Toward Probabilistic Diagnosis and Understanding of Depression Based on Functional MRI Data Analysis with Logistic Group LASSO

Advancing the diagnosis of major depressive disorder: Integrating neuroimaging and machine learning

Major depressive disorder (MDD), a psychiatric disorder characterized by functional brain deficits, poses considerable diagnostic and treatment challenges, especially in adolescents owing to varying clinical presentations. Biomarkers hold substantial clinical potential in the field of mental health, enabling objective assessments of physiological and pathological states, facilitating early diagnosis, and enhancing clinical decision-making and patient outcomes. Recent breakthroughs combine neuroimaging with machine learning (ML) to distinguish brain activity patterns between MDD patients and healthy controls, paving the way for diagnostic support and personalized treatment. However, the accuracy of the results depends on the selection of neuroimaging features and algorithms. Ensuring privacy protection, ML model accuracy, and fostering trust are essential steps prior to clinical implementation. Future research should prioritize the establishment of comprehensive legal frameworks and regulatory mechanisms for using ML in MDD diagnosis while safeguarding patient privacy and rights. By doing so, we can advance accuracy and personalized care for MDD.

MicroRNA classification and discovery for major depressive disorder diagnosis: Towards a robust and interpretable machine learning approach

BACKGROUND

Major depressive disorder (MDD) is notably underdiagnosed and undertreated due to its complex nature and subjective diagnostic methods. Biomarker identification would help provide a clearer understanding of MDD aetiology. Although machine learning (ML) has been implemented in previous studies to study the alteration of microRNA (miRNA) levels in MDD cases, clinical translation has not been feasible due to the lack of interpretability (i.e. too many miRNAs for consideration) and stability.

METHODS

This study applied logistic regression (LR) model to the blood miRNA expression profile to differentiate patients with MDD (n = 60) from healthy controls (HCs, n = 60). Embedded (L1-regularised logistic regression) feature selector was utilised to extract clinically relevant miRNAs, and optimized for clinical application.

RESULTS

Patients with MDD could be differentiated from HCs with the area under the receiver operating characteristic curve (AUC) of 0.81 on testing data when all available miRNAs were considered (which served as a benchmark). Our LR model selected miRNAs up to 5 (known as LR-5 model) emerged as the best model because it achieved a moderate classification ability (AUC = 0.75), relatively high interpretability (feature number = 5) and stability (ϕ̂Z=0.55) compared to the benchmark. The top-ranking miRNAs identified by our model have demonstrated associations with MDD pathways involving cytokine signalling in the immune system, the reelin signalling pathway, programmed cell death and cellular responses to stress.

CONCLUSION

The LR-5 model, which is optimised based on ML design factors, may lead to a robust and clinically usable MDD diagnostic tool.

Spectral Graph Neural Network-Based Multi-Atlas Brain Network Fusion for Major Depressive Disorder Diagnosis

Major Depressive Disorder (MDD) imposes a substantial burden within the healthcare domain, impacting millions of individuals worldwide. Functional Magnetic Resonance Imaging (fMRI) has emerged as a promising tool for the objective diagnosis of MDD, enabling the investigation of functional connectivity patterns in the brain associated with this disorder. However, most existing methods focus on a single brain atlas, which limits their ability to capture the complex, multi-scale nature of functional brain networks. To address these limitations, we propose a novel multi-atlas fusion method that incorporates early and late fusion in a unified framework. Our method introduces the concept of the holistic Functional Connectivity Network (FCN), which captures both intra-atlas relationships within individual atlases and inter-regional relationships between atlases with different brain parcellation scales. This comprehensive representation enables the identification of potential disease-related patterns associated with MDD in the early stage of our framework. Moreover, by decoding the holistic FCN from various perspectives through multiple spectral Graph Convolutional Neural Networks and fusing their results with decision-level ensembles, we further improve the performance of MDD diagnosis. Our approach is easily implemented with minimal modifications to existing model structures and demonstrates a robust performance across different baseline models. Our method, evaluated on public resting-state fMRI datasets, surpasses the current multi-atlas fusion methods, enhancing the accuracy of MDD diagnosis. The proposed novel multi-atlas fusion framework provides a more reliable MDD diagnostic technique. Experimental results show our approach outperforms both single- and multi-atlas-based methods, demonstrating its effectiveness in advancing MDD diagnosis.

Regional decreases of cortical thickness in major depressive disorder and their correlation with illness duration: a case-control study

Background

Alterations in brain structure and function in major depressive disorder (MDD) have been identified in a number of studies, but findings regarding cortical thickness were various and inconsistent. Our current study aims to explore the differences in cortical thickness between individuals with MDD and healthy controls (HC) in a Chinese population.

Methods

We investigated T1-weighted brain magnetic resonance imaging data from 61 participants (31 MDD and 30 HC). The cortical thickness between the two groups and analyzed correlations between cortical thickness and demographic variables in the MDD group for regions with significant between-group differences were conducted.

Results

Compared with the HC group, patients with MDD had significantly decreased cortical thickness, in left pars triangularis, left pars orbitalis, left rostral middle frontal gyrus, left supramarginal gyrus, right parahippocampal gyrus, right lingual gyrus, right fusiform and right inferior parietal gyrus. The cortical thickness of left rostral middle frontal gyrus was negatively correlated (r = -0.47, p = 0.028) with the illness duration in patients with MDD.

Conclusion

Our study distinguished that cortical thickness decreases in numerous brain regions both in the left and right hemisphere in individuals with MDD, and the negative correlation between the cortical thickness of left rostral middle frontal gyrus illness duration. Our current findings are valuable in providing neural markers to identify MDD and understanding the potential pathophysiology of mood disorders.

Stable sound decoding despite modulated sound representation in the auditory cortex

The activity of neurons in the auditory cortex is driven by both sounds and non-sensory context. To investigate the neuronal correlates of non-sensory context, we trained head-fixed mice to perform a two-alternative-choice auditory task in which either reward or stimulus expectation (prior) was manipulated in blocks. Using two-photon calcium imaging to record populations of single neurons in the auditory cortex, we found that both stimulus and reward expectation modulated the activity of these neurons. A linear decoder trained on this population activity could decode stimuli as well or better than predicted by the animal's performance. Interestingly, the optimal decoder was stable even in the face of variable sensory representations. Neither the context nor the mouse's choice could be reliably decoded from the recorded neural activity. Our findings suggest that, in spite of modulation of auditory cortical activity by task priors, the auditory cortex does not represent sufficient information about these priors to exploit them optimally. Thus, the combination of rapidly changing sensory information with more slowly varying task information required for decisions in this task might be represented in brain regions other than the auditory cortex.

Stable sound decoding despite modulated sound representation in the auditory cortex

The activity of neurons in the auditory cortex is driven by both sounds and non-sensory context. To investigate the neuronal correlates of non-sensory context, we trained head-fixed mice to perform a two-alternative choice auditory task in which either reward or stimulus expectation (prior) was manipulated in blocks. Using two-photon calcium imaging to record populations of single neurons in auditory cortex, we found that both stimulus and reward expectation modulated the activity of these neurons. A linear decoder trained on this population activity could decode stimuli as well or better than predicted by the animal's performance. Interestingly, the optimal decoder was stable even in the face of variable sensory representations. Neither the context nor the mouse's choice could be reliably decoded from the recorded neural activity. Our findings suggest that in spite of modulation of auditory cortical activity by task priors, auditory cortex does not represent sufficient information about these priors to exploit them optimally and that decisions in this task require that rapidly changing sensory information be combined with more slowly varying task information extracted and represented in brain regions other than auditory cortex.

Groupwise structural sparsity for discriminative voxels identification

This paper investigates the selection of voxels for functional Magnetic Resonance Imaging (fMRI) brain data. We aim to identify a comprehensive set of discriminative voxels associated with human learning when exposed to a neutral visual stimulus that predicts an aversive outcome. However, due to the nature of the unconditioned stimuli (typically a noxious stimulus), it is challenging to obtain sufficient sample sizes for psychological experiments, given the tolerability of the subjects and ethical considerations. We propose a stable hierarchical voting (SHV) mechanism based on stability selection to address this challenge. This mechanism enables us to evaluate the quality of spatial random sampling and minimizes the risk of false and missed detections. We assess the performance of the proposed algorithm using simulated and publicly available datasets. The experiments demonstrate that the regularization strategy choice significantly affects the results' interpretability. When applying our algorithm to our collected fMRI dataset, it successfully identifies sparse and closely related patterns across subjects and displays stable weight maps for three experimental phases under the fear conditioning paradigm. These findings strongly support the causal role of aversive conditioning in altering visual-cortical activity.

Predicting Responses to Electroconvulsive Therapy in Adolescents with Treatment-Refractory Depression Based on Resting-State fMRI

OBJECTS

The efficacy of electroconvulsive therapy (ECT) in the treatment of adolescents with treatment-refractory depression is still unsatisfactory, and the individual differences are large. It is not clear which factors are related to the treatment effect. Resting-state fMRI may be a good tool to predict the clinical efficacy of this treatment, and it is helpful to identify the most suitable population for this treatment.

METHODS

Forty treatment-refractory depression adolescents were treated by ECT and evaluated using HAMD and BSSI scores before and after treatment, and were then divided into a treatment response group and a non-treatment group according to the reduction rate of the HAMD scale. We extracted the ALFF, fALFF, ReHo, and functional connectivity of patients as predicted features after a two-sample t-test and LASSO to establish and evaluate a prediction model of ECT in adolescents with treatment-refractory depression.

RESULTS

Twenty-seven patients achieved a clinical response; symptoms of depression and suicidal ideation were significantly improved after treatment with ECT, which was reflected in a significant decrease in the scores of HAMD and BSSI (p < 0.001). The efficacy was predicted by ALFF, fALFF, ReHo, and whole-brain-based functional connectivity. We found that models built on a subset of features of ALFF in the left insula, fALFF in the left superior parietal gyrus, right superior parietal gyrus, and right angular, and functional connectivity between the left superior frontal gyrus, dorsolateral-right paracentral lobule, right middle frontal gyrus, orbital part-left cuneus, right olfactory cortex-left hippocampus, left insula-left thalamus, and left anterior cingulate gyrus-right hippocampus to have the best predictive performance (AUC > 0.8).

CONCLUSIONS

The local brain function in the insula, superior parietal gyrus, and angular gyrus as well as characteristic changes in the functional connectivity of cortical-limbic circuits may serve as potential markers for efficacy judgment of ECT and help to provide optimized individual treatment strategies for adolescents with depression and suicidal ideation in the early stages of treatment.

Pattern recognition reveals sex-dependent neural substrates of sexual perception

Sex differences in brain activity evoked by sexual stimuli remain elusive despite robust evidence for stronger enjoyment of and interest toward sexual stimuli in men than in women. To test whether visual sexual stimuli evoke different brain activity patterns in men and women, we measured hemodynamic brain activity induced by visual sexual stimuli in two experiments with 91 subjects (46 males). In one experiment, the subjects viewed sexual and nonsexual film clips, and dynamic annotations for nudity in the clips were used to predict hemodynamic activity. In the second experiment, the subjects viewed sexual and nonsexual pictures in an event-related design. Men showed stronger activation than women in the visual and prefrontal cortices and dorsal attention network in both experiments. Furthermore, using multivariate pattern classification we could accurately predict the sex of the subject on the basis of the brain activity elicited by the sexual stimuli. The classification generalized across the experiments indicating that the sex differences were task-independent. Eye tracking data obtained from an independent sample of subjects (N = 110) showed that men looked longer than women at the chest area of the nude female actors in the film clips. These results indicate that visual sexual stimuli evoke discernible brain activity patterns in men and women which may reflect stronger attentional engagement with sexual stimuli in men.

A systematic review on the potential use of machine learning to classify major depressive disorder from healthy controls using resting state fMRI measures

BACKGROUND

Major Depressive Disorder (MDD) is a psychiatric disorder characterized by functional brain deficits, as documented by resting-state functional magnetic resonance imaging (rs-fMRI) studies.

AIMS

In recent years, some studies used machine learning (ML) approaches, based on rs-fMRI features, for classifying MDD from healthy controls (HC). In this context, this review aims to provide a comprehensive overview of the results of these studies.

DESIGN

The studies research was performed on 3 online databases, examining English-written articles published before August 5, 2022, that performed a two-class ML classification using rs-fMRI features. The search resulted in 20 eligible studies.

RESULTS

The reviewed studies showed good performance metrics, with better performance achieved when the dataset was restricted to a more homogeneous group in terms of disease severity. Regions within the default mode network, salience network, and central executive network were reported as the most important features in the classification algorithms.

LIMITATIONS

The small sample size together with the methodological and clinical heterogeneity limited the generalizability of the findings.

CONCLUSIONS

In conclusion, ML applied to rs-fMRI features can be a valid approach to classify MDD and HC subjects and to discover features that can be used for additional investigation of the pathophysiology of the disease.

Whole-brain dynamical modelling for classification of Parkinson's disease

Simulated whole-brain connectomes demonstrate enhanced inter-individual variability depending on the data processing and modelling approach. By considering the human brain connectome as an individualized attribute, we investigate how empirical and simulated whole-brain connectome-derived features can be utilized to classify patients with Parkinson's disease against healthy controls in light of varying data processing and model validation. To this end, we applied simulated blood oxygenation level-dependent signals derived by a whole-brain dynamical model simulating electrical signals of neuronal populations to reveal differences between patients and controls. In addition to the widely used model validation via fitting the dynamical model to empirical neuroimaging data, we invented a model validation against behavioural data, such as subject classes, which we refer to as behavioural model fitting and show that it can be beneficial for Parkinsonian patient classification. Furthermore, the results of machine learning reported in this study also demonstrated that the performance of the patient classification can be improved when the empirical data are complemented by the simulation results. We also showed that the temporal filtering of blood oxygenation level-dependent signals influences the prediction results, where filtering in the low-frequency band is advisable for Parkinsonian patient classification. In addition, composing the feature space of empirical and simulated data from multiple brain parcellation schemes provided complementary features that improved prediction performance. Based on our findings, we suggest that combining the simulation results with empirical data is effective for inter-individual research and its clinical application.

Identifying and distinguishing of essential tremor and Parkinson's disease with grouped stability analysis based on searchlight-based MVPA

BACKGROUND

Since both essential tremor (ET) and Parkinson's disease (PD) are movement disorders and share similar clinical symptoms, it is very difficult to recognize the differences in the presentation, course, and treatment of ET and PD, which leads to misdiagnosed commonly.

PURPOSE

Although neuroimaging biomarker of ET and PD has been investigated based on statistical analysis, it is unable to assist the clinical diagnosis of ET and PD and ensure the efficiency of these biomarkers. The aim of the study was to identify the neuroimaging biomarkers of ET and PD based on structural magnetic resonance imaging (MRI). Moreover, the study also distinguished ET from PD via these biomarkers to validate their classification performance.

METHODS

This study has developed and implemented a three-level machine learning framework to identify and distinguish ET and PD. First of all, at the model-level assessment, the searchlight-based machine learning method has been used to identify the group differences of patients (ET/PD) with normal controls (NCs). And then, at the feature-level assessment, the stability of group differences has been tested based on structural brain atlas separately using the permutation test to identify the robust neuroimaging biomarkers. Furthermore, the identified biomarkers of ET and PD have been applied to classify ET from PD based on machine learning techniques. Finally, the identified biomarkers have been compared with the previous findings of the biology-level assessment.

RESULTS

According to the biomarkers identified by machine learning, this study has found widespread alterations of gray matter (GM) for ET and large overlap between ET and PD and achieved superior classification performance (PCA + SVM, accuracy = 100%).

CONCLUSIONS

This study has demonstrated the significance of a machine learning framework to identify and distinguish ET and PD. Future studies using a large data set are needed to confirm the potential clinical application of machine learning techniques to discern between PD and ET.

Prediction of violence in male schizophrenia using sMRI, based on machine learning algorithms

BACKGROUND

Violent behavior in patients with schizophrenia (SCZ) is a major social problem. The early identification of SCZ patients with violence can facilitate implementation of targeted intervention.

METHODS

A total of 57 male SCZ patients were recruited into this study. The general linear model was utilized to compare differences in structural magnetic resonance imaging (sMRI) including gray matter volume, cortical surface area, and cortical thickness between 30 SCZ patients who had exhibited violence and 27 SCZ patients without a history of violence. Based on machine learning algorithms, the different sMRI features between groups were integrated into the models for prediction of violence in SCZ patients.

RESULTS

After controlling for the whole brain volume and age, the general linear model showed significant reductions in right bankssts thickness, inferior parietal thickness as well as left frontal pole volume in the patients with SCZ and violence relative to those without violence. Among seven machine learning algorithms, Support Vector Machine (SVM) have better performance in differentiating patients with violence from those without violence, with its balanced accuracy and area under curve (AUC) reaching 0.8231 and 0.841, respectively.

CONCLUSIONS

Patients with SCZ who had a history of violence displayed reduced cortical thickness and volume in several brain regions. Based on machine learning algorithms, structural MRI features are useful to improve predictive ability of SCZ patients at particular risk of violence.

Selecting Multiple Node Statistics Jointly from Functional Connectivity Networks for Brain Disorders Identification

Functional connectivity networks (FCN) analysis is instructive for the diagnosis of brain diseases, such as mild cognitive impairment (MCI) and major depressive disorder (MDD) at their early stages. As the critical step of FCN analysis, feature representation provides the basis for finding potential biomarkers of brain diseases. In previous studies, different node statistics (e.g. local efficiency and local clustering coefficients) are usually extracted from FCNs as features for the diagnosis/classification task, which can specifically locate disease-related regions on the node level, so as to help us understand the neurodevelopmental roots of brain disorders. However, each node statistic is proposed only considering a kind of specific network property, which has one-sidedness and limitations. As a result, it is incomplete to represent a node with only one statistic. To resolve this issue, we put forward a novel scheme to select multiple node statistics jointly from the estimated FCNs for automated classification, called multiple node statistics feature selection (MNSFS). Specifically, we first extract multiple statistics from the same nodes and assign each kind of statistic into a group. Then, sparse group least absolute shrinkage and selection operator (sgLASSO) is used to select groups (nodes) and statistics in the groups towards a better classification performance. Such a technique enables us to simultaneously locate the discriminative brain regions, as well as the specific statistics associated with these brain regions, making the classification results more interpretable. We conducted our scheme on two public databases for identifying subjects with MCI and MDD from normal controls. Experimental results show that the proposed scheme achieves superior classification accuracy and features interpreted on the benchmark datasets.

Resting-state neural signal variability in women with depressive disorders

Aberrant activity and connectivity in default mode (DMN), frontoparietal (FPN), and salience (SN) network regions is well-documented in depression. Recent neuroimaging research suggests that altered variability in the blood oxygen level-dependent (BOLD) signal may disrupt normal network integration and be an important novel predictor of psychopathology. However, no studies have yet determined the relationship between resting-state BOLD signal variability and depressive disorders nor applied BOLD signal variability features to the classification of depression history using machine learning (ML). We collected resting-state fMRI data for 79 women with different depression histories: no history, past history, and current depressive disorder. We tested voxelwise differences in BOLD signal variability related to depression group and severity. We also investigated whether BOLD signal variability of DMN, FPN, and SN regions could predict depression history group using a supervised random forest ML model. Results indicated that individuals with any history of depression had significantly decreased BOLD signal variability in the left and right cerebellum and right parietal cortex (pFWE <0.05). Furthermore, greater depression severity was also associated with reduced BOLD signal variability in the cerebellum. A random forest model classified participant depression history with 74% accuracy, with the ventral anterior cingulate cortex of the DMN as the most important variable in the model. These findings provide novel support for resting-state BOLD signal variability as a marker of neural dysfunction in depression and implicate decreased neural signal variability in the pathophysiology of depression.

Resting-state functional connectivity does not predict individual differences in the effects of emotion on memory

Emotion-laden events and objects are typically better remembered than neutral ones. This is usually explained by stronger functional coupling in the brain evoked by emotional content. However, most research on this issue has focused on functional connectivity evoked during or after learning. The effect of an individual’s functional connectivity at rest is unknown. Our pre-registered study addresses this issue by analysing a large database, the Cambridge Centre for Ageing and Neuroscience, which includes resting-state data and emotional memory scores from 303 participants aged 18–87 years. We applied regularised regression to select the relevant connections and replicated previous findings that whole-brain resting-state functional connectivity can predict age and intelligence in younger adults. However, whole-brain functional connectivity predicted neither an emotional enhancement effect (i.e., the degree to which emotionally positive or negative events are remembered better than neutral events) nor a positivity bias effect (i.e., the degree to which emotionally positive events are remembered better than negative events), failing to support our pre-registered hypotheses. These results imply a small or no association between individual differences in functional connectivity at rest and emotional memory, and support recent notions that resting-state functional connectivity is not always useful in predicting individual differences in behavioural measures.

Autism detection based on multiple time scale model

OBJECTIVE

Current autism clinical detection relies on doctor observation and filling of clinical scales, which is subjective and easily misdetection. Existing autism research of functional magnetic resonance imaging (fMRI) over-compresses the time-scale information and has poor generalization ability. This study extracts multiple time scale brain features of fMRI, providing objective detection.

APPROACH

We first use least absolute shrinkage and selection operator (LASSO) to build a sparse network and extract features with a time scale of 1. Then, we use hidden markov model (HMM) to extract features that describe the dynamic changes of the brain, with a time scale of 2. Additionally, to analyze the features of the potential network activity of autism from a higher time scale, we use long short-term memory (LSTM) to construct an auto-encoder to re-encode the original data and extract the features of the at a higher time scale, with a time scale of T, and T is the time length of fMRI. We use Recursive Feature Elimination (RFE) for feature selection for three different time scale features, merge them into multiple time scale features, and finally use one-dimensional convolution neural network (1DCNN) for classification.

MAIN RESULTS

Compared with well-established models, our method has achieved better results. The accuracy of our method is 76.0%, and the area under the roc curve is 0.83, tested on the completely independent data, so our method has better generalization ability.

SIGNIFICANCE

This research analyzes fMRI sequences from multiple time scale to detect autism, and it also provides a new framework and research ideas for subsequent fMRI analysis.

Machine Learning on Early Diagnosis of Depression

To review the recent progress of machine learning for the early diagnosis of depression (major depressive disorder). The source of data was 32 original studies in the Web of Science. The search terms were "depression" (title) and "random forest" (abstract). The eligibility criteria were the dependent variable of depression, the interventions of machine learning (the decision tree, the naïve Bayesian, the random forest, the support vector machine and/or the artificial neural network), the outcomes of accuracy and/or the area under the receiver operating characteristic curve (AUC) for the early diagnosis of depression, the publication year of 2000 or later, the publication language of English and the publication journal of SCIE/SSCI. Different machine learning methods would be appropriate for different types of data for the early diagnosis of depression, e.g., logistic regression, the random forest, the support vector machine and/or the artificial neural network in the case of numeric data, the random forest in the case of genomic data. Their performance measures reported varied within 60.1-100.0 for accuracy and 64.0-96.0 for the AUC. Machine learning provides an effective, non-invasive decision support system for early diagnosis of depression.

An insight into diagnosis of depression using machine learning techniques: a systematic review

BACKGROUND

In this modern era, depression is one of the most prevalent mental disorders from which millions of individuals are affected today. The symptoms of depression are heterogeneous and often coincide with other disorders such as bipolar disorder, Parkinson's, schizophrenia, etc. It is a serious mental illness that may lead to other health problems if left untreated. Currently, identifying individuals with depression is totally based on the expertise of the clinician's experience. In order to assist clinicians in identifying the characteristics and classifying depressed people, different types of data modalities and machine learning techniques have been incorporated by researchers in this field. This study aims to find the answers to some important questions related to the trend of publications, data modality, machine learning models, dataset usage, pre-processing techniques and feature extraction and selection techniques that are prevalent and guide the direction of future research on depression diagnosis.

METHODS

This systematic review was conducted using a broad range of articles from two major databases: IEEE Xplore and PubMed. Studies ranging from the years 2011 to April 2021 were retrieved from the databases resulting in a total of 590 articles (53 articles from the IEEE Xplore database and 537 articles from the PubMed database). Out of those, the articles which satisfied the defined inclusion criteria were investigated for further analysis.

RESULTS

A total of 135 articles were identified and analysed for this review. High growth in the number of publications has been observed in recent years. Furthermore, significant diversity in the use of data modalities and machine learning classifiers has also been noted in this study. fMRI data with an SVM classifier was found to be the most popular choice among researchers. In most of the studies, data scarcity and small sample size, particularly for neuroimaging data are major concerns. The use of identical data pre-processing tools for similar data modalities can be seen. This study also provides statistical analysis of the current framework with respect to the modality, machine learning classifier, sample size and accuracy by applying one-way ANOVA and the Tukey - Kramer test.

CONCLUSION

The results indicate that an effective fusion of machine learning techniques with a potential data modality has a promising future for assisting clinicians in automatic depression diagnosis.

A neural network approach to optimising treatments for depression using data from specialist and community psychiatric services in Australia, New Zealand and Japan

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

CT classification model of pancreatic serous cystic neoplasms and mucinous cystic neoplasms based on a deep neural network

BACKGROUND

At present, numerous challenges exist in the diagnosis of pancreatic SCNs and MCNs. After the emergence of artificial intelligence (AI), many radiomics research methods have been applied to the identification of pancreatic SCNs and MCNs.

PURPOSE

A deep neural network (DNN) model termed Multi-channel-Multiclassifier-Random Forest-ResNet (MMRF-ResNet) was constructed to provide an objective CT imaging basis for differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs).

MATERIALS AND METHODS

This study is a retrospective analysis of pancreatic unenhanced and enhanced CT images in 63 patients with pancreatic SCNs and 47 patients with MCNs (3 of which were mucinous cystadenocarcinoma) confirmed by pathology from December 2010 to August 2016. Different image segmented methods (single-channel manual outline ROI image and multi-channel image), feature extraction methods (wavelet, LBP, HOG, GLCM, Gabor, ResNet, and AlexNet) and classifiers (KNN, Softmax, Bayes, random forest classifier, and Majority Voting rule method) are used to classify the nature of the lesion in each CT image (SCNs/MCNs). Then, the comparisons of classification results were made based on sensitivity, specificity, precision, accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), with pathological results serving as the gold standard.

RESULTS

Multi-channel-ResNet (AUC 0.98) was superior to Manual-ResNet (AUC 0.91).CT image characteristics of lesions extracted by ResNet are more representative than wavelet, LBP, HOG, GLCM, Gabor, and AlexNet. Compared to the use of three classifiers alone and Majority Voting rule method, the use of the MMRF-ResNet model exhibits a better evaluation effect (AUC 0.96) for the classification of the pancreatic SCNs and MCNs.

CONCLUSION

The CT image classification model MMRF-ResNet is an effective method to distinguish between pancreatic SCNs and MCNs.

Effect of SSRIs on Resting-State Functional Brain Networks in Adolescents with Major Depressive Disorder

Investigation of brain changes in functional connectivity and functional network topology from receiving 8-week selective serotonin reuptake inhibitor (SSRI) treatments is conducted in 12 unmedicated adolescents with major depressive disorder (MDD) by using wavelet-filtered resting-state functional magnetic resonance imaging (fMRI). Changes are observed in frontal-limbic, temporal, and default mode networks. In particular, topological analysis shows, at the global scale and in the 0.12–0.25 Hz band, that the normalized clustering coefficient and smallworldness of brain networks decreased after treatment. Regional changes in clustering coefficient and efficiency were observed in the bilateral caudal middle frontal gyrus, rostral middle frontal gyrus, superior temporal gyrus, left pars triangularis, putamen, and right superior frontal gyrus. Furthermore, changes of nodal centrality and changes of connectivity associated with these frontal and temporal regions confirm the global topological alternations. Moreover, frequency dependence is observed from FDR-controlled subnetworks for the limbic-cortical connectivity change. In the high-frequency band, the altered connections involve mostly frontal regions, while the altered connections in the low-frequency bands spread to parietal and temporal areas. Due to the limitation of small sample sizes and lack of placebo control, these preliminary findings require confirmation with future work using larger samples. Confirmation of biomarkers associated with treatment could suggest potential avenues for clinical applications such as tracking treatment response and neurobiologically informed treatment optimization.

Identifying behavioral types of dietary lapse from a mobile weight loss program: Preliminary investigation from a secondary data analysis

Success in behavioral weight loss (BWL) programs depends on adherence to the recommended diet to reduce caloric intake. Dietary lapses (i.e., deviations from the BWL diet) occur frequently and can adversely affect weight loss outcomes. Research indicates that lapse behavior is heterogenous; there are many eating behaviors that could constitute a dietary lapse, but they are rarely studied as distinct contributors to weight outcomes. This secondary analysis aims to evaluate six behavioral lapse types during a 10-week mobile BWL program (eating a large portion, eating when not intended, eating an off-plan food, planned lapse, being unaware of caloric content, and endorsing multiple types of lapse). Associations between weekly behavioral lapse type frequency and weekly weight loss were investigated, and predictive contextual characteristics (psychological, behavioral, and environmental triggers for lapse) and individual difference (e.g., age, gender) factors were examined across lapse types. Participants (N = 121) with overweight/obesity (M_BMI = 34.51; 84.3% female; 69.4% White) used a mobile BWL program for 10 weeks, self-weighed weekly using Bluetooth scales, completed daily ecological momentary assessment of lapse behavior and contextual characteristics, and completed a baseline demographics questionnaire. Linear mixed models revealed significant negative associations between unplanned lapses and percent weight loss. Unplanned lapses from eating a large portion, eating when not intended, and having multiple "types" were significantly negatively associated with weekly percent weight loss. A lasso regression showed that behavioral lapse types share many similar stable factors, with other factors being unique to specific lapse types. Results add to the prior literature on lapses and weight loss in BWL and provide preliminary evidence that behavioral lapse types could aid in understanding adherence behavior and developing precision medicine tools to improve dietary adherence.

Clustering of Multiple Psychiatric Disorders Using Functional Connectivity in the Data-Driven Brain Subnetwork

Recently, the dimensional approach has attracted much attention, bringing a paradigm shift to a continuum of understanding of different psychiatric disorders. In line with this new paradigm, we examined whether there was common functional connectivity related to various psychiatric disorders in an unsupervised manner without explicitly using diagnostic label information. To this end, we uniquely applied a newly developed network-based multiple clustering method to resting-state functional connectivity data, which allowed us to identify pairs of relevant brain subnetworks and subject cluster solutions accordingly. Thus, we identified four subject clusters, which were characterized as major depressive disorder (MDD), young healthy control (young HC), schizophrenia (SCZ)/bipolar disorder (BD), and autism spectrum disorder (ASD), respectively, with the relevant brain subnetwork represented by the cerebellum-thalamus-pallidum-temporal circuit. The clustering results were validated using independent datasets. This study is the first cross-disorder analysis in the framework of unsupervised learning of functional connectivity based on a data-driven brain subnetwork.

The psychology of professional and student actors: Creativity, personality, and motivation

As a profession, acting is marked by a high-level of economic and social riskiness concomitantly with the possibility for artistic satisfaction and/or public admiration. Current understanding of the psychological attributes that distinguish professional actors is incomplete. Here, we compare samples of professional actors (n = 104), undergraduate student actors (n = 100), and non-acting adults (n = 92) on 26 psychological dimensions and use machine-learning methods to classify participants based on these attributes. Nearly all of the attributes measured here displayed significant univariate mean differences across the three groups, with the strongest effect sizes being on Creative Activities, Openness, and Extraversion. A cross-validated Least Absolute Shrinkage and Selection Operator (LASSO) classification model was capable of identifying actors (either professional or student) from non-actors with a 92% accuracy and was able to sort professional from student actors with a 96% accuracy when age was included in the model, and a 68% accuracy with only psychological attributes included. In these LASSO models, actors in general were distinguished by high levels of Openness, Assertiveness, and Elaboration, but professional actors were specifically marked by high levels of Originality, Volatility, and Literary Activities.

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 heuristic information cluster search approach for precise functional brain mapping

Detection of the relevant brain regions for characterizing the distinction between cognitive conditions is one of the most sought after objectives in neuroimaging research. A popular approach for achieving this goal is the multivariate pattern analysis which is currently conducted through a number of approaches such as the popular searchlight procedure. This is due to several advantages such as being automatic and flexible with regards to size of the search region. However, these approaches suffer from a number of limitations which can lead to misidentification of truly informative regions which in turn results in imprecise information maps. These limitations mainly stem from several factors such as the fact that the information value of the search spheres are assigned to the voxel at the center of them (in case of searchlight), the requirement for manual tuning of parameters such as searchlight radius and shape, and high complexity and low interpretability in commonly used machine learning-based approaches. Other drawbacks include overlooking the structure and interactions within the regions, and the disadvantages of using certain regularization techniques in analysis of datasets with characteristics of common functional magnetic resonance imaging data. In this article, we propose a fully data-driven maximum relevance minimum redundancy search algorithm for detecting precise information value of the clusters within brain regions while alleviating the above-mentioned limitations. Moreover, in order to make the proposed method faster, we propose an efficient algorithmic implementation. We evaluate and compare the proposed algorithm with the searchlight procedure as well as least absolute shrinkage and selection operator regularization-based mapping approach using both real and synthetic datasets. The analysis results of the proposed approach demonstrate higher information detection precision and map specificity compared to the benchmark approaches.

Enhancing Multi-Center Generalization of Machine Learning-Based Depression Diagnosis From Resting-State fMRI

Resting-state fMRI has the potential to help doctors detect abnormal behavior in brain activity and to diagnose patients with depression. However, resting-state fMRI has a bias depending on the scanner site, which makes it difficult to diagnose depression at a new site. In this paper, we propose methods to improve the performance of the diagnosis of major depressive disorder (MDD) at an independent site by reducing the site bias effects using regression. For this, we used a subgroup of healthy subjects of the independent site to regress out site bias. We further improved the classification performance of patients with depression by focusing on melancholic depressive disorder. Our proposed methods would be useful to apply depression classifiers to subjects at completely new sites.

Multimodal Depression Detection: Fusion of Electroencephalography and Paralinguistic Behaviors Using a Novel Strategy for Classifier Ensemble

Currently, depression has become a common mental disorder and one of the main causes of disability worldwide. Due to the difference in depressive symptoms evoked by individual differences, how to design comprehensive and effective depression detection methods has become an urgent demand. This study explored from physiological and behavioral perspectives simultaneously and fused pervasive electroencephalography (EEG) and vocal signals to make the detection of depression more objective, effective and convenient. After extraction of several effective features for these two types of signals, we trained six representational classifiers on each modality, then denoted diversity and correlation of decisions from different classifiers using co-decision tensor and combined these decisions into the ultimate classification result with multi-agent strategy. Experimental results on 170 (81 depressed patients and 89 normal controls) subjects showed that the proposed multi-modal depression detection strategy is superior to the single-modal classifiers or other typical late fusion strategies in accuracy, f1-score and sensitivity. This work indicates that late fusion of pervasive physiological and behavioral signals is promising for depression detection and the multi-agent strategy can take advantage of diversity and correlation of different classifiers effectively to gain a better final decision.

Incorporating prior information with fused sparse group lasso: Application to prediction of clinical measures from neuroimages

Predicting clinical variables from whole-brain neuroimages is a high-dimensional problem that can potentially benefit from feature selection or extraction. Penalized regression is a popular embedded feature selection method for high-dimensional data. For neuroimaging applications, spatial regularization using the ℓ 1 or ℓ 2 norm of the image gradient has shown good performance, yielding smooth solutions in spatially contiguous brain regions. Enormous resources have been devoted to establishing structural and functional brain connectivity networks that can be used to define spatially distributed yet related groups of voxels. We propose using the fused sparse group lasso (FSGL) penalty to encourage structured, sparse, and interpretable solutions by incorporating prior information about spatial and group structure among voxels. We present optimization steps for FSGL penalized regression using the alternating direction method of multipliers algorithm. With simulation studies and in application to real functional magnetic resonance imaging data from the Autism Brain Imaging Data Exchange, we demonstrate conditions under which fusion and group penalty terms together outperform either of them alone.

Effectiveness of imaging genetics analysis to explain degree of depression in Parkinson's disease

Depression is one of the most common and important neuropsychiatric symptoms in Parkinson's disease and often becomes worse as Parkinson's disease progresses. However, the underlying mechanisms of depression in Parkinson's disease are not clear. The aim of our study was to find genetic features related to depression in Parkinson's disease using an imaging genetics approach and to construct an analytical model for predicting the degree of depression in Parkinson's disease. The neuroimaging and genotyping data were obtained from an openly accessible database. We computed imaging features through connectivity analysis derived from tractography of diffusion tensor imaging. The imaging features were used as intermediate phenotypes to identify genetic variants according to the imaging genetics approach. We then constructed a linear regression model using the genetic features from imaging genetics approach to describe clinical scores indicating the degree of depression. As a comparison, we constructed other models using imaging features and genetic features based on references to demonstrate the effectiveness of our imaging genetics model. The models were trained and tested in a five-fold cross-validation. The imaging genetics approach identified several brain regions and genes known to be involved in depression, with the potential to be used as meaningful biomarkers. Our proposed model using imaging genetic features predicted and explained the degree of depression in Parkinson's disease appropriately (adjusted R2 larger than 0.6 over five training folds) and with a lower error and higher correlation than with other models over five test folds.

Cortical thickness in major depressive disorder: A systematic review and meta-analysis

Neuroimaging studies assessing neurobiological differences between patients with major depressive disorder (MDD) and healthy controls (HC) are often hindered by small sample sizes and heterogeneity of the patient sample. We performed a comprehensive literature search for studies assessing cortical thickness between patient and control groups, including studies investigating treatment effects on cortical thickness. We identified 34 studies meeting criteria for the systematic review and used Seed-based d Mapping to meta-analyze 24 of those that met additional criteria. Analysis of the full sample of subjects (MDD = 1073; HC = 936) revealed significant thinning in the MDD group in the bilateral orbitofrontal gyrus (BA 11), left pars opercularis (BA 45) and left calcarine fissure/lingual gyrus (BA 17), as well as an area of significant thickening in the left supramarginal gyrus (BA 40). These results support other imaging modalities that report disruptions in various frontal and temporal areas in MDD and identify additional areas in all major cerebral lobes likely to be significant when parsing for biomarkers of treatment or relapse.

Network changes associated with transdiagnostic depressive symptom improvement following cognitive behavioral therapy in MDD and PTSD

Despite widespread use of cognitive behavioral therapy (CBT) in clinical practice, its mechanisms with respect to brain networks remain sparsely described. In this study, we applied tools from graph theory and network science to better understand the transdiagnostic neural mechanisms of this treatment for depression. A sample of 64 subjects was included in a study of network dynamics: 33 patients (15 MDD, 18 PTSD) received longitudinal fMRI resting state scans before and after 12 weeks of CBT. Depression severity was rated on the Montgomery-Asberg Depression Rating Scale (MADRS). Thirty-one healthy controls were included to determine baseline network roles. Univariate and multivariate regression analyses were conducted on the normalized change scores of within- and between-system connectivity and normalized change score of the MADRS. Penalized regression was used to select a sparse set of predictors in a data-driven manner. Univariate analyses showed greater symptom reduction was associated with an increased functional role of the Ventral Attention (VA) system as an incohesive provincial system (decreased between- and decreased within-system connectivity). Multivariate analyses selected between-system connectivity of the VA system as the most prominent feature associated with depression improvement. Observed VA system changes are interesting in light of brain controllability descriptions: attentional control systems, including the VA system, fall on the boundary between-network communities, and facilitate integration or segregation of diverse cognitive systems. Thus, increasing segregation of the VA system following CBT (decreased between-network connectivity) may result in less contribution of emotional attention to cognitive processes, thereby potentially improving cognitive control.

Identification of depression subtypes and relevant brain regions using a data-driven approach

It is well known that depressive disorder is heterogeneous, yet little is known about its neurophysiological subtypes. In the present study, we identified neurophysiological subtypes of depression related to specific neural substrates. We performed cluster analysis for 134 subjects (67 depressive subjects and 67 controls) using a high-dimensional dataset consisting of resting state functional connectivity measured by functional MRI, clinical questionnaire scores, and various biomarkers. Applying a newly developed, multiple co-clustering method to this dataset, we identified three subtypes of depression that are characterized by functional connectivity between the right Angular Gyrus (AG) and other brain areas in default mode networks, and Child Abuse Trauma Scale (CATS) scores. These subtypes are also related to Selective Serotonin-Reuptake Inhibitor (SSRI) treatment outcomes, which implies that we may be able to predict effectiveness of treatment based on AG-related functional connectivity and CATS.

Machine learning in major depression: From classification to treatment outcome prediction

AIMS

Major depression disorder (MDD) is the single greatest cause of disability and morbidity, and affects about 10% of the population worldwide. Currently, there are no clinically useful diagnostic biomarkers that are able to confirm a diagnosis of MDD from bipolar disorder (BD) in the early depressive episode. Therefore, exploring translational biomarkers of mood disorders based on machine learning is in pressing need, though it is challenging, but with great potential to improve our understanding of these disorders.

DISCUSSIONS

In this study, we review popular machine-learning methods used for brain imaging classification and predictions, and provide an overview of studies, specifically for MDD, that have used magnetic resonance imaging data to either (a) classify MDDs from controls or other mood disorders or (b) investigate treatment outcome predictors for individual patients. Finally, challenges, future directions, and potential limitations related to MDD biomarker identification are also discussed, with a goal of offering a comprehensive overview that may help readers to better understand the applications of neuroimaging data mining in depression.

