Identification of suicidality in adolescent major depressive disorder patients using sMRI: A machine learning approach

Effectiveness of artificial intelligence in detecting and managing depressive disorders: Systematic review

OBJECTIVES

This study underscores the importance of exploring AI's creative applications in treating depressive disorders to revolutionize mental health care. Through innovative integration of AI technologies, the research confirms their positive effects on preventing, diagnosing, and treating depression. The systematic review establishes an evidence base for AI in depression management, offering directions for effective interventions.

METHODS

This systematic literature review investigates the effectiveness of AI in depression management by analyzing studies from January 1, 2017, to May 31, 2022. Utilizing search engines like IEEE Xplore, PubMed, and Web of Science, the review focused on keywords such as Depression/Mental Health, Machine Learning/Artificial Intelligence, and Prediction/Diagnosis. The analysis of 95 documents involved classification based on use, data type, and algorithm type.

RESULTS

The study revealed that AI in depression management excelled in accuracy, particularly in monitoring and prediction. Biomarker-derived data demonstrated the highest accuracy, with the CNN algorithm proving most effective. The findings affirm the therapeutic benefits of AI, including treatment, detection, and disease prediction, highlighting its potential in analyzing monitored data for depression management.

LIMITATIONS

This study exclusively examined the application of AI in individuals with depressive disorders. Interpretation should be cautious due to the limited scope of subjects to this specific population.

CONCLUSIONS

To introduce digital healthcare and therapies for ongoing depression management, it's crucial to present empirical evidence on the medical fee payment system, safety, and efficacy. These findings support enhanced medical accessibility through digital healthcare, offering personalized disease management for patients seeking non-face-to-face treatment.

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

Machine learning (ML) has emerged as a promising tool to enhance suicidal prediction. However, as many large-sample studies mixed psychiatric and non-psychiatric populations, a formal psychiatric diagnosis emerged as a strong predictor of suicidal risk, overshadowing more subtle risk factors specific to distinct populations. To overcome this limitation, we conducted a systematic review of ML studies evaluating suicidal behaviors exclusively in psychiatric clinical populations. A systematic literature search was performed from inception through November 17, 2022 on PubMed, EMBASE, and Scopus following the PRISMA guidelines. Original research using ML techniques to assess the risk of suicide or predict suicide attempts in the psychiatric population were included. An assessment for bias risk was performed using the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines. About 1032 studies were retrieved, and 81 satisfied the inclusion criteria and were included for qualitative synthesis. Clinical and demographic features were the most frequently employed and random forest, support vector machine, and convolutional neural network performed better in terms of accuracy than other algorithms when directly compared. Despite heterogeneity in procedures, most studies reported an accuracy of 70% or greater based on features such as previous attempts, severity of the disorder, and pharmacological treatments. Although the evidence reported is promising, ML algorithms for suicidal prediction still present limitations, including the lack of neurobiological and imaging data and the lack of external validation samples. Overcoming these issues may lead to the development of models to adopt in clinical practice. Further research is warranted to boost a field that holds the potential to critically impact suicide mortality.

Enhancing the efficacy of depression detection system using optimal feature selection from EHR

Diagnosing depression at an early stage is crucial and majorly depends on the clinician's skill. The present work aims to develop an automated tool for assisting the diagnostic procedure of depression using multiple machine-learning techniques. The dataset of sample size 4184 used in this study contains biometric and demographic information of individuals with or without depression, accessed from the University of Nice Sophia-Antipolis. The Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting (XGBoost) are used for classifying the depressed from the control group. To enhance the computational efficiency, various feature selection algorithms like Recursive Feature Elimination (RFE), Mutual Information (MI) and three bio-inspired techniques, viz. Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Firefly Algorithms (FA) have been incorporated. To enhance the feature selection process further, majority voting is carried out in all possible combinations of three, four and five feature selection techniques. These feature selection techniques bring down the feature set size significantly to a mean of 33 from the actual size of 61 which is a reduction of 45.90%. The classification accuracy of the enhanced model varies between 84.18% and 88.46%, which is a significant improvement in performance as compared to the pre-existing models (83.76-85.89%). The proposed predictive models outperform the pre-existing classification models without feature selection and thereby enhancing both the performance and efficiency of the diagnostic process.

