Complexity in mood disorder diagnosis: fMRI connectivity networks predicted medication-class of response in complex patients

Identifying misdiagnosed bipolar disorder using support vector machine: feature selection based on fMRI of follow-up confirmed affective disorders

Nearly a quarter of bipolar disorder (BD) patients were misdiagnosed as major depressive disorder (MDD) patients, which cannot be corrected until mania/hypomania develops. It is important to recognize these obstacles so that the appropriate treatment can be initiated. Thus, we sought to distinguish patients with BD from MDD, especially to identify misdiagnosed BD before mania/hypomania, and further explore potential trait features that allow accurate differential diagnosis independent of state matters. Functional magnetic resonance imaging scans were performed at baseline on 92 MDD patients and 48 BD patients. The MDD patients were then followed up for more than two years. After follow-up, 23 patients transformed into BD (tBD), and 69 patients whose diagnoses remained unchanged were eligible for unipolar depression (UD). A support vector machine classifier was trained on the amygdala-based functional connectivity (FC) of 48 BD and 50 UD patients using a novel region-based feature selection. Then, the classifier was tested on the dataset, encompassing tBD and the remaining UD. It performed well for known BD and UD and can also distinguish tBD from UD with an accuracy of 81%, sensitivity of 82.6%, specificity of 79%, and AUC of 74.6%, respectively. Feature selection results revealed that ten regions within the cortico-limbic neural circuit contributed most to classification. Furthermore, in the FC comparisons among diseases, BD and tBD shared almost overlapped FC patterns in the cortico-limbic neural circuit, and both of them presented pronounced differences in most regions within the circuit compared with UD. The FC values of the most discriminating brain regions had no prominent correlations with the severity of depression, anxiety, and mania/hypomania (FDR correction). It suggests that BD possesses some trait features in the cortico-limbic neural circuit, rendering it dichotomized by the classifier based on known-diagnosis data.

Aberrant brain dynamics and spectral power in children with ADHD and its subtypes

Attention-deficit/hyperactivity disorder (ADHD) is a prevalent neurodevelopmental disorder in children, usually categorized as three subtypes, predominant inattention (ADHD-I), predominant hyperactivity-impulsivity (ADHD-HI), and a combined subtype (ADHD-C). Yet, common and unique abnormalities of electroencephalogram (EEG) across different subtypes remain poorly understood. Here, we leveraged microstate characteristics and power features to investigate temporal and frequency abnormalities in ADHD and its subtypes using high-density EEG on 161 participants (54 ADHD-Is and 53 ADHD-Cs and 54 healthy controls). Four EEG microstates were identified. The coverage of salience network (state C) were decreased in ADHD compared to HC (p = 1.46e-3), while the duration and contribution of frontal-parietal network (state D) were increased (p = 1.57e-3; p = 1.26e-4). Frequency power analysis also indicated that higher delta power in the fronto-central area (p = 6.75e-4) and higher power of theta/beta ratio in the bilateral fronto-temporal area (p = 3.05e-3) were observed in ADHD. By contrast, remarkable subtype differences were found primarily on the visual network (state B), of which ADHD-C have higher occurrence and coverage than ADHD-I (p = 9.35e-5; p = 1.51e-8), suggesting that children with ADHD-C might exhibit impulsivity of opening their eyes in an eye-closed experiment, leading to hyper-activated visual network. Moreover, the top discriminative features selected from support vector machine model with recursive feature elimination (SVM-RFE) well replicated the above results, which achieved an accuracy of 72.7% and 73.8% separately in classifying ADHD and two subtypes. To conclude, this study highlights EEG microstate dynamics and frequency features may serve as sensitive measurements to detect the subtle differences in ADHD and its subtypes, providing a new window for better diagnosis of ADHD.

Multi-study evaluation of neuroimaging-based prediction of medication class in mood disorders

Clinicians often face a dilemma in diagnosing bipolar disorder patients with complex symptoms who spend more time in a depressive state than a manic state. The current gold standard for such diagnosis, the Diagnostic and Statistical Manual (DSM), is not objectively grounded in pathophysiology. In such complex cases, relying solely on the DSM may result in misdiagnosis as major depressive disorder (MDD). A biologically-based classification algorithm that can accurately predict treatment response may help patients suffering from mood disorders. Here we used an algorithm to do so using neuroimaging data. We used the neuromark framework to learn a kernel function for support vector machine (SVM) on multiple feature subspaces. The neuromark framework achieves up to 95.45% accuracy, 0.90 sensitivity, and 0.92 specificity in predicting antidepressant (AD) vs. mood stabilizer (MS) response in patients. We incorporated two additional datasets to evaluate the generalizability of our approach. The trained algorithm achieved up to 89% accuracy, 0.88 sensitivity, and 0.89 specificity in predicting the DSM-based diagnosis on these datasets. We also translated the model to distinguish responders to treatment from nonresponders with up to 70% accuracy. This approach reveals multiple salient biomarkers of medication-class of response within mood disorders.

Multi-scale convolutional recurrent neural network for psychiatric disorder identification in resting-state EEG

Background

Accurate classification based on affordable objective neuroimaging biomarkers are important steps toward designing individualized treatment.

Methods

In this work, we investigated a deep learning classification model, multi-scale convolutional recurrent neural network (MCRNN), to explore psychiatric disorder-related biomarkers by leveraging the spatiotemporal information of resting-state EEG (rsEEG) using a multiple psychiatric disorder database containing 327 individuals diagnosed with schizophrenia, bipolar, major depressive disorders, and healthy controls. All subjects were mapped to a shared low-dimensional subspace for intuitively interpreting the inter-relationship and separation of psychiatric disorders.

Results

Psychiatric disorders were identified using rsEEG with high accuracy ranged from 78.6 to 91.3% in patient vs. controls two-class classification, and 68.2% in four-class classification. The control-to-schizophrenia trajectory interpretated by the model was consistent with the disease severity in clinical observation.

Conclusion

The MsRNN demonstrated a capability in extracting discriminative rsEEG biomarkers for psychiatric disorder classification, indicating its potential to facilitate our understanding of psychiatric disorders and monitoring interventions.

Multi-model order spatially constrained ICA reveals highly replicable group differences and consistent predictive results from resting data: A large N fMRI schizophrenia study

Brain functional networks identified from resting functional magnetic resonance imaging (fMRI) data have the potential to reveal biomarkers for brain disorders, but studies of complex mental illnesses such as schizophrenia (SZ) often yield mixed results across replication studies. This is likely due in part to the complexity of the disorder, the short data acquisition time, and the limited ability of the approaches for brain imaging data mining. Therefore, the use of analytic approaches which can both capture individual variability while offering comparability across analyses is highly preferred. Fully blind data-driven approaches such as independent component analysis (ICA) are hard to compare across studies, and approaches that use fixed atlas-based regions can have limited sensitivity to individual sensitivity. By contrast, spatially constrained ICA (scICA) provides a hybrid, fully automated solution that can incorporate spatial network priors while also adapting to new subjects. However, scICA has thus far only been used with a single spatial scale (ICA dimensionality, i.e., ICA model order). In this work, we present an approach using multi-objective optimization scICA with reference algorithm (MOO-ICAR) to extract subject-specific intrinsic connectivity networks (ICNs) from fMRI data at multiple spatial scales, which also enables us to study interactions across spatial scales. We evaluate this approach using a large N (N > 1,600) study of schizophrenia divided into separate validation and replication sets. A multi-scale ICN template was estimated and labeled, then used as input into scICA which was computed on an individual subject level. We then performed a subsequent analysis of multiscale functional network connectivity (msFNC) to evaluate the patient data, including group differences and classification. Results showed highly consistent group differences in msFNC in regions including cerebellum, thalamus, and motor/auditory networks. Importantly, multiple msFNC pairs linking different spatial scales were implicated. The classification model built on the msFNC features obtained up to 85% F1 score, 83% precision, and 88% recall, indicating the strength of the proposed framework in detecting group differences between schizophrenia and the control group. Finally, we evaluated the relationship of the identified patterns to positive symptoms and found consistent results across datasets. The results verified the robustness of our framework in evaluating brain functional connectivity of schizophrenia at multiple spatial scales, implicated consistent and replicable brain networks, and highlighted a promising approach for leveraging resting fMRI data for brain biomarker development.

Predicting Future Depressive Episodes from Resting-State fMRI with Generative Embedding

After a first episode of major depressive disorder (MDD), there is substantial risk for a long-term remitting-relapsing course. Prevention and early interventions are thus critically important. Various studies have examined the feasibility of detecting at-risk individuals based on out-of-sample predictions about the future occurrence of depression. However, functional magnetic resonance imaging (MRI) has received very little attention for this purpose so far. Here, we explored the utility of generative models (i.e. different dynamic causal models, DCMs) as well as functional connectivity (FC) for predicting future episodes of depression in never-depressed adults, using a large dataset (N=906) of task-free ("resting state") fMRI data from the UK Biobank. Connectivity analyses were conducted using timeseries from pre-computed spatially independent components of different dimensionalities. Over a three year period, 50% of participants showed indications of at least one depressive episode, while the other 50% did not. Using nested cross-validation for training and a held-out test set (80/20 split), we systematically examined the combination of 8 connectivity feature sets and 17 classifiers. We found that a generative embedding procedure based on combining regression DCM (rDCM) with a support vector machine (SVM) enabled the best predictions, both on the training set (0.63 accuracy, 0.66 area under the curve, AUC) and the test set (0.62 accuracy, 0.64 AUC; p<0.001). However, on the test set, rDCM was only slightly superior to predictions based on FC (0.59 accuracy, 0.61 AUC). Interpreting model predictions based on SHAP (SHapley Additive exPlanations) values suggested that the most predictive connections were widely distributed and not confined to specific networks. Overall, our analyses suggest (i) ways of improving future fMRI-based generative embedding approaches for the early detection of individuals at-risk for depression and that (ii) achieving accuracies of clinical utility may require combination of fMRI with other data modalities.

Classification of major depressive disorder using an attention-guided unified deep convolutional neural network and individual structural covariance network

Major depressive disorder (MDD) is the second leading cause of disability worldwide. Currently, the structural magnetic resonance imaging-based MDD diagnosis models mainly utilize local grayscale information or morphological characteristics in a single site with small samples. Emerging evidence has demonstrated that different brain structures in different circuits have distinct developmental timing, but mature coordinately within the same functional circuit. Thus, establishing an attention-guided unified classification framework with deep learning and individual structural covariance networks in a large multisite dataset could facilitate developing an accurate diagnosis strategy. Our results showed that attention-guided classification could improve the classification accuracy from primary 75.1% to ultimate 76.54%. Furthermore, the discriminative features of regional covariance connectivities and local structural characteristics were found to be mainly located in prefrontal cortex, insula, superior temporal cortex, and cingulate cortex, which have been widely reported to be closely associated with depression. Our study demonstrated that our attention-guided unified deep learning framework may be an effective tool for MDD diagnosis. The identified covariance connectivities and structural features may serve as biomarkers for MDD.

Temporal multi-step predictive modeling of remission in major depressive disorder using early stage treatment data; STAR*D based machine learning approach

BACKGROUND

Artificial intelligence is currently being used to facilitate early disease detection, better understand disease progression, optimize medication/treatment dosages, and uncover promising novel treatments and potential outcomes.

METHODS

Utilizing the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) dataset, we built a machine learning model to predict depression remission rates using same clinical data as features for each of the first three antidepressant treatment steps in STAR*D. We only used early treatment data (baseline and first follow up) in each STAR*D step to temporally analyze predictive features of remission at the end of the step.

RESULTS

Our model showed significant prediction performance across the three treatment steps, At step 1, Model accuracy was 66 %; sensitivity-65 %, specificity-67 %, positive predictive value (PPV)-65.5 %, and negative predictive value (NPV)-66.6 %. At step 2, model accuracy was 71.3 %, sensitivity-74.3 %, specificity-69 %, PPV-64.5 %, and NPV-77.9 %. At step 3, accuracy reached 84.6 %; sensitivity-69 %, specificity-88.8 %, PPV-67 %, and NPV-91.1 %. Across all three steps, the early Quick Inventory of Depressive Symptomatology-Self-Report (QIDS-SR) scores were key elements in predicting the final treatment outcome. The model also identified key sociodemographic factors that predicted treatment remission at different steps.

LIMITATIONS

The retrospective design, lack of replication in an independent dataset, and the use of "a complete case analysis" model in our analysis.

CONCLUSIONS

This proof-of-concept study showed that using early treatment data, multi-step temporal prediction of depressive symptom remission results in clinically useful accuracy rates. Whether these predictive models are generalizable deserves further study.

Prediction of gender from longitudinal MRI data via deep learning on adolescent data reveals unique patterns associated with brain structure and change over a two-year period

Deep learning algorithms for predicting neuroimaging data have shown considerable promise in various applications. Prior work has demonstrated that deep learning models that take advantage of the data's 3D structure can outperform standard machine learning on several learning tasks. However, most prior research in this area has focused on neuroimaging data from adults. Within the Adolescent Brain and Cognitive Development (ABCD) dataset, a large longitudinal development study, we examine structural MRI data to predict gender and identify gender-related changes in brain structure. Results demonstrate that gender prediction accuracy is exceptionally high (>97%) with training epochs > 200 and that this accuracy increases with age. Brain regions identified as the most discriminative in the task under study include predominantly frontal areas and the temporal lobe. When evaluating gender predictive changes specific to a two-year increase in age, a broader set of visual, cingulate, and insular regions are revealed. Our findings show a robust gender-related structural brain change pattern, even over a small age range. This suggests that it might be possible to study how the brain changes during adolescence by looking at how these changes are related to different behavioral and environmental factors.

Diagnostic identification of chronic insomnia using ALFF and FC features of resting-state functional MRI and logistic regression approach

This study investigated whether the amplitude of low-frequency fluctuation (ALFF) and functional connectivity (FC) features could be used as potentially neurological markers to identify chronic insomnia (CI) using resting-state functional MRI and machine learning method logistic regression (LR). This study included 49 CI patients and 47 healthy controls (HC). Voxel-wise features, including the amplitude of low-frequency fluctuations (ALFF) and functional connectivity (FC), were extracted from resting-state functional magnetic resonance brain images. Then, we divided the data into two independent cohorts for training (44 CI patients and 42 HC patients), and independent validation (5 CI patients and 5 HC patients) by using logistic regression. The model was evaluated using 20 rounds of fivefold cross‑validation for training. In particular, a two-sample t-test (GRF corrected, p-voxel < 0.001, p-cluster < 0.05) was used for feature selection during the model training. Finally, single‑shot testing of the final model was performed on the independent validation cohort. A correlation analysis (Bonferroni correction, p < 0.05/4) was also conducted to determine whether the features contributing to the prediction were correlated with clinical characteristics, including the Insomnia Severity Index (ISI), Pittsburgh sleep quality index (PSQI), self-rating anxiety scale (SAS), and self-rating depression scale (SDS). Results showed that resting-state features had a discrimination accuracy of 86.40%, with a sensitivity of 93.00% and specificity of 79.80%. The area under the curve (AUC) was 0.89 (all [Formula: see text]< 0.001). The ALFF and FC features showed significant differences between the CI patients and HC. The regions contributing to the prediction mainly included the anterior cingulate, prefrontal cortex, orbital part of the frontal lobe, angular gyrus, cingulate gyrus, praecuneus, parietal lobe, temporal gyrus, superior temporal gyrus, and middle temporal gyrus. Furthermore, some specific functional connectivity among related regions was positively correlated with the ISI, and also negatively related to the SDS in correlation analysis. Our current study suggested that ALFF and FC in the regions contributing to diagnostic identification might serve as potential neuromarkers for CI.

IABC: A Toolbox for Intelligent Analysis of Brain Connectivity

Brain functional networks and connectivity have played an important role in exploring brain function for understanding the brain and disclosing the mechanisms of brain disorders. Independent component analysis (ICA) is one of the most widely applied data-driven methods to extract brain functional networks/connectivity. However, it is hard to guarantee the reliability of networks/connectivity due to the randomness of component order and the difficulty in selecting an optimal component number in ICA. To facilitate the analysis of brain functional networks and connectivity using ICA, we developed a MATLAB toolbox called Intelligent Analysis of Brain Connectivity (IABC). IABC incorporates our previously proposed group information guided independent component analysis (GIG-ICA), NeuroMark, and splitting-merging assisted reliable ICA (SMART ICA) methods, which can estimate reliable individual-subject neuroimaging measures for further analysis. After user inputs functional magnetic resonance imaging (fMRI) data of multiple subjects that are regularly organized (e.g., in Brain Imaging Data Structure (BIDS)) and clicks a few buttons to set parameters, IABC automatically outputs brain functional networks, their related time courses, and functional network connectivity of each subject. All these neuroimaging measures are promising for providing clues in understanding brain function and differentiating brain disorders.

Global hippocampus functional connectivity as a predictive neural marker for conversion to future mood disorder in unaffected offspring of bipolar disorder parents

OBJECTIVES

Hippocampus-related functional alteration in genetically at-risk individuals may reflect an endophenotype of a mood disorder. Herein, we performed a prospective study to investigate whether baseline hippocampus functional connectivity (FC) in offspring of patients with bipolar disorder (BD) would predict subsequent conversion to mood disorder.

METHODS

Eighty bipolar offspring and 40 matched normal controls (NC) underwent resting state functional MRI (rsfMRI) scanning on a 3.0 Tesla MR scanner. The offspring were subdivided into asymptomatic offspring (AO) (n = 41) and symptomatic offspring (SO) (n = 39) according to whether they manifested subthreshold mood symptoms. After identifying the different hippocampus FCs between the AO and SO, a logistic regression analysis was conducted to investigate whether the baseline hippocampus FCs predicted a future mood disorder during a 6-year follow-up.

RESULTS

We identified seven baseline para/hippocampus FCs that showed differences between AO and SO, which were entered as predictive features in the logistic regressive model. Of the 80 bipolar offspring entering the analysis, the FCs between left hippocampus and left precuneus, and between right hippocampus and left posterior cingulate, showed a discriminative capacity for predicting future mood disorder (area-under-curve, or AUC=75.76 % and 75.00 % respectively), and for predicting BD onset (AUC=77.46 % and 81.63 %, respectively).

CONCLUSIONS

The present findings revealed high predictive utility of the hippocampus resting state FCs for future mood disorder and BD onset in individuals at familial risk. These neural markers can potentially improve early detection of individuals carrying particularly high risk for future mood disorder.

Personalized Diagnosis and Treatment for Neuroimaging in Depressive Disorders

Depressive disorders are highly heterogeneous in nature. Previous studies have not been useful for the clinical diagnosis and prediction of outcomes of major depressive disorder (MDD) at the individual level, although they provide many meaningful insights. To make inferences beyond group-level analyses, machine learning (ML) techniques can be used for the diagnosis of subtypes of MDD and the prediction of treatment responses. We searched PubMed for relevant studies published until December 2021 that included depressive disorders and applied ML algorithms in neuroimaging fields for depressive disorders. We divided these studies into two sections, namely diagnosis and treatment outcomes, for the application of prediction using ML. Structural and functional magnetic resonance imaging studies using ML algorithms were included. Thirty studies were summarized for the prediction of an MDD diagnosis. In addition, 19 studies on the prediction of treatment outcomes for MDD were reviewed. We summarized and discussed the results of previous studies. For future research results to be useful in clinical practice, ML enabling individual inferences is important. At the same time, there are important challenges to be addressed in the future.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

Background

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

Objective

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

Methods

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

Results

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

Conclusions

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

Evidence of shared and distinct functional and structural brain signatures in schizophrenia and autism spectrum disorder

Schizophrenia (SZ) and autism spectrum disorder (ASD) share considerable clinical features and intertwined historical roots. It is greatly needed to explore their similarities and differences in pathophysiologic mechanisms. We assembled a large sample size of neuroimaging data (about 600 SZ patients, 1000 ASD patients, and 1700 healthy controls) to study the shared and unique brain abnormality of the two illnesses. We analyzed multi-scale brain functional connectivity among functional networks and brain regions, intra-network connectivity, and cerebral gray matter density and volume. Both SZ and ASD showed lower functional integration within default mode and sensorimotor domains, but increased interaction between cognitive control and default mode domains. The shared abnormalties in intra-network connectivity involved default mode, sensorimotor, and cognitive control networks. Reduced gray matter volume and density in the occipital gyrus and cerebellum were observed in both illnesses. Interestingly, ASD had overall weaker changes than SZ in the shared abnormalities. Interaction between visual and cognitive regions showed disorder-unique deficits. In summary, we provide strong neuroimaging evidence of the convergent and divergent changes in SZ and ASD that correlated with clinical features.

Fluoxetine and environmental enrichment similarly reverse chronic social stress-related depression- and anxiety-like behavior, but have differential effects on amygdala gene expression

The adverse effects of stress on brain and behavior have long been known and well-studied, with abundant evidence linking stress to, among other things, mood and anxiety disorders. Likewise, many have investigated potential treatments for stress-related mood and anxiety phenotypes and demonstrated good response to standard antidepressant medications like selective serotonin reuptake inhibitors (SSRIs), as well as environmental manipulations like exercise or enrichment. However, the extent to which stress and various treatments act on overlapping pathways in the brain is less well understood. Here, we used a widely studied social defeat stress paradigm to induce a robust depression- and anxiety-like phenotype and chronic corticosterone elevation that persisted for at least 4 weeks in wild type male mice. When mice were treated with either the SSRI fluoxetine or an enriched environment, both led to similar behavioral recovery from social defeat. We then focused on the amygdala and assessed the effects of social defeat, fluoxetine, and enrichment on 168 genes broadly related to synaptic plasticity or oxidative stress. We found 24 differentially expressed genes in response to social defeat stress. Interestingly, fluoxetine led to broad normalization of the stress-induced expression pattern while enrichment led to expression changes in a separate set of genes. Together, this study provides additional insight into the chronic effects of social defeat stress on behavior and gene expression in the amygdala. The findings also suggest that, for a subset of genes assessed, fluoxetine and environmental enrichment have strikingly divergent effects on expression in the amygdala, despite leading to similar behavioral outcomes.

Data-driven approaches to neuroimaging biomarkers for neurological and psychiatric disorders: emerging approaches and examples

PURPOSE OF REVIEW

The 'holy grail' of clinical applications of neuroimaging to neurological and psychiatric disorders via personalized biomarkers has remained mostly elusive, despite considerable effort. However, there are many reasons to continue to be hopeful, as the field has made remarkable advances over the past few years, fueled by a variety of converging technical and data developments.

RECENT FINDINGS

We discuss a number of advances that are accelerating the push for neuroimaging biomarkers including the advent of the 'neuroscience big data' era, biomarker data competitions, the development of more sophisticated algorithms including 'guided' data-driven approaches that facilitate automation of network-based analyses, dynamic connectivity, and deep learning. Another key advance includes multimodal data fusion approaches which can provide convergent and complementary evidence pointing to possible mechanisms as well as increase predictive accuracy.

SUMMARY

The search for clinically relevant neuroimaging biomarkers for neurological and psychiatric disorders is rapidly accelerating. Here, we highlight some of these aspects, provide recent examples from studies in our group, and link to other ongoing work in the field. It is critical that access and use of these advanced approaches becomes mainstream, this will help propel the community forward and facilitate the production of robust and replicable neuroimaging biomarkers.

The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review (Preprint).. [DOI: 10.2196/preprints.29749] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

BACKGROUND

Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.

OBJECTIVE

This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.

METHODS

The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.

RESULTS

We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.

CONCLUSIONS

This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

A multivariate neuromonitoring approach to neuroplasticity-based computerized cognitive training in recent onset psychosis

Two decades of studies suggest that computerized cognitive training (CCT) has an effect on cognitive improvement and the restoration of brain activity. Nevertheless, individual response to CCT remains heterogenous, and the predictive potential of neuroimaging in gauging response to CCT remains unknown. We employed multivariate pattern analysis (MVPA) on whole-brain resting-state functional connectivity (rsFC) to (neuro)monitor clinical outcome defined as psychosis-likeness change after 10-hours of CCT in recent onset psychosis (ROP) patients. Additionally, we investigated if sensory processing (SP) change during CCT is associated with individual psychosis-likeness change and cognitive gains after CCT. 26 ROP patients were divided into maintainers and improvers based on their SP change during CCT. A support vector machine (SVM) classifier separating 56 healthy controls (HC) from 35 ROP patients using rsFC (balanced accuracy of 65.5%, P < 0.01) was built in an independent sample to create a naturalistic model representing the HC-ROP hyperplane. This model was out-of-sample cross-validated in the ROP patients from the CCT trial to assess associations between rsFC pattern change, cognitive gains and SP during CCT. Patients with intact SP threshold at baseline showed improved attention despite psychosis status on the SVM hyperplane at follow-up (p < 0.05). Contrarily, the attentional gains occurred in the ROP patients who showed impaired SP at baseline only if rsfMRI diagnosis status shifted to the healthy-like side of the SVM continuum. Our results reveal the utility of MVPA for elucidating treatment response neuromarkers based on rsFC-SP change and pave the road to more personalized interventions.

Functional connectivity between the amygdala and subgenual cingulate gyrus predicts the antidepressant effects of ketamine in patients with treatment-resistant depression

Aim

Approximately one‐third of patients with major depressive disorder develop treatment‐resistant depression. One‐third of patients with treatment‐resistant depression demonstrate resistance to ketamine, which is a novel antidepressant effective for this disorder. The objective of this study was to examine the utility of resting‐state functional magnetic resonance imaging for the prediction of treatment response to ketamine in treatment‐resistant depression.

Methods

An exploratory seed‐based resting‐state functional magnetic resonance imaging analysis was performed to examine baseline resting‐state functional connectivity differences between ketamine responders and nonresponders before treatment with multiple intravenous ketamine infusions.

Results

Fifteen patients with treatment‐resistant depression received multiple intravenous subanesthetic (0.5 mg/kg/40 minutes) ketamine infusions, and nine were identified as responders. The exploratory resting‐state functional magnetic resonance imaging analysis identified a cluster of significant baseline resting‐state functional connectivity differences associating ketamine response between the amygdala and subgenual anterior cingulate gyrus in the right hemisphere. Using anatomical region of interest analysis of the resting‐state functional connectivity, ketamine response was predicted with 88.9% sensitivity and 100% specificity. The resting‐state functional connectivity of significant group differences between responders and nonresponders retained throughout the treatment were considered a trait‐like feature of heterogeneity in treatment‐resistant depression.

Conclusion

This study suggests the possible clinical utility of resting‐state functional magnetic resonance imaging for predicting the antidepressant effects of ketamine in treatment‐resistant depression patients and implicated resting‐state functional connectivity alterations to determine the trait‐like pathophysiology underlying treatment response heterogeneity in treatment‐resistant depression.

This study illustrates that the alteration in the RSFC within the right AN in TRD patients reflects the antidepressant response to ketamine at baseline. The alteration remained throughout the 2‐week treatment with multiple ketamine infusions and seemed to reflect the trait‐like features underlying treatment heterogeneity in TRD. By employing an anatomical ROI of the sc/sgACC, the present study also suggests the possible clinical utility of the rsfMRI to predict the treatment response to ketamine in TRD patients.

Distinct Features of Cerebral Blood Flow and Spontaneous Neural Activity as Integrated Predictors of Early Response to Antidepressants

AIMS

The purpose of this study is to explore whether pre-treatment features of brain function can discriminate non-responders to antidepressant medication in the early phase.

METHODS

Forty-four treatment-responsive depressed (RD) patients, 36 non-responsive depressed (NRD) patients, and 42 healthy controls (HCs) were recruited. Regional cerebral blood flow (CBF) and amplitude of low-frequency fluctuation (ALFF) values were calculated for all subjects. Correlation analyses were used to explore the relationship between symptom improvement and CBF/ALFF. Receiver operating characteristics (ROC) and the 10-fold cross-validation support vector machine (SVM) classifier were applied for the discrimination of treatment response.

RESULTS

Compared with the HCs, the RD and NRD groups exhibited lower CBF and ALFF in the right posterior lobe of the cerebellum. Compared with the NRD group, the RD group showed distinct CBF patterns in the left frontal striatal regions and right frontal cerebellar regions, as well as distinct ALFF features in the left frontoparietal striatum and right frontotemporal striatal cerebellar regions. The ROC and SVM classifier revealed the optimal power to distinguish the RD and NRD groups based on the combined measures (i.e., CBF and ALFF).

CONCLUSION

Distinct features of CBF and ALFF in the frontal striatal network may serve as promising neuroimaging predictors for identifying patients with blunted responsiveness, which may facilitate personalized antidepressant treatment.

Neuroimaging-based Individualized Prediction of Cognition and Behavior for Mental Disorders and Health: Methods and Promises

The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move toward a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling, which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits, and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations, and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.

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.

NeuroMark: An automated and adaptive ICA based pipeline to identify reproducible fMRI markers of brain disorders

•

Propose a new pipeline to link brain changes among different datasets, studies, and disorders.

•

Identify reproducible biomarkers in schizophrenia using independent data.

•

Find both common and unique brain impairments in schizophrenia and autism.

•

Reveal gradual changes from healthy controls to mild cognitive impairment to Alzheimer’s disease.

•

Obtain high classification accuracy (~90%) between bipolar disorder and major depressive disorder.

Many mental illnesses share overlapping or similar clinical symptoms, confounding the diagnosis. It is important to systematically characterize the degree to which unique and similar changing patterns are reflective of brain disorders. Increasing sharing initiatives on neuroimaging data have provided unprecedented opportunities to study brain disorders. However, it is still an open question on replicating and translating findings across studies. Standardized approaches for capturing reproducible and comparable imaging markers are greatly needed. Here, we propose a pipeline based on the priori-driven independent component analysis, NeuroMark, which is capable of estimating brain functional network measures from functional magnetic resonance imaging (fMRI) data that can be used to link brain network abnormalities among different datasets, studies, and disorders. NeuroMark automatically estimates features adaptable to each individual subject and comparable across datasets/studies/disorders by taking advantage of the reliable brain network templates extracted from 1828 healthy controls as guidance. Four studies including 2442 subjects were conducted spanning six brain disorders (schizophrenia, autism spectrum disorder, mild cognitive impairment, Alzheimer’s disease, bipolar disorder, and major depressive disorder) to evaluate validity of the proposed pipeline from different perspectives (replication of brain abnormalities, cross-study comparison, identification of subtle brain changes, and multi-disorder classification using identified biomarkers). Our results highlight that NeuroMark effectively identified replicated brain network abnormalities of schizophrenia across different datasets; revealed interesting neural clues on the overlap and specificity between autism and schizophrenia; demonstrated brain functional impairments present to varying degrees in mild cognitive impairments and Alzheimer's disease; and captured biomarkers that achieved good performance in classifying bipolar disorder and major depressive disorder.

Identifying commonality and specificity across psychosis sub-groups via classification based on features from dynamic connectivity analysis

It is difficult to distinguish schizophrenia (SZ), schizoaffective disorder (SAD), and bipolar disorder with psychosis (BPP) as their clinical diagnoses rely on symptoms that overlap. In this paper, we investigate if there is biological evidence to support the symptom-based clinical categories by looking across the three disorders using dynamic connectivity measures, and provide meaningful characteristics on which brain functional connectivity measures are commonly or uniquely impaired. Large-sample functional magnetic resonance image (fMRI) datasets from 623 subjects including 238 healthy controls (HCs), 113 SZ patients, 132 SAD patients, and 140 BPP patients were analyzed. First, we computed whole-brain dynamic functional connectivity (DFC) using a sliding-window technique, and then extracted the individual connectivity states by applying our previously proposed decomposition-based DFC analysis method. Next, with the features from the dominant connectivity state, we assessed the clinical categories by performing both four-group (SZ, SAD, BPP and healthy control groups) and pair-wise classification using a support vector machine within cross-validation. Furthermore, we comprehensively summarized the shared and unique connectivity alterations among the disorders. In terms of the classification performance, our method achieved 69% in the four-group classification and >80% in the between-group classifications for the mean overall accuracy; and yielded 66% in the four-group classification and >80% in the between-group classifications for the mean balanced accuracy. Through summarizing the features that were automatically selected in the classifications, we found that among the three symptom-related disorders, their disorder-common impairments primarily included the decreased connectivity strength between thalamus and cerebellum and the increased strength between postcentral gyrus and thalamus. The disorder-unique changes included more various brain regions, mainly in the temporal and frontal gyrus. Our work demonstrates that dynamic functional connectivity provides biological evidence that both common and unique impairments exist in psychosis sub-groups.

The Care of Patients With Complex Mood Disorders

This article focuses on some common dilemmas facing clinicians, patients, and families in managing the treatment of complicated mood disorders. Specifically, this article reviews the interaction of depressive states, including unipolar, bipolar, and mixed, with other adversities, including comorbid physical and psychological disorders, personality vulnerabilities, misuse of drugs and alcohol, and social and family problems. These issues are not always clearly differentiated from the depressive illness. Each of these adversities can worsen an existing mood disorder and influence the patient's resolve to persist with a treatment plan. Although this article is not focused strictly on treatment-resistant depression, these coexisting issues make depressive states harder to manage therapeutically. For brevity, the aim of this article has been limited to discussion of some complex situations that psychiatrists in general practice may encounter.

Preliminary prediction of individual response to electroconvulsive therapy using whole-brain functional magnetic resonance imaging data

•

The negative FC networks achieve predictive accuracy of 76.23% for ECT response.

•

The consensus FCs represent predominately frontal, temporal and subcortical regions.

•

FCs that changed significantly were concentrated in frontal and limbic networks.

•

Longitudinal change overlapped with two FCs compared with FC with predictive power.

Electroconvulsive therapy (ECT) works rapidly and has been widely used to treat depressive disorders (DEP). However, identifying biomarkers predictive of response to ECT remains a priority to individually tailor treatment and understand treatment mechanisms. This study used a connectome-based predictive modeling (CPM) approach in 122 patients with DEP to determine if pre-ECT whole-brain functional connectivity (FC) predicts depressive rating changes and remission status after ECT (47 of 122 total subjects or 38.5% of sample), and whether pre-ECT and longitudinal changes (pre/post-ECT) in regional brain network biomarkers are associated with treatment-related changes in depression ratings. Results show the networks with the best predictive performance of ECT response were negative (anti-correlated) FC networks, which predict the post-ECT depression severity (continuous measure) with a 76.23% accuracy for remission prediction. FC networks with the greatest predictive power were concentrated in the prefrontal and temporal cortices and subcortical nuclei, and include the inferior frontal (IFG), superior frontal (SFG), superior temporal (STG), inferior temporal gyri (ITG), basal ganglia (BG), and thalamus (Tha). Several of these brain regions were also identified as nodes in the FC networks that show significant change pre-/post-ECT, but these networks were not related to treatment response. This study design has limitations regarding the longitudinal design and the absence of a control group that limit the causal inference regarding mechanism of post-treatment status. Though predictive biomarkers remained below the threshold of those recommended for potential translation, the analysis methods and results demonstrate the promise and generalizability of biomarkers for advancing personalized treatment strategies.

Enhanced baseline activity in the left ventromedial putamen predicts individual treatment response in drug-naive, first-episode schizophrenia: Results from two independent study samples

Background

Antipsychotic medications are the common treatment for schizophrenia. However, reliable biomarkers that can predict individual treatment response are still lacking. The present study aimed to examine whether baseline putamen activity can predict individual treatment response in schizophrenia.

Methods

Two independent samples of patients with drug-naive, first-episode schizophrenia (32 patients in sample 1 and 44 in sample 2) and matched healthy controls underwent resting-state functional magnetic resonance imaging (fMRI) at baseline. Patients were treated with olanzapine for 8 weeks; symptom severity was assessed using the Positive and Negative Syndrome Scale (PANSS) at baseline and week 8. Fractional amplitude of low frequency fluctuation (fALFF) and pattern classification techniques were used to analyze the data.

Findings

Univariate analysis shows an elevated pre-treatment fALFF in the left ventromedial putamen in both patient samples compared to healthy controls (p's < 0.001). The support vector regression (SVR) analysis suggests a positive relationship between baseline pre-treatment fALFF in the left ventromedial putamen and improvement in positive symptom at week 8 in each patient group using a cross-validated method (r = 0.452, p = .002; r = 0.511, p = .003, respectively).

Interpretation

Our study suggests that elevated pre-treatment mean fALFF in the left ventromedial putamen may predict individual therapeutic response to olanzapine treatment in drug-naive, first-episode patients with schizophrenia. Future studies are needed to confirm whether this finding is generalizable to patients with schizophrenia treated with other antipsychotic medications.

Fund

The National Key R&D Program of China and the National Natural Science Foundation of China.

Group ICA for identifying biomarkers in schizophrenia: 'Adaptive' networks via spatially constrained ICA show more sensitivity to group differences than spatio-temporal regression

Brain functional networks identified from fMRI data can provide potential biomarkers for brain disorders. Group independent component analysis (GICA) is popular for extracting brain functional networks from multiple subjects. In GICA, different strategies exist for reconstructing subject-specific networks from the group-level networks. However, it is unknown whether these strategies have different sensitivities to group differences and abilities in distinguishing patients. Among GICA, spatio-temporal regression (STR) and spatially constrained ICA approaches such as group information guided ICA (GIG-ICA) can be used to propagate components (indicating networks) to a new subject that is not included in the original subjects. In this study, based on the same a priori network maps, we reconstructed subject-specific networks using these two methods separately from resting-state fMRI data of 151 schizophrenia patients (SZs) and 163 healthy controls (HCs). We investigated group differences in the estimated functional networks and the functional network connectivity (FNC) obtained by each method. The networks were also used as features in a cross-validated support vector machine (SVM) for classifying SZs and HCs. We selected features using different strategies to provide a comprehensive comparison between the two methods. GIG-ICA generally showed greater sensitivity in statistical analysis and better classification performance (accuracy 76.45 ± 8.9%, sensitivity 0.74 ± 0.11, specificity 0.79 ± 0.11) than STR (accuracy 67.45 ± 8.13%, sensitivity 0.65 ± 0.11, specificity 0.71 ± 0.11). Importantly, results were also consistent when applied to an independent dataset including 82 HCs and 82 SZs. Our work suggests that the functional networks estimated by GIG-ICA are more sensitive to group differences, and GIG-ICA is promising for identifying image-derived biomarkers of brain disease.

•

We investigate which group ICA method is more sensitive to group differences in networks and FNC.

•

We evaluate which group ICA method can result in better classification performance.

•

We compare the spatio-temporal regression (STR) and GIG-ICA using different feature selection and model building strategies and independent samples.

•

We use different feature selection and model building strategies and classification using independent samples.

•

Using fMRI data including schizophrenia patients, GIG-ICA shows better performance than the traditional STR method.

Complexity in mood disorder diagnosis: fMRI connectivity networks predicted medication-class of response in complex patients

OBJECTIVE

This study determined the clinical utility of an fMRI classification algorithm predicting medication-class of response in patients with challenging mood diagnoses.

METHODS

Ninety-nine 16-27-year-olds underwent resting state fMRI scans in three groups-BD, MDD and healthy controls. A predictive algorithm was trained and cross-validated on the known-diagnosis patients using maximally spatially independent components (ICs), constructing a similarity matrix among subjects, partitioning the matrix in kernel space and optimizing support vector machine classifiers and IC combinations. This classifier was also applied to each of 12 new individual patients with unclear mood disorder diagnoses.

RESULTS

Classification within the known-diagnosis group was approximately 92.4% accurate. The five maximally contributory ICs were identified. Applied to the complicated patients, the algorithm diagnosis was consistent with optimal medication-class of response to sustained recovery in 11 of 12 cases (i.e., almost 92% accuracy).

CONCLUSION

This classification algorithm performed well for the know-diagnosis but also predicted medication-class of response in difficult-to-diagnose patients. Further research can enhance this approach and extend these findings to be more clinically accessible.