Multivariate classification of smokers and nonsmokers using SVM-RFE on structural MRI images

Distinguishing schizophrenia and bipolar disorder through a Multiclass Classification model based on multimodal neuroimaging data

This study aimed to identify neural biomarkers for schizophrenia (SZ) and bipolar disorder (BP) by analyzing multimodal neuroimaging. Utilizing data from structural magnetic resonance imaging (sMRI), diffusion tensor imaging (DTI), and resting-state functional magnetic resonance imaging (rs-fMRI), multiclass classification models were created for SZ, BP, and healthy controls (HC). A total of 113 participants (BP: 31, SZ: 39, and HC: 43) were recruited under strict enrollment control, from which 272, 200, and 1875 features were extracted from sMRI, DTI, and rs-fMRI data, respectively. A support vector machine (SVM) with recursive feature elimination (RFE) was employed to build the models using a one-against-one approach and leave-one-out cross-validation, achieving a classification accuracy of 70.8%. The most discriminative features were primarily from rs-fMRI, along with significant findings in sMRI and DTI. Key biomarkers identified included the increased thickness of the left cuneus cortex and decreased regional functional connectivity strength (rFCS) in the left supramarginal gyrus as shared indicators for BP and SZ. Additionally, decreased fractional anisotropy in the left superior fronto-occipital fasciculus was suggested as specific to BP, while decreased rFCS in the left inferior parietal area might serve as a specific biomarker for SZ. These findings underscore the potential of multimodal neuroimaging in distinguishing between BP and SZ and contribute to the understanding of their neural underpinnings.

Maximum margin and global criterion based-recursive feature selection

In this research paper, we aim to investigate and address the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. We identify two main challenges associated with these methods. Firstly, the feature ranking criterion utilized in these approaches is inconsistent with the maximum-margin theory. Secondly, the computation of the criterion is performed locally, lacking the ability to measure the importance of features globally. To overcome these challenges, we propose a novel feature ranking criterion called Maximum Margin and Global (MMG) criterion. This criterion utilizes the classification margin to determine the importance of features and computes it globally, enabling a more accurate assessment of feature importance. Moreover, we introduce an optimal feature subset evaluation algorithm that leverages the MMG criterion to determine the best subset of features. To enhance the efficiency of the proposed algorithms, we provide two alpha seeding strategies that significantly reduce computational costs while maintaining high accuracy. These strategies offer a practical means to expedite the feature selection process. Through extensive experiments conducted on ten benchmark datasets, we demonstrate that our proposed algorithms outperform current state-of-the-art methods. Additionally, the alpha seeding strategies yield significant speedups, further enhancing the efficiency of the feature selection process.

Perspective of artificial intelligence in healthcare data management: A journey towards precision medicine

Mounting evidence has highlighted the implementation of big data handling and management in the healthcare industry to improve the clinical services. Various private and public companies have generated, stored, and analyzed different types of big healthcare data, such as omics data, clinical data, electronic health records, personal health records, and sensing data with the aim to move in the direction of precision medicine. Additionally, with the advancement in technologies, researchers are curious to extract the potential involvement of artificial intelligence and machine learning on big healthcare data to enhance the quality of patient's lives. However, seeking solutions from big healthcare data requires proper management, storage, and analysis, which imposes hinderances associated with big data handling. Herein, we briefly discuss the implication of big data handling and the role of artificial intelligence in precision medicine. Further, we also highlighted the potential of artificial intelligence in integrating and analyzing the big data that offer personalized treatment. In addition, we briefly discuss the applications of artificial intelligence in personalized treatment, especially in neurological diseases. Lastly, we discuss the challenges and limitations imposed by artificial intelligence in big data management and analysis to hinder precision medicine.

Distinguishing Patients with MRI-Negative Temporal Lobe Epilepsy from Normal Controls Based on Individual Morphological Brain Network

Temporal Lobe Epilepsy (TLE) is the most common subtype of focal epilepsy and the most refractory to drug treatment. Roughly 30% of patients do not have easily identifiable structural abnormalities. In other words, MRI-negative TLE has normal MRI scans on visual inspection. Thus, MRI-negative TLE is a diagnostic and therapeutic challenge. In this study, we investigate the cortical morphological brain network to identify MRI-negative TLE. The 210 cortical ROIs based on the Brainnetome atlas were used to define the network nodes. The least absolute shrinkage and selection operator (LASSO) algorithm and Pearson correlation methods were used to calculate the inter-regional morphometric features vector correlation respectively. As a result, two types of networks were constructed. The topological characteristics of networks were calculated by graph theory. Then after, a two-stage feature selection strategy, including a two-sample t-test and support vector machine-based recursive feature elimination (SVM-RFE), was performed in feature selection. Finally, classification with support vector machine (SVM) and leave-one-out cross-validation (LOOCV) was employed for the training and evaluation of the classifiers. The performance of two constructed brain networks was compared in MRI-negative TLE classification. The results indicated that the LASSO algorithm achieved better performance than the Pearson pairwise correlation method. The LASSO algorithm provides a robust method of individual morphological network construction for distinguishing patients with MRI-negative TLE from normal controls.

Visual expertise modulates resting-state brain network dynamics in radiologists: a degree centrality analysis

Visual expertise reflects accumulated experience in reviewing domain-specific images and has been shown to modulate brain function in task-specific functional magnetic resonance imaging studies. However, little is known about how visual experience modulates resting-state brain network dynamics. To explore this, we recruited 22 radiology interns and 22 matched healthy controls and used resting-state functional magnetic resonance imaging (rs-fMRI) and the degree centrality (DC) method to investigate changes in brain network dynamics. Our results revealed significant differences in DC between the RI and control group in brain regions associated with visual processing, decision making, memory, attention control, and working memory. Using a recursive feature elimination-support vector machine algorithm, we achieved a classification accuracy of 88.64%. Our findings suggest that visual experience modulates resting-state brain network dynamics in radiologists and provide new insights into the neural mechanisms of visual expertise.

Aberrant topology of white matter networks in patients with methamphetamine dependence and its application in support vector machine-based classification

Brain white matter (WM) networks have been widely studied in neuropsychiatric disorders. However, few studies have evaluated alterations in WM network topological organization in patients with methamphetamine (MA) dependence. Therefore, using machine learning classification methods to analyze WM network topological attributes may give new insights into patients with MA dependence. In the study, diffusion tensor imaging-based probabilistic tractography was used to map the weighted WM networks in 46 MA-dependent patients and 46 control subjects. Using graph-theoretical analyses, the global and regional topological attributes of WM networks for both groups were calculated and compared to determine inter-group differences using a permutation-based general linear model. In addition, the study used a support vector machine (SVM) learning approach to construct a classifier for discriminating subjects with MA dependence from control subjects. Relative to the control group, the MA-dependent group exhibited abnormal topological organization, as evidenced by decreased small-worldness and modularity, and increased nodal efficiency in the right medial superior temporal gyrus, right pallidum, and right ventromedial putamen; the MA-dependent group had the higher hubness scores in 25 regions, which were mainly located in the default mode network. An SVM trained with topological attributes achieved classification accuracy, sensitivity, specificity, and kappa values of 98.09% ± 2.59%, 98.24% ± 4.00%, 97.94% ± 4.26%, and 96.18% ± 5.19% for patients with MA dependence. Our results may suggest altered global WM structural networks in MA-dependent patients. Furthermore, the abnormal WM network topological attributes may provide promising features for the construction of high-efficacy classification models.

Smoking is associated with lower brain volume and cognitive differences: A large population analysis based on the UK Biobank

The evidence about the association of smoking with both brain structure and cognitive functions remains inconsistent. Using structural magnetic resonance imaging from the UK Biobank (n = 33,293), we examined the relationships between smoking status, dosage, and abstinence with total and 166 regional brain gray matter volumes (GMV). The relationships between the smoking parameters with cognitive function, and whether this relationship was mediated by brain structure, were then investigated. Smoking was associated with lower total and regional GMV, with the extent depending on the frequency of smoking and on whether smoking had ceased: active regular smokers had the lowest GMV (Cohen's d = -0.362), and former light smokers had a slightly smaller GMV (Cohen's d = -0.060). The smaller GMV in smokers was most evident in the thalamus. Higher lifetime exposure (i.e., pack-years) was associated with lower total GMV (β = -311.84, p = 8.35 × 10-36). In those who ceased smoking, the duration of abstinence was associated with a larger total GMV (β = 139.57, p = 2.36 × 10-08). It was further found that reduced cognitive function was associated with smoker parameters and that the associations were partially mediated by brain structure. This is the largest scale investigation we know of smoking and brain structure, and these results are likely to be robust. The findings are of associations between brain structure and smoking, and in the future, it will be important to assess whether brain structure influences smoking status, or whether smoking influences brain structure, or both.

Increased spontaneous activity of the superior frontal gyrus with reduced functional connectivity to visual attention areas and cerebellum in male smokers

Background

Chronic smokers have abnormal spontaneous regional activity and disrupted functional connectivity as revealed by previous neuroimaging studies. Combining different dimensions of resting-state functional indicators may help us learn more about the neuropathological mechanisms of smoking.

Methods

The amplitude of low frequency fluctuations (ALFF) of 86 male smokers and 56 male non-smokers were first calculated. Brain regions that displayed significant differences in ALFF between two groups were selected as seeds for further functional connectivity analysis. Besides, we examined correlations between brain areas with abnormal activity and smoking measurements.

Results

Increased ALFF in left superior frontal gyrus (SFG), left medial superior frontal gyrus (mSFG) and middle frontal gyrus (MFG) as well as decreased ALFF in right calcarine sulcus were observed in smokers compared with non-smokers. In the seed-based functional connectivity analysis, smokers showed attenuated functional connectivity with left SFG in left precuneus, left fusiform gyrus, left lingual gyrus, left cerebellum 4 5 and cerebellum 6 as well as lower functional connectivity with left mSGF in left fusiform gyrus, left lingual gyrus, left parahippocampal gyrus (PHG), left calcarine sulcus, left cerebellum 4 5, cerebellum 6 and cerebellum 8 (GRF corrected, Pvoxel < 0.005, Pcluster<0.05). Furthermore, attenuated functional connectivity with left mSGF in left lingual gyrus and PHG displayed a negative correlation with FTND scores (r = −0.308, p = 0.004; r = −0.326, p = 0.002 Bonferroni corrected).

Conclusion

Our findings of increased ALFF in SFG with reduced functional connectivity to visual attention areas and cerebellum subregions may shed new light on the pathophysiology of smoking.

Machine learning with neuroimaging biomarkers: Application in the diagnosis and prediction of drug addiction

Drug abuse is a serious problem worldwide. Owing to intermittent intake of certain substances and the early inconspicuous clinical symptoms, this brings huge challenges for timely diagnosing addiction status and preventing substance use disorders (SUDs). As a non-invasive technique, neuroimaging can capture neurobiological signatures of abnormality in multiple brain regions caused by drug consumption in each clinical stage, like parenchymal morphology alteration as well as aberrant functional activity and connectivity of cerebral areas, making it realizable to diagnosis, prediction and even preemptive therapy of addiction. Machine learning (ML) algorithms primarily used for classification have been extensively applied in analysing medical imaging datasets. Significant neurobiological characteristics employed and revealed by classifiers were used to diagnose addictive states and predict initiation and vulnerability to drug usage, treatment abstinence, relapse and resilience of addicts and the risk of SUD. In this review, we summarize application of ML methods in neuroimaging focusing on addicts' diagnosis of clinical status and risk prediction and elucidate the discriminative neurobiological features from brain electrophysiological, morphological and functional perspectives that contribute most to the classifier, finally highlighting the auxiliary role of ML in addiction treatment.

Real-World Visual Experience Alters Baseline Brain Activity in the Resting State: A Longitudinal Study Using Expertise Model of Radiologists

Visual experience modulates the intensity of evoked brain activity in response to training-related stimuli. Spontaneous fluctuations in the restful brain actively encode previous learning experience. However, few studies have considered how real-world visual experience alters the level of baseline brain activity in the resting state. This study aimed to investigate how short-term real-world visual experience modulates baseline neuronal activity in the resting state using the amplitude of low-frequency (<0.08 Hz) fluctuation (ALFF) and a visual expertise model of radiologists, who possess fine-level visual discrimination skill of homogeneous stimuli. In detail, a group of intern radiologists (n = 32) were recruited. The resting-state fMRI data and the behavioral data regarding their level of visual expertise in radiology and face recognition were collected before and after 1 month of training in the X-ray department in a local hospital. A machine learning analytical method, i.e., support vector machine, was used to identify subtle changes in the level of baseline brain activity. Our method led to a superb classification accuracy of 86.7% between conditions. The brain regions with highest discriminative power were the bilateral cingulate gyrus, the left superior frontal gyrus, the bilateral precentral gyrus, the bilateral superior parietal lobule, and the bilateral precuneus. To the best of our knowledge, this study is the first to investigate baseline neurodynamic alterations in response to real-world visual experience using longitudinal experimental design. These results suggest that real-world visual experience alters the resting-state brain representation in multidimensional neurobehavioral components, which are closely interrelated with high-order cognitive and low-order visual factors, i.e., attention control, working memory, memory, and visual processing. We propose that our findings are likely to help foster new insights into the neural mechanisms of visual expertise.

Machine Learning for Detecting Parkinson’s Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

Parkinson’s disease (PD) is one of the most common progressive degenerative diseases, and its diagnosis is challenging on clinical grounds. Clinically, effective and quantifiable biomarkers to detect PD are urgently needed. In our study, we analyzed data from two centers, the primary set was used to train the model, and the independent external validation set was used to validate our model. We applied amplitude of low-frequency fluctuation (ALFF)-based radiomics method to extract radiomics features (including first- and high-order features). Subsequently, t-test and least absolute shrinkage and selection operator (LASSO) were harnessed for feature selection and data dimensionality reduction, and grid search method and nested 10-fold cross-validation were applied to determine the optimal hyper-parameter λ of LASSO and evaluate the performance of the model, in which a support vector machine was used to construct the classification model to classify patients with PD and healthy controls (HCs). We found that our model achieved good performance [accuracy = 81.45% and area under the curve (AUC) = 0.850] in the primary set and good generalization in the external validation set (accuracy = 67.44% and AUC = 0.667). Most of the discriminative features were high-order radiomics features, and the identified brain regions were mainly located in the sensorimotor network and lateral parietal cortex. Our study indicated that our proposed method can effectively classify patients with PD and HCs, ALFF-based radiomics features that might be potential biomarkers of PD, and provided further support for the pathological mechanism of PD, that is, PD may be related to abnormal brain activity in the sensorimotor network and lateral parietal cortex.

Discriminative Analysis of Schizophrenia Patients Using Topological Properties of Structural and Functional Brain Networks: A Multimodal Magnetic Resonance Imaging Study

Interest in the application of machine learning (ML) techniques to multimodal magnetic resonance imaging (MRI) data for the diagnosis of schizophrenia (SZ) at the individual level is growing. However, a few studies have applied the features of structural and functional brain networks derived from multimodal MRI data to the discriminative analysis of SZ patients at different clinical stages. In this study, 205 normal controls (NCs), 61 first-episode drug-naive SZ (FESZ) patients, and 79 chronic SZ (CSZ) patients were recruited. We acquired their structural MRI, diffusion tensor imaging, and resting-state functional MRI data and constructed brain networks for each participant, including the gray matter network (GMN), white matter network (WMN), and functional brain network (FBN). We then calculated 3 nodal properties for each brain network, including degree centrality, nodal efficiency, and betweenness centrality. Two classifications (SZ vs. NC and FESZ vs. CSZ) were performed using five ML algorithms. We found that the SVM classifier with the input features of the combination of nodal properties of both the GMN and FBN achieved the best performance to discriminate SZ patients from NCs [accuracy, 81.2%; area under the receiver operating characteristic curve (AUC), 85.2%; p &lt; 0.05]. Moreover, the SVM classifier with the input features of the combination of the nodal properties of both the GMN and WMN achieved the best performance to discriminate FESZ from CSZ patients (accuracy, 86.2%; AUC, 92.3%; p &lt; 0.05). Furthermore, the brain areas in the subcortical/cerebellum network and the frontoparietal network showed significant importance in both classifications. Together, our findings provide new insights to understand the neuropathology of SZ and further highlight the potential advantages of multimodal network properties for identifying SZ patients at different clinical stages.

Machine learning approaches for parsing comorbidity/heterogeneity in antisociality and substance use disorders: A primer

By some accounts, as many as 93% of individuals diagnosed with antisocial personality disorder (ASPD) or psychopathy also meet criteria for some form of substance use disorder (SUD). This high level of comorbidity, combined with an overlapping biopsychosocial profile, and potentially interacting features, has made it difficult to delineate the shared/unique characteristics of each disorder. Moreover, while rarely acknowledged, both SUD and antisociality exist as highly heterogeneous disorders in need of more targeted parcellation. While emerging data-driven nosology for psychiatric disorders (e.g., Research Domain Criteria (RDoC), Hierarchical Taxonomy of Psychopathology (HiTOP)) offers the opportunity for a more systematic delineation of the externalizing spectrum, the interrogation of large, complex neuroimaging-based datasets may require data-driven approaches that are not yet widely employed in psychiatric neuroscience. With this in mind, the proposed article sets out to provide an introduction into machine learning methods for neuroimaging that can help parse comorbid, heterogeneous externalizing samples. The modest machine learning work conducted to date within the externalizing domain demonstrates the potential utility of the approach but remains highly nascent. Within the paper, we make suggestions for how future work can make use of machine learning methods, in combination with emerging psychiatric nosology systems, to further diagnostic and etiological understandings of the externalizing spectrum. Finally, we briefly consider some challenges that will need to be overcome to encourage further progress in the field.

Classification of Obsessive-Compulsive Disorder Using Distance Correlation on Resting-State Functional MRI Images

Both the Pearson correlation and partial correlation methods have been widely used in the resting-state functional MRI (rs-fMRI) studies. However, they can only measure linear relationship, although partial correlation excludes some indirect effects. Recent distance correlation can discover both the linear and non-linear dependencies. Our goal was to use the multivariate pattern analysis to compare the ability of such three correlation methods to distinguish between the patients with obsessive-compulsive disorder (OCD) and healthy control subjects (HCSs), so as to find optimal correlation method. The main process includes four steps. First, the regions of interest are defined by automated anatomical labeling (AAL). Second, functional connectivity (FC) matrices are constructed by the three correlation methods. Third, the best discriminative features are selected by support vector machine recursive feature elimination (SVM-RFE) with a stratified N-fold cross-validation strategy. Finally, these discriminative features are used to train a classifier. We had a total of 128 subjects out of which 61 subjects had OCD and 67 subjects were normal. All the three correlation methods with SVM have achieved good results, among which distance correlation is the best [accuracy = 93.01%, specificity = 89.71%, sensitivity = 95.08%, and area under the receiver-operating characteristic curve (AUC) = 0.94], followed by Pearson correlation and partial correlation is the last. The most discriminative regions of the brain for distance correlation are right dorsolateral superior frontal gyrus, orbital part of left superior frontal gyrus, orbital part of right middle frontal gyrus, right anterior cingulate and paracingulate gyri, left the supplementary motor area, and right precuneus, which are the promising biomarkers of OCD.

A multivariate pattern analysis of resting-state functional MRI data in Naïve and chronic betel quid chewers

Betel quid (BQ) is the fourth most commonly consumed psychoactive substance in the world. However, comprehensive functional magnetic resonance imaging (fMRI) studies exploring the neurophysiological mechanism of BQ addiction are lacking. Betel-quid-dependent (BQD) individuals (n = 24) and age-matched healthy controls (HC) (n = 26) underwent fMRI before and after chewing BQ. Multivariate pattern analysis (MVPA) was used to explore the acute effects of BQ-chewing in both groups. A cross-sectional comparison was conducted to explore the chronic effects of BQ-chewing. Regression analysis was used to investigate the relationship between altered circuits of BQD individuals and the severity of BQ addiction. MVPA achieved classification accuracies of up to 90% in both groups for acute BQ-chewing. Suppression of the default-mode network was the most prominent feature. BQD showed more extensive and intensive within- and between-network dysconnectivity of the default, frontal-parietal, and occipital regions associated with high-order brain functions such as self-awareness, inhibitory control, and decision-making. In contrast, the chronic effects of BQ on the brain function were mild, but impaired circuits were predominately located in the default and frontal-parietal networks which might be associated with compulsive drug use. Simultaneously quantifying the effects of both chronic and acute BQ exposure provides a possible neuroimaging-based BQ addiction foci. Results from this study may help us understand the neural mechanisms involved in BQ-chewing and BQ dependence.

Support vector machine based classification of smokers and nonsmokers using diffusion tensor imaging

Despite significant progress in treatments for smoking cessation, smoking continues to be a significant public health concern, especially in young adulthood. Thus, developing a predictive model that can classify and characterize the brain-based biomarkers predicting smoking status would be imperative to improving treatment development. In this study, we applied a support vector machine-based classification method to discriminate 70 young male smokers and 70 matched nonsmokers using their diffusion tensor imaging (DTI) data. The classification procedure achieved an average accuracy of 88.6% and an average area under the curve of 0.95. The most discriminative features that contributed to the classification were primarily located in the sagittal stratum (SS), external capsule (EC), superior longitudinal fasciculus (SLF), anterior corona radiata (ACR) and inferior front-occipital fasciculus (IFOF). The following regression analysis showed a significant negatively correlation between the average RD values of the left ACR (r = -0.247, p = 0.039) and FTND. The average MD values in the right EC (r = -0.254, p = 0.034) and RD values in the right IFOF (r = -0.240, p = 0.046) were inversely associated with pack-years. Our findings indicate that the discriminative white matter (WM) features as brain biomarkers provide great predictive power for smoking status and suggest that machine learning techniques can reveal underlying smoking-related neurobiology.

Detection and Classification of Bearing Surface Defects Based on Machine Vision

Surface defects on bearings can directly affect the service life and reduce the performance of equipment. At present, the detection of bearing surface defects is mostly done manually, which is labor-intensive and results in poor stability. To improve the inspection speed and the defect recognition rate, we proposed a bearing surface defect detection and classification method using machine vision technology. The method makes two main contributions. It proposes a local multi-neural network (Lc-MNN) image segmentation algorithm with the wavelet transform as the classification feature. The precision segmentation of the defect image is accomplished in three steps: wavelet feature extraction, Lc-MNN region division, and Lc-MNN classification. It also proposes a feature selection algorithm (SCV) that makes comprehensive use of scalar feature selection, correlation analysis, and vector feature selection to first remove similar features through correlation analysis, further screen the results with a scalar feature selection algorithm, and finally select the classification features using a feature vector selection algorithm. Using 600 test samples with three types of defect in the experiment, an identification rate of 99.5% was achieved without the need for large-scale calculation. The comparison tests indicated that the proposed method can achieve efficient feature selection and defect classification.

Identification of internet gaming disorder individuals based on ventral tegmental area resting-state functional connectivity

Objective neuroimaging markers are imminently in need for more accurate clinical diagnosis of Internet gaming disorder (IGD). Recent neuroimaging evidence suggested that IGD is associated with abnormalities in the mesolimbic dopamine (DA) system. As the key nodes of the DA pathways, ventral tegmental area (VTA) and substantia nigra (SN) and their connected brain regions may serve as potential markers to identify IGD. Therefore, we aimed to develop optimal classifiers to identify IGD individuals by using VTA and bilateral SN resting-state functional connectivity (RSFC) patterns. A dataset including 146 adolescents (66 IGDs and 80 healthy controls (HCs)) was used to build classification models and another independent dataset including 28 subjects (14 IGDs and 14 HCs) was employed to validate the generalization ability of the models. Multi-voxel pattern analysis (MVPA) with linear support vector machine (SVM) was used to select the features. Our results demonstrated that the VTA RSFC circuits successfully identified IGD individuals (mean accuracy: 86.1%, mean sensitivity: 84.5%, mean specificity: 86.6%, the mean area under the receiver operating characteristic curve: 0.91). Furthermore, the independent generalization ability of the VTA RSFC classifier model was also satisfied (accuracy = 78.5%, sensitivity = 71.4%, specificity = 85.8%). The VTA connectivity circuits that were selected as distinguishing features were mainly included bilateral thalamus, right hippocampus, right pallidum, right temporal pole superior gyrus and bilateral temporal superior gyrus. These findings demonstrated that the potential of the resting-state neuroimaging features of VTA RSFC as objective biomarkers for the IGD clinical diagnosis in the future.

Exploring feature selection of St John's wort grown under different light spectra using 1 H-NMR spectroscopy

INTRODUCTION

Nuclear magnetic resonance (NMR) spectroscopy combined with multivariate statistical analysis can provide tools to help detect differences in plant chemistry when grown under varying conditions. Hypericum perforatum, or Saint John's wort, plants are a suitable model to explore methods of discrimination between early stage plants grown in different conditions.

OBJECTIVES

The purpose of this work was to develop a method for identifying differences in chemical profiles between young Hypericum perforatum plants grown under different lighting conditions.

MATERIAL AND METHODS

Cuttings were grown for 3 weeks under different light conditions. Plant extracts were prepared in MeOD-d₄ and analysed by ¹ H-NMR. A multivariate analysis method of the NMR data was developed in an effort to determine variations in chemical profiles.

RESULTS

The method identified specific metabolites as drivers of difference between the plants grown under different light conditions. STOCSY (statistical total correlation spectroscopy) and quantification of highlighted metabolites supported the findings of the multivariate analysis. Glutamine, sucrose and fructose were found to be chemical markers of light quality in this study.

CONCLUSION

NMR metabolomics using a medium field instrument could find differences in plant chemistry when grown in different conditions. This method could easily be extended to benchtop instruments and be used for crop monitoring and growth condition optimisation.

Towards a brain-based predictome of mental illness

Neuroimaging-based approaches have been extensively applied to study mental illness in recent years and have deepened our understanding of both cognitively healthy and disordered brain structure and function. Recent advancements in machine learning techniques have shown promising outcomes for individualized prediction and characterization of patients with psychiatric disorders. Studies have utilized features from a variety of neuroimaging modalities, including structural, functional, and diffusion magnetic resonance imaging data, as well as jointly estimated features from multiple modalities, to assess patients with heterogeneous mental disorders, such as schizophrenia and autism. We use the term "predictome" to describe the use of multivariate brain network features from one or more neuroimaging modalities to predict mental illness. In the predictome, multiple brain network-based features (either from the same modality or multiple modalities) are incorporated into a predictive model to jointly estimate features that are unique to a disorder and predict subjects accordingly. To date, more than 650 studies have been published on subject-level prediction focusing on psychiatric disorders. We have surveyed about 250 studies including schizophrenia, major depression, bipolar disorder, autism spectrum disorder, attention-deficit hyperactivity disorder, obsessive-compulsive disorder, social anxiety disorder, posttraumatic stress disorder, and substance dependence. In this review, we present a comprehensive review of recent neuroimaging-based predictomic approaches, current trends, and common shortcomings and share our vision for future directions.

A New Method Based on CEEMD Combined With Iterative Feature Reduction for Aided Diagnosis of Epileptic EEG

In the clinical diagnosis of epileptic diseases, the intelligent diagnosis of epileptic electroencephalogram (EEG) signals has become a research focus in the field of brain diseases. In order to solve the problem of time-consuming and easily influenced by human subjective factors, artificial intelligence pattern recognition algorithm has been applied to EEG signals recognition. However, at present, the common empirical mode decomposition (EMD) signal decomposition algorithm does not consider the problem of mode aliasing. The EEG features obtained by feature extraction may be mixed with some unimportant features that affect the classification accuracy. In this paper, we proposed a new method based on complementary ensemble empirical mode decomposition (CEEMD) combined with iterative feature reduction for aided diagnosis of epileptic EEG. First of all, the evaluation indexes of decomposing and reconstructing signals by several methods were compared. The CEEMD was selected as the decomposition method of the signals. Then, the support vector machine recursive elimination (SVM-RFE) was used to reduce 9 features extracted from EEG data. The support vector classification of the gray wolf optimizer (GWO-SVC) recognition model was established for different feature subsets. By comparing the classification accuracy of training set and test set of different feature subsets, and considering the complexity of the model reflected by the number of features selected by SVM-RFE, the analysis showed that the 6 feature subsets with fewer features and higher classification accuracy could reflect the key information of epileptic EEG. The accuracy of the training set classification was 99.38% and the test set was as high as 100%. The recognition time was only 1.6551 s. Finally, in order to verify the reliability of the algorithm proposed in this paper, the proposed algorithm compared with the classification model established by the raw EEG signals and the optimization model established by other intelligent optimization algorithms. It is found that the algorithm used in this paper has higher classification accuracy and faster recognition time than other processing methods. The experimental results show that CEEMD combined with SVM-RFE is feasible for rapid and accurate recognition of EEG signals, which provides a theoretical basis for the aided diagnosis of epilepsy.

Characterizing the Structural Pattern of Heavy Smokers Using Multivoxel Pattern Analysis

Background: Smoking addiction is a major public health issue which causes a series of chronic diseases and mortalities worldwide. We aimed to explore the most discriminative gray matter regions between heavy smokers and healthy controls with a data-driven multivoxel pattern analysis technique, and to explore the methodological differences between multivoxel pattern analysis and voxel-based morphometry. Methods: Traditional voxel-based morphometry has continuously contributed to finding smoking addiction-related regions on structural magnetic resonance imaging. However, voxel-based morphometry has its inherent limitations. In this study, a multivoxel pattern analysis using a searchlight algorithm and support vector machine was applied on structural magnetic resonance imaging to identify the spatial pattern of gray matter volume in heavy smokers. Results: Our proposed method yielded a voxel-wise accuracy of at least 81% for classifying heavy smokers from healthy controls. The identified regions were primarily located at the temporal cortex and prefrontal cortex, occipital cortex, thalamus (bilateral), insula (left), anterior and median cingulate gyri, and precuneus (left). Conclusions: Our results suggested that several regions, which were seldomly reported in voxel-based morphometry analysis, might be latently correlated with smoking addiction. Such findings might provide insights for understanding the mechanism of chronic smoking and the creation of effective cessation treatment. Multivoxel pattern analysis can be efficient in locating brain discriminative regions which were neglected by voxel-based morphometry.

Support vector machine-based multivariate pattern classification of methamphetamine dependence using arterial spin labeling

Arterial spin labeling (ASL) magnetic resonance imaging has been widely applied to identify cerebral blood flow (CBF) abnormalities in a number of brain disorders. To evaluate its significance in detecting methamphetamine (MA) dependence, this study used a multivariate pattern classification algorithm, ie, a support vector machine (SVM), to construct classifiers for discriminating MA-dependent subjects from normal controls. Forty-five MA-dependent subjects, 45 normal controls, and 36 heroin-dependent subjects were enrolled. Classifiers trained with ASL-CBF data from the left or right cerebrum showed significant hemispheric asymmetry in their cross-validated prediction performance (P < 0.001 for accuracy, sensitivity, specificity, kappa, and area under the curve [AUC] of the receiver operating characteristics [ROC] curve). A classifier trained with ASL-CBF data from all cerebral regions (bilateral hemispheres and corpus callosum) was able to differentiate MA-dependent subjects from normal controls with a cross-validated prediction accuracy, sensitivity, specificity, kappa, and AUC of 89%, 94%, 84%, 0.78, and 0.95, respectively. The discrimination map extracted from this classifier covered multiple brain circuits that either constitute a network related to drug abuse and addiction or could be impaired in MA-dependence. The cerebral regions contribute most to classification include occipital lobe, insular cortex, postcentral gyrus, corpus callosum, and inferior frontal cortex. This classifier was also specific to MA-dependence rather than substance use disorders in general (ie, 55.56% accuracy for heroin dependence). These results support the future utilization of ASL with an SVM-based classifier for the diagnosis of MA-dependence and could help improve the understanding of MA-related neuropathology.

Brain Gray Matter Volume and Functional Connectivity Are Associated With Smoking Cessation Outcomes

Smoking cessation is critical for reducing the risk of respiratory, cardiovascular diseases and cancers. However, most cessation attempts resulted in failure. In the present study, we aim to explore whether alterations of brain gray matter (GM) volume and functional connectivity (FC) are related to cessation outcomes, in hope of providing evidence for improving smoking cessation outcomes. Seventy-three smokers and 41 non-smokers were enrolled in the present study. All smokers participated in a 12-week smoking cessation treatment during which Varenicline was used to aid cessation. At the end of treatment, the smokers were divided into quitters and relapsers based on their abstinence performance. Structural magnetic resonance imaging (MRI) and voxel-based morphometry were applied to quantify the differences of regional brain volumes among the three groups at baseline. In addition, resting-state FC was used to investigate the related functional changes. In comparison with non-smokers, the smokers showed smaller GM volume in the left dorsal medial thalamus. Among the 73 smokers, 29 subjects successfully quitted smoking. The quitters showed greater GM volume than the relapsers in the right postcentral gyrus, right putamen\caudate nucleus and left orbitofrontal cortex (OFC). The GM volume in the left OFC was found to be negatively correlated with the pack years and daily smoking amount in the quitters. Furthermore, we found significantly reduced FC between left thalamus and left cerebellum in the relapsers. These findings extended our knowledge of the neural mechanism of smoking cessation, and suggested that brain structural and functional changes were related to smoking cessation outcomes.

Use of Magnetic Resonance Imaging and Artificial Intelligence in Studies of Diagnosis of Parkinson's Disease

Parkinson's disease (PD) is a common neurodegenerative disorder. It has a delitescent onset and a slow progress. The clinical manifestations of PD in patients are highly heterogeneous. Thus, PD diagnosis process is complex and mainly depends on the professional knowledge and experience of the physician. Magnetic resonance imaging (MRI) could detect the small changes in the brain of PD patients, and quantitative analysis of brain MRI may improve the clinical diagnosis efficiency. However, due to the complexity of clinical courses in PD and the high dimensionality in multimodal MRI data, traditional mathematical analysis could not effectively extract the huge information in them. Up to now, the accuracy of PD diagnosis in large sample size is still unsatisfying. As artificial intelligence (AI) is becoming more mature, varieties of statistical models and machine learning (ML) algorithms have been used for quantitative imaging data analysis to explore a diagnostic result. This review aims to state an overview of existing research recently that used statistical ML/AI methods to perform quantitative analysis of MR image data for the study of PD diagnosis. First we review the recent research in three subareas: diagnosis, differential diagnosis, and subtyping of PD. Then we described the overall workflow from MR image to classification result. Finally, we summarized a critical assessment of the current research and provide some recommendations for likely future research developments and trends.

MinE-RFE: determine the optimal subset from RFE by minimizing the subset-accuracy–defined energy

Recursive feature elimination (RFE), as one of the most popular feature selection algorithms, has been extensively applied to bioinformatics. During the training, a group of candidate subsets are generated by iteratively eliminating the least important features from the original features. However, how to determine the optimal subset from them still remains ambiguous. Among most current studies, either overall accuracy or subset size (SS) is used to select the most predictive features. Using which one or both and how they affect the prediction performance are still open questions. In this study, we proposed MinE-RFE, a novel RFE-based feature selection approach by sufficiently considering the effect of both factors. Subset decision problem was reflected into subset-accuracy space and became an energy-minimization problem. We also provided a mathematical description of the relationship between the overall accuracy and SS using Gaussian Mixture Models together with spline fitting. Besides, we comprehensively reviewed a variety of state-of-the-art applications in bioinformatics using RFE. We compared their approaches of deciding the final subset from all the candidate subsets with MinE-RFE on diverse bioinformatics data sets. Additionally, we also compared MinE-RFE with some well-used feature selection algorithms. The comparative results demonstrate that the proposed approach exhibits the best performance among all the approaches. To facilitate the use of MinE-RFE, we further established a user-friendly web server with the implementation of the proposed approach, which is accessible at http://qgking.wicp.net/MinE/. We expect this web server will be a useful tool for research community.

Discrimination of smoking status by MRI based on deep learning method

Background

This study aimed to assess the feasibility of deep learning-based magnetic resonance imaging (MRI) in the prediction of smoking status.

Methods

The head MRI 3D-T1WI images of 127 subjects (61 smokers and 66 non-smokers) were collected, and 176 image slices obtained for each subject. These subjects were 23-45 years old, and the smokers had at least 5 years of smoking experience. Approximate 25% of the subjects were randomly selected as the test set (15 smokers and 16 non-smokers), and the remaining subjects as the training set. Two deep learning models were developed: deep 3D convolutional neural network (Conv3D) and convolution neural network plus a recurrent neural network (RNN) with long short-term memory architecture (ConvLSTM).

Results

In the prediction of smoking status, Conv3D model achieved an accuracy of 80.6% (25/31), a sensitivity of 80.0% and a specificity of 81.3%, and ConvLSTM model achieved an accuracy of 93.5% (29/31), a sensitivity of 93.33% and a specificity of 93.75%. The accuracy obtained by these methods was significantly higher than that (<70%) obtained with support vector machine (SVM) methods.

Conclusions

The deep learning-based MRI can accurately predict smoking status. Studies with large sample size are needed to improve the accuracy and to predict the level of nicotine dependence.

Predicting chemo-brain in breast cancer survivors using multiple MRI features and machine-learning

PURPOSE

Breast cancer (BC) is the most common cancer in women worldwide. There exist various advanced chemotherapy drugs for BC; however, chemotherapy drugs may result in brain damage during treatment. When a patient's brain is changed in response to chemo drugs, it is termed chemo-brain. In this study, we aimed to construct machine-learning models to detect the subtle alternations of the brain in postchemotherapy BC patients.

METHODS

Nineteen BC patients undergoing chemotherapy and 20 healthy controls (HCs) were recruited for this study. Both groups underwent resting-state functional MRI and generalized q-sampling imaging (GQI).

RESULTS

Logistic regression (LR) with GQI indices in standardized voxel-wise analysis, LR with mean regional homogeneity in regional summation analysis, decision tree classifier (CART) with generalized fractional anisotropy in voxel-wise analysis, and XGBoost (XGB) with normalized quantitative anisotropy had formidable performances in classifying subjects into a chemo-brain group or an HC group. Classifying the brain MRIs of HC and postchemotherapy patients by conducting leave-one-out cross-validation resulted in the highest accuracy of 84%, which was attained by LR, CART, and XGB with multiple feature sets.

CONCLUSIONS

In our study, we constructed the machine-learning models that were able to identify chemo-brains from normal brains. We are hopeful that these results will be helpful in clinically tracking chemo-brains in the future.

Hick-Hyman Law is Mediated by the Cognitive Control Network in the Brain

The Hick-Hyman law describes a linear increase in reaction time (RT) as a function of the information entropy of response selection, which is computed as the binary logarithm of the number of response alternatives. While numerous behavioral studies have provided evidence for the Hick-Hyman law, its neural underpinnings have rarely been examined and are still unclear. In this functional magnetic resonance imaging study, by utilizing a choice reaction time task to manipulate the entropy of response selection, we examined brain activity mediating the input and the output, as well as the connectivity between corresponding regions in human participants. Beyond confirming the Hick-Hyman law in RT performance, we found that activation of the cognitive control network (CCN) increased and activation of the default mode network (DMN) decreased, both as a function of entropy. However, only the CCN, but not the DMN, was involved in mediating the relationship between entropy and RT. The CCN was involved in both stages of uncertainty representation and response generation, while the DMN was mainly involved at the stage of uncertainty representation. These findings indicate that the CCN serves as a core entity underlying the Hick-Hyman law by coordinating uncertainty representation and response generation in the brain.

Decision Variants for the Automatic Determination of Optimal Feature Subset in RF-RFE

Feature selection, which identifies a set of most informative features from the original feature space, has been widely used to simplify the predictor. Recursive feature elimination (RFE), as one of the most popular feature selection approaches, is effective in data dimension reduction and efficiency increase. A ranking of features, as well as candidate subsets with the corresponding accuracy, is produced through RFE. The subset with highest accuracy (HA) or a preset number of features (PreNum) are often used as the final subset. However, this may lead to a large number of features being selected, or if there is no prior knowledge about this preset number, it is often ambiguous and subjective regarding final subset selection. A proper decision variant is in high demand to automatically determine the optimal subset. In this study, we conduct pioneering work to explore the decision variant after obtaining a list of candidate subsets from RFE. We provide a detailed analysis and comparison of several decision variants to automatically select the optimal feature subset. Random forest (RF)-recursive feature elimination (RF-RFE) algorithm and a voting strategy are introduced. We validated the variants on two totally different molecular biology datasets, one for a toxicogenomic study and the other one for protein sequence analysis. The study provides an automated way to determine the optimal feature subset when using RF-RFE.

A Novel Approach to the Identification of Compromised Pulmonary Systems in Smokers by Exploiting Tidal Breathing Patterns

Smoking causes unalterable physiological abnormalities in the pulmonary system. This is emerging as a serious threat worldwide. Unlike spirometry, tidal breathing does not require subjects to undergo forceful breathing maneuvers and is progressing as a new direction towards pulmonary health assessment. The aim of the paper is to evaluate whether tidal breathing signatures can indicate deteriorating adult lung condition in an otherwise healthy person. If successful, such a system can be used as a pre-screening tool for all people before some of them need to undergo a thorough clinical checkup. This work presents a novel systematic approach to identify compromised pulmonary systems in smokers from acquired tidal breathing patterns. Tidal breathing patterns are acquired during restful breathing of adult participants. Thereafter, physiological attributes are extracted from the acquired tidal breathing signals. Finally, a unique classification approach of locally weighted learning with ridge regression (LWL-ridge) is implemented, which handles the subjective variations in tidal breathing data without performing feature normalization. The LWL-ridge classifier recognized compromised pulmonary systems in smokers with an average classification accuracy of 86.17% along with a sensitivity of 80% and a specificity of 92%. The implemented approach outperformed other variants of LWL as well as other standard classifiers and generated comparable results when applied on an external cohort. This end-to-end automated system is suitable for pre-screening people routinely for early detection of lung ailments as a preventive measure in an infrastructure-agnostic way.

Structural and functional brain abnormalities in drug-naive, first-episode, and chronic patients with schizophrenia: a multimodal MRI study

BACKGROUND

Structural and functional brain abnormalities in schizophrenia (SZ) have been widely reported. However, a few studies have investigated both structural and functional characteristics in SZ patients at different stages to understand the neuropathology of SZ.

METHODS

In this study, we recruited 44 first-episode drug-naive SZ (FESZ) patients, 44 medicated chronic SZ (CSZ) patients, and 56 normal controls (NCs) and acquired their structural and resting-state functional magnetic resonance imaging (MRI). We then made group comparisons on structural and functional characteristics, including regional gray matter volume (GMV), regional homogeneity, amplitude of low-frequency fluctuation, and degree centrality. A linear support vector machine (SVM) combined with a recursive feature elimination (RFE) algorithm was implemented to discriminate three groups.

RESULTS

Our results indicated that the regional GMV was significantly decreased in patients compared with that in NCs; CSZ patients have more diffused GMV decreases primarily involved in the frontal and temporal lobes when compared with FESZ patients. Both FESZ and CSZ patients showed significant functional alterations compared with NCs; when compared with FESZ patients, CSZ patients showed significant reductions in functional characteristics in several brain regions associated with auditory, visual processing, and sensorimotor functions. Moreover, a linear SVM combined with a RFE algorithm was implemented to discriminate three groups. The accuracies of the three classifiers were 79.80%, 83.16%, and 81.71%, respectively. The performance of classifiers in this study with multimodal MRI was better than that of previous discriminative analyses of SZ patients with single-modal MRI.

CONCLUSION

Our findings bring new insights into the understanding of the neuropathology of SZ and contribute to stage-specific biomarkers in diagnosis and interventions of SZ.

Alteration of gray matter texture features over the whole brain in medication-overuse headache using a 3-dimentional texture analysis

Background

Imaging studies have provided valuable information in understanding the headache neuromechanism for medication-overuse headache (MOH), and the aim of this study is to investigate altered texture features of MR structural images over the whole brain in MOH using a 3-dimentional texture analysis.

Methods

Brain three-dimensional T1-weighted structural images were obtained from 44 MOH patients and 32 normal controls (NC). The imaging processing included two steps: gray matter (gray images) segment and a 3-dimensional texture features mapping. Voxel-based gray-level co-occurrence matrix (VGLCM) was performed to measure the texture parameters mapping including Contrast, Correlation, Energy, Entropy and inverse difference moment (IDM).

Results

The texture parameters of increased Contrast and Entropy, decreased Energy and IDM were identified in cerebellar vermis of MOH patients compared to NCs. Increased Contrast and decreased Energy were found in left cerebellum. Increased Correlation located in left dorsolateral periaqueductal gray (L-dlPAG), right parahippocampal gyrus (R-PHG), and left middle frontal gyrus (L-MFG) and decreased Correlation located in right superior parietal lobule(R-SPL). Disease duration was positively correlated with Contrast of vermis and negatively correlated with Correlation of R-SPL.HAMD score was negatively correlated with Correlation of R-PHG. MoCA score was positively correlated with Correlation of R-SPL.

Conclusion

The altered textures in gray matter related to pain discrimination and modulation, affective and cognitive processing were helpful in understanding the pathogenesis of MOH. Texture analysis using VGLCM is a sensitive and efficient method to detect subtle gray matter changes in MOH.

Electronic supplementary material

The online version of this article (10.1186/s10194-017-0820-4) contains supplementary material, which is available to authorized users.

Combining Multiple Resting-State fMRI Features during Classification: Optimized Frameworks and Their Application to Nicotine Addiction

Machine learning techniques have been applied to resting-state fMRI data to predict neurological or neuropsychiatric disease states. Existing studies have used either a single type of resting-state feature or a few feature types (<4) in the prediction model. However, resting-state data can be processed in many different ways, yielding different feature types containing complementary and/or novel information, leaving uncertain the most informative features to provide to the classifier. In this study, multiple resting-state features were calculated from two main analytical categories: local measures and network measures. Feature selection was adopted using an optimized grid-search approach selecting top ranked features from statistical tests. We then tested three optimized frameworks: feature combination, kernel combination, and classifier combination, all using the support vector machine as an elementary classifier, to combine these resting-state feature types. When applied to nicotine addiction, with a cohort size of 100 smokers and 100 non-smokers, via a 10-fold cross-validation procedure, the feature combination and the classifier combination achieved an accuracy of 75.5%, while the kernel combination achieved a 73.0% accuracy; all three combination frameworks improved classification performance compared to the single feature type based results (best accuracy 70.5%). This study not only reveals the discriminative power of resting-state data, but also demonstrates the efficiency of combining multiple features from one data phenotype to improve classification performance.

Altered functional connectivity architecture of the brain in medication overuse headache using resting state fMRI

Background

Functional connectivity density (FCD) could identify the abnormal intrinsic and spontaneous activity over the whole brain, and a seed-based resting-state functional connectivity (RSFC) could further reveal the altered functional network with the identified brain regions. This may be an effective assessment strategy for headache research. This study is to investigate the RSFC architecture changes of the brain in the patients with medication overuse headache (MOH) using FCD and RSFC methods.

Methods

3D structure images and resting-state functional MRI data were obtained from 37 MOH patients, 18 episodic migraine (EM) patients and 32 normal controls (NCs). FCD was calculated to detect the brain regions with abnormal functional activity over the whole brain, and the seed-based RSFC was performed to explore the functional network changes in MOH and EM.

Results

The decreased FCD located in right parahippocampal gyrus, and the increased FCD located in left inferior parietal gyrus and right supramarginal gyrus in MOH compared with NC, and in right caudate and left insula in MOH compared with EM. RSFC revealed that decreased functional connectivity of the brain regions with decreased FCD anchored in the right dorsal-lateral prefrontal cortex, right frontopolar cortex in MOH, and in left temporopolar cortex and bilateral visual cortices in EM compared with NC, and in frontal-temporal-parietal pattern in MOH compared with EM.

Conclusions

These results provided evidence that MOH and EM suffered from altered intrinsic functional connectivity architecture, and the current study presented a new perspective for understanding the neuromechanism of MOH and EM pathogenesis.

Discriminative analysis of schizophrenia using support vector machine and recursive feature elimination on structural MRI images

Structural abnormalities in schizophrenia (SZ) patients have been well documented with structural magnetic resonance imaging (MRI) data using voxel-based morphometry (VBM) and region of interest (ROI) analyses. However, these analyses can only detect group-wise differences and thus, have a poor predictive value for individuals. In the present study, we applied a machine learning method that combined support vector machine (SVM) with recursive feature elimination (RFE) to discriminate SZ patients from normal controls (NCs) using their structural MRI data. We first employed both VBM and ROI analyses to compare gray matter volume (GMV) and white matter volume (WMV) between 41 SZ patients and 42 age- and sex-matched NCs. The method of SVM combined with RFE was used to discriminate SZ patients from NCs using significant between-group differences in both GMV and WMV as input features. We found that SZ patients showed GM and WM abnormalities in several brain structures primarily involved in the emotion, memory, and visual systems. An SVM with a RFE classifier using the significant structural abnormalities identified by the VBM analysis as input features achieved the best performance (an accuracy of 88.4%, a sensitivity of 91.9%, and a specificity of 84.4%) in the discriminative analyses of SZ patients. These results suggested that distinct neuroanatomical profiles associated with SZ patients might provide a potential biomarker for disease diagnosis, and machine-learning methods can reveal neurobiological mechanisms in psychiatric diseases.