Connectomics-based resting-state functional network alterations predict suicidality in major depressive disorder

Suicidal behavior is a major concern for patients who suffer from major depressive disorder (MDD). However, dynamic alterations and dysfunction of resting-state networks (RSNs) in MDD patients with suicidality have remained unclear. Thus, we investigated whether subjects with different severity of suicidal ideation and suicidal behavior may have different disturbances in brain RSNs and whether these changes could be used as the diagnostic biomarkers to discriminate MDD with or without suicidal ideation and suicidal behavior. Then a multicenter, cross-sectional study of 528 MDD patients with or without suicidality and 998 healthy controls was performed. We defined the probability of dying by the suicide of the suicidality components as a 'suicidality gradient'. We constructed ten RSNs, including default mode (DMN), subcortical (SUB), ventral attention (VAN), and visual network (VIS). The network connections of RSNs were analyzed among MDD patients with different suicidality gradients and healthy controls using ANCOVA, chi-squared tests, and network-based statistical analysis. And support vector machine (SVM) model was designed to distinguish patients with mild-to-severe suicidal ideation, and suicidal behavior. We found the following abnormalities with increasing suicidality gradient in MDD patients: within-network connectivity values initially increased and then decreased, and one-versus-other network values decreased first and then increased. Besides, within- and between-network connectivity values of the various suicidality gradients are mainly negatively correlated with HAMD anxiety and positively correlated with weight. We found that VIS and DMN-VIS values were affected by age (p < 0.05), cingulo-opercular network, and SUB-VAN values were statistically influenced by sex (p < 0.05). Furthermore, the SVM model could distinguish MDD patients with different suicidality gradients (AUC range, 0.73-0.99). In conclusion, we have identified that disrupted brain connections were present in MDD patients with different suicidality gradient. These findings provided useful information about the pathophysiological mechanisms of MDD patients with suicidality.

A multimodal prediction model for suicidal attempter in major depressive disorder

Background

Suicidal attempts in patients with major depressive disorder (MDD) have become an important challenge in global mental health affairs. To correctly distinguish MDD patients with and without suicidal attempts, a multimodal prediction model was developed in this study using multimodality data, including demographic, depressive symptoms, and brain structural imaging data. This model will be very helpful in the early intervention of MDD patients with suicidal attempts.

Methods

Two feature selection methods, support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF) algorithms, were merged for feature selection in 208 MDD patients. SVM was then used as a classification model to distinguish MDD patients with suicidal attempts or not.

Results

The multimodal predictive model was found to correctly distinguish MDD patients with and without suicidal attempts using integrated features derived from SVM-RFE and RF, with a balanced accuracy of 77.78%, sensitivity of 83.33%, specificity of 70.37%, positive predictive value of 78.95%, and negative predictive value of 76.00%. The strategy of merging the features from two selection methods outperformed traditional methods in the prediction of suicidal attempts in MDD patients, with hippocampal volume, cerebellar vermis volume, and supracalcarine volume being the top three features in the prediction model.

Conclusions

This study not only developed a new multimodal prediction model but also found three important brain structural phenotypes for the prediction of suicidal attempters in MDD patients. This prediction model is a powerful tool for early intervention in MDD patients, which offers neuroimaging biomarker targets for treatment in MDD patients with suicidal attempts.

Classification of suicidality by training supervised machine learning models with brain MRI findings: A systematic review

BACKGROUND

Suicide is a global public health issue causing around 700,000 deaths worldwide each year. Therefore, identifying suicidal thoughts and behaviors in patients can help lower the suicide-related mortality rate. This review aimed to investigate the feasibility of suicidality identification by applying supervised Machine Learning (ML) methods to Magnetic Resonance Imaging (MRI) data.

METHODS

We conducted a systematic search on PubMed, Scopus, and Web of Science to identify studies examining suicidality by applying ML methods to MRI features. Also, the Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed for the quality assessment.

RESULTS

23 studies met the inclusion criteria. Of these, 20 developