by the linking theory between syntax and semantics. The latter choice relates to several learning schemes over global views of the parses. For example, re-ranking stages operating over alternative predicate-argument sequences of the same sentence have shown to be very effective. In this article, we propose several kernel functions to model parse tree properties in kernel-based machines, for example, perceptrons or support vector machines. In particular, we define different kinds of tree kernels as general approaches to feature engineering in SRL. Moreover, we extensively experiment with such kernels to investigate their contribution to individual stages of an SRL architecture both in isolation and in combination with other traditional manually coded features. The results for boundary recognition, classification, and re-ranking stages provide systematic evidence about the significant impact of tree kernels on the overall accuracy, especially when the amount of training data is small. As a conclusive result, tree kernels allow for a general and easily portable feature engineering method which is applicable to a large family of natural language processing tasks.

Failed cooperative, but not competitive, interaction between large-scale brain networks impairs working memory in schizophrenia

2016 ◽  
Vol 46 (6) ◽  
pp. 1211-1224 ◽  
Author(s):  
W. Pu ◽  
Q. Luo ◽  
L. Palaniyappan ◽  
Z. Xue ◽  
S. Yao ◽  
...  
Keyword(s):  
Working Memory ◽  
Granger Causality ◽  
Large Scale ◽  
Dynamic Interaction ◽  
Healthy Controls ◽  
Causality Analysis ◽  
Imaging Data ◽  
Planar Imaging ◽  
Attentional Deficit ◽  
Attention Disorder

BackgroundA large-scale network named the default mode network (DMN) dynamically cooperates and competes with an external attention system (EAS) to facilitate various cognitive functioning that is prominently impaired in schizophrenia. However, it is unclear whether the cognitive deficit in schizophrenia is related to the disrupted competition and/or cooperation between these two networks.MethodA total of 35 schizophrenia patients and 30 healthy controls were scanned using gradient-echo echo-planar imaging during n-back working memory (WM) processing. Brain activities of the DMN and EAS were measured using general linear modelling of the functional magnetic resonance imaging data. Dynamic interaction between the DMN and EAS was decomposed into two directions using Granger causality analysis.ResultsWe observed a significant failure of DMN suppression in patients with schizophrenia, which was significantly related to WM/attentional deficit. Granger causality modelling showed that in healthy controls, while the EAS inhibitorily influenced the DMN, the DMN exerted an ‘excitatory’ or cooperative influence back on the EAS, especially in those with lower WM accuracy. In schizophrenia, this ‘excitatory’ DMN→EAS influence within the reciprocal EAS–DMN loop was significantly reduced, especially in patients with WM/attentional deficit.ConclusionsThe dynamic interaction between the DMN and EAS is likely to be comprised of both competitive and cooperative influences. In healthy controls, both the ‘inhibitory’ EAS→DMN interaction and ‘excitatory’ DMN→EAS interaction are correlated with WM performance. In schizophrenia, reduced ‘cooperative’ influence from the DMN to dorsal nodes of the EAS occurs in the context of non-suppression of the DMN and may form a possible pathophysiological substrate of WM deficit and attention disorder.

scholarly journals PIC-Me: paralogs and isoforms classifier based on machine-learning approaches

2021 ◽  
Vol 22 (S11) ◽  
Author(s):  
Jooseong Oh ◽  
Sung-Gwon Lee ◽  
Chungoo Park
Keyword(s):  
Machine Learning ◽  
Large Scale ◽  
Gene Annotation ◽  
Sequence Similarity ◽  
Global Analysis ◽  
Model Organism ◽  
Model Organisms ◽  
Support Vector ◽  
Learning Approaches ◽  
Rna Seq

Abstract Background Paralogs formed through gene duplication and isoforms formed through alternative splicing have been important processes for increasing protein diversity and maintaining cellular homeostasis. Despite their recognized importance and the advent of large-scale genomic and transcriptomic analyses, paradoxically, accurate annotations of all gene loci to allow the identification of paralogs and isoforms remain surprisingly incomplete. In particular, the global analysis of the transcriptome of a non-model organism for which there is no reference genome is especially challenging. Results To reliably discriminate between the paralogs and isoforms in RNA-seq data, we redefined the pre-existing sequence features (sequence similarity, inverse count of consecutive identical or non-identical blocks, and match-mismatch fraction) previously derived from full-length cDNAs and EST sequences and described newly discovered genomic and transcriptomic features (twilight zone of protein sequence alignment and expression level difference). In addition, the effectiveness and relevance of the proposed features were verified with two widely used support vector machine (SVM) and random forest (RF) models. From nine RNA-seq datasets, all AUC (area under the curve) scores of ROC (receiver operating characteristic) curves were over 0.9 in the RF model and significantly higher than those in the SVM model. Conclusions In this study, using an RF model with five proposed RNA-seq features, we implemented our method called Paralogs and Isoforms Classifier based on Machine-learning approaches (PIC-Me) and showed that it outperformed an existing method. Finally, we envision that our tool will be a valuable computational resource for the genomics community to help with gene annotation and will aid in comparative transcriptomics and evolutionary genomics studies, especially those on non-model organisms.

scholarly journals Machine Learning Approaches: From Theory to Application in Schizophrenia

2013 ◽  
Vol 2013 ◽  
pp. 1-12 ◽  
Author(s):  
Elisa Veronese ◽  
Umberto Castellani ◽  
Denis Peruzzo ◽  
Marcella Bellani ◽  
Paolo Brambilla
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Support Vector Machine ◽  
Clinical Practice ◽  
Disease Diagnosis ◽  
Support Vector ◽  
Healthy Controls ◽  
Learning Approaches ◽  
Neuroimaging Data ◽  
Comparison Of The Results

In recent years, machine learning approaches have been successfully applied for analysis of neuroimaging data, to help in the context of disease diagnosis. We provide, in this paper, an overview of recent support vector machine-based methods developed and applied in psychiatric neuroimaging for the investigation of schizophrenia. In particular, we focus on the algorithms implemented by our group, which have been applied to classify subjects affected by schizophrenia and healthy controls, comparing them in terms of accuracy results with other recently published studies. First we give a description of the basic terminology used in pattern recognition and machine learning. Then we separately summarize and explain each study, highlighting the main features that characterize each method. Finally, as an outcome of the comparison of the results obtained applying the described different techniques, conclusions are drawn in order to understand how much automatic classification approaches can be considered a useful tool in understanding the biological underpinnings of schizophrenia. We then conclude by discussing the main implications achievable by the application of these methods into clinical practice.

Sign in / Sign up

Export Citation Format

Share Document