CONCLUSIONS

We hope such efforts may highlight the need for an urgently needed paradigm shift in treatment, to guide personalized optimal clinical care.

Resting-State Brain Functional Hyper-Network Construction Based on Elastic Net and Group Lasso Methods

Brain network analysis has been widely applied in neuroimaging studies. A hyper-network construction method was previously proposed to characterize the high-order relationships among multiple brain regions, where every edge is connected to more than two brain regions and can be represented by a hyper-graph. A brain functional hyper-network is constructed by a sparse linear regression model using resting-state functional magnetic resonance imaging (fMRI) time series, which in previous studies has been solved by the lasso method. Despite its successful application in many studies, the lasso method has some limitations, including an inability to explain the grouping effect. That is, using the lasso method may cause relevant brain regions be missed in selecting related regions. Ideally, a hyper-edge construction method should be able to select interacting brain regions as accurately as possible. To solve this problem, we took into account the grouping effect among brain regions and proposed two methods to improve the construction of the hyper-network: the elastic net and the group lasso. The three methods were applied to the construction of functional hyper-networks in depressed patients and normal controls. The results showed structural differences among the hyper-networks constructed by the three methods. The hyper-network structure obtained by the lasso was similar to that obtained by the elastic net method but very different from that obtained by the group lasso. The classification results indicated that the elastic net method achieved better classification results than the lasso method with the two proposed methods of hyper-network construction. The elastic net method can effectively solve the grouping effect and achieve better classification performance.

Cortical folding alterations in fetuses with isolated non-severe ventriculomegaly

Neuroimaging of brain diseases plays a crucial role in understanding brain abnormalities and early diagnosis. Of great importance is the study of brain abnormalities in utero and the assessment of deviations in case of maldevelopment. In this work, brain magnetic resonance images from 23 isolated non-severe ventriculomegaly (INSVM) fetuses and 25 healthy controls between 26 and 29 gestational weeks were used to identify INSVM-related cortical folding deviations from normative development. Since these alterations may reflect abnormal neurodevelopment, our working hypothesis is that markers of cortical folding can provide cues to improve the prediction of later neurodevelopmental problems in INSVM subjects. We analyzed the relationship of ventricular enlargement with cortical folding alterations in a regional basis using several curvature-based measures describing the folding of each cortical region. Statistical analysis (global and hemispheric) and sparse linear regression approaches were then used to find the cortical regions whose folding is associated with ventricular dilation. Results from both approaches were in great accordance, showing a significant cortical folding decrease in the insula, posterior part of the temporal lobe and occipital lobe. Moreover, compared to the global analysis, stronger ipsilateral associations of ventricular enlargement with reduced cortical folding were encountered by the hemispheric analysis. Our findings confirm and extend previous studies by identifying various cortical regions and emphasizing ipsilateral effects of ventricular enlargement in altered folding. This suggests that INSVM is an indicator of altered cortical development, and moreover, cortical regions with reduced folding constitute potential prognostic biomarkers to be used in follow-up studies to decipher the outcome of INSVM fetuses.

Imaging and Genetic Biomarkers Predicting Transition to Psychosis

The search for diagnostic and prognostic biomarkers in schizophrenia care and treatment is the focus of many within the research community. Longitudinal cohorts of patients presenting at elevated genetic and clinical risk have provided a wealth of data that has informed our understanding of the development of schizophrenia and related psychotic disorders.Imaging follow-up of high-risk cohorts has demonstrated changes in cerebral grey matter of those that eventually transition to schizophrenia that predate the onset of symptoms and evolve over the course of illness. Longitudinal follow-up studies demonstrate that observed grey matter changes can be employed to differentiate those who will transition to schizophrenia from those who will not prior to the onset of the disorder.In recent years our understanding of the genetic makeup of schizophrenia has advanced significantly. The development of modern analysis techniques offers researchers the ability to objectively quantify genetic risk; these have been successfully applied within a high-risk paradigm to assist in differentiating between high-risk individuals who will subsequently become unwell and those who will not.This chapter will discuss the application of imaging and genetic biomarkers within high-risk groups to predict future transition to schizophrenia and related psychotic disorders. We aim to provide an overview of current approaches focussing on grey matter changes that are predictive of future transition to illness, the developing field of genetic risk scores and other methods being developed to aid clinicians in diagnosis and prognosis.

Model selection and prediction of outcomes in recent onset schizophrenia patients who undergo cognitive training

Predicting treatment outcomes in psychiatric populations remains a challenge, but is increasingly important in the pursuit of personalized medicine. Patients with schizophrenia have deficits in cognition, and targeted cognitive training (TCT) of auditory processing and working memory has been shown to improve some of these impairments; but little is known about the baseline patient characteristics predictive of cognitive improvement. Here we use a model selection and regression approach called least absolute shrinkage and selection operator (LASSO) to examine predictors of cognitive improvement in response to TCT for patients with recent onset schizophrenia. Forty-three individuals with recent onset schizophrenia randomized to undergo TCT were assessed at baseline on measures of cognition, symptoms, functioning, illness duration, and demographic variables. We carried out 10-fold cross-validation of LASSO for model selection and regression. We followed up on these results using linear models for statistical inference. No individual variable was found to correlate with improvement in global cognition using a Pearson correlation approach, and a linear model including all variables was also found not to be significant. However, the LASSO model identified baseline global cognition, education, and gender in a model predictive of improvement on global cognition following TCT. These findings offer guidelines for personalized approaches to cognitive training for patients with schizophrenia.

Detecting Neuroimaging Biomarkers for Depression: A Meta-analysis of Multivariate Pattern Recognition Studies

BACKGROUND

Multiple studies have examined functional and structural brain alteration in patients diagnosed with major depressive disorder (MDD). The introduction of multivariate statistical methods allows investigators to utilize data concerning these brain alterations to generate diagnostic models that accurately differentiate patients with MDD from healthy control subjects (HCs). However, there is substantial heterogeneity in the reported results, the methodological approaches, and the clinical characteristics of participants in these studies.

METHODS

We conducted a meta-analysis of all studies using neuroimaging (volumetric measures derived from T1-weighted images, task-based functional magnetic resonance imaging [MRI], resting-state MRI, or diffusion tensor imaging) in combination with multivariate statistical methods to differentiate patients diagnosed with MDD from HCs.

RESULTS

Thirty-three (k = 33) samples including 912 patients with MDD and 894 HCs were included in the meta-analysis. Across all studies, patients with MDD were separated from HCs with 77% sensitivity and 78% specificity. Classification based on resting-state MRI (85% sensitivity, 83% specificity) and on diffusion tensor imaging data (88% sensitivity, 92% specificity) outperformed classifications based on structural MRI (70% sensitivity, 71% specificity) and task-based functional MRI (74% sensitivity, 77% specificity).

CONCLUSIONS

Our results demonstrate the high representational capacity of multivariate statistical methods to identify neuroimaging-based biomarkers of depression. Future studies are needed to elucidate whether multivariate neuroimaging analysis has the potential to generate clinically useful tools for the differential diagnosis of affective disorders and the prediction of both treatment response and functional outcome.

Prediction of clinical depression scores and detection of changes in whole-brain using resting-state functional MRI data with partial least squares regression

In diagnostic applications of statistical machine learning methods to brain imaging data, common problems include data high-dimensionality and co-linearity, which often cause over-fitting and instability. To overcome these problems, we applied partial least squares (PLS) regression to resting-state functional magnetic resonance imaging (rs-fMRI) data, creating a low-dimensional representation that relates symptoms to brain activity and that predicts clinical measures. Our experimental results, based upon data from clinically depressed patients and healthy controls, demonstrated that PLS and its kernel variants provided significantly better prediction of clinical measures than ordinary linear regression. Subsequent classification using predicted clinical scores distinguished depressed patients from healthy controls with 80% accuracy. Moreover, loading vectors for latent variables enabled us to identify brain regions relevant to depression, including the default mode network, the right superior frontal gyrus, and the superior motor area.

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

Neuroimaging-based single subject prediction of brain disorders has gained increasing attention in recent years. Using a variety of neuroimaging modalities such as structural, functional and diffusion MRI, along with machine learning techniques, hundreds of studies have been carried out for accurate classification of patients with heterogeneous mental and neurodegenerative disorders such as schizophrenia and Alzheimer's disease. More than 500 studies have been published during the past quarter century on single subject prediction focused on a multiple brain disorders. In the first part of this study, we provide a survey of more than 200 reports in this field with a focus on schizophrenia, mild cognitive impairment (MCI), Alzheimer's disease (AD), depressive disorders, autism spectrum disease (ASD) and attention-deficit hyperactivity disorder (ADHD). Detailed information about those studies such as sample size, type and number of extracted features and reported accuracy are summarized and discussed. To our knowledge, this is by far the most comprehensive review of neuroimaging-based single subject prediction of brain disorders. In the second part, we present our opinion on major pitfalls of those studies from a machine learning point of view. Common biases are discussed and suggestions are provided. Moreover, emerging trends such as decentralized data sharing, multimodal brain imaging, differential diagnosis, disease subtype classification and deep learning are also discussed. Based on this survey, there is extensive evidence showing the great potential of neuroimaging data for single subject prediction of various disorders. However, the main bottleneck of this exciting field is still the limited sample size, which could be potentially addressed by modern data sharing models such as the ones discussed in this paper. Emerging big data technologies and advanced data-intensive machine learning methodologies such as deep learning have coincided with an increasing need for accurate, robust and generalizable single subject prediction of brain disorders during an exciting time. In this report, we survey the past and offer some opinions regarding the road ahead.

Cognitive behavioral therapy changes functional connectivity between medial prefrontal and anterior cingulate cortices

BACKGROUND

Depression is characterized by negative self-cognition. Our previous study (Yoshimura et al. 2014) revealed changes in brain activity after cognitive behavioral therapy (CBT) for depression, but changes in functional connectivity were not assessed.

METHOD

This study included 29 depressive patients and 15 healthy control participants. Functional Magnetic Resonance Imaging was used to investigate possible CBT-related functional connectivity changes associated with negative emotional self-referential processing. Depressed and healthy participants (overlapping with our previous study, Yoshimura et al. 2014) were included. We defined a seed region (medial prefrontal cortex) and coupled region (ACC) based on our previous study, and we examined changes in MPFC-ACC functional connectivity from pretreatment to posttreatment.

RESULTS

CBT was associated with reduced functional connectivity between the MPFC and ACC. Symptom change with CBT was positively correlated with change in MPFC-ACC functional connectivity.

LIMITATIONS

Patients received pharmacotherapy including antidepressant. The present sample size was quite small and more study is needed. Statistical threshold in fMRI analysis was relatively liberal.

CONCLUSIONS

CBT for depression may disrupt MPFC-ACC connectivity, with associated improvements in depressive symptoms and dysfunctional cognition.

Guidelines for Developing and Reporting Machine Learning Predictive Models in Biomedical Research: A Multidisciplinary View

Background

As more and more researchers are turning to big data for new opportunities of biomedical discoveries, machine learning models, as the backbone of big data analysis, are mentioned more often in biomedical journals. However, owing to the inherent complexity of machine learning methods, they are prone to misuse. Because of the flexibility in specifying machine learning models, the results are often insufficiently reported in research articles, hindering reliable assessment of model validity and consistent interpretation of model outputs.

Objective

To attain a set of guidelines on the use of machine learning predictive models within clinical settings to make sure the models are correctly applied and sufficiently reported so that true discoveries can be distinguished from random coincidence.

Methods

A multidisciplinary panel of machine learning experts, clinicians, and traditional statisticians were interviewed, using an iterative process in accordance with the Delphi method.

Results

The process produced a set of guidelines that consists of (1) a list of reporting items to be included in a research article and (2) a set of practical sequential steps for developing predictive models.

Conclusions

A set of guidelines was generated to enable correct application of machine learning models and consistent reporting of model specifications and results in biomedical research. We believe that such guidelines will accelerate the adoption of big data analysis, particularly with machine learning methods, in the biomedical research community.

Factors associated with performing tuberculosis screening of HIV-positive patients in Ghana: LASSO-based predictor selection in a large public health data set

Background

The purpose of this study is to propose the Least Absolute Shrinkage and Selection Operators procedure (LASSO) as an alternative to conventional variable selection models, as it allows for easy interpretation and handles multicollinearities. We developed a model on the basis of LASSO-selected parameters in order to link associated demographical, socio-economical, clinical and immunological factors to performing tuberculosis screening in HIV-positive patients in Ghana.

Methods

Applying the LASSO method and multivariate logistic regression analysis on a large public health data set, we selected relevant predictors related to tuberculosis screening.

Results

One Thousand Ninety Five patients infected with HIV were enrolled into this study with 691 (63.2 %) of them having tuberculosis screening documented in their patient folders. Predictors found to be significantly associated with performance of tuberculosis screening can be classified into factors related to the clinician’s perception of the clinical state, as well as those related to PLHIV’s awareness. These factors include newly diagnosed HIV infections (n = 354 (32.42 %), aOR 1.84), current CD4+ T cell count (aOR 0.92), non-availability of HIV type (n = 787 (72.07 %), aOR 0.56), chronic cough (n = 32 (2.93 %), aOR 5.07), intake of co-trimoxazole (n = 271 (24.82 %), aOR 2.31), vitamin supplementation (n = 220 (20.15 %), aOR 2.64) as well as the use of mosquito bed nets (n = 613 (56.14 %), aOR 1.53).

Conclusions

Accelerated TB screening among newly diagnosed HIV-patients indicates that application of the WHO screening form for intensifying tuberculosis case finding among HIV-positive individuals in resource-limited settings is increasingly adopted. However, screening for TB in PLHIV is still impacted by clinician’s perception of patient’s health state and PLHIV’s health awareness. Education of staff, counselling of PLHIV and sufficient financing are needed for further improvement in implementation of TB screening for all PLHIV. The LASSO approach proved a convenient method for automatic variable selection in a large public health data set that requires efficient and fast algorithms.

Trials registration

ClinicalTrials.gov NCT01897909 (July 5, 2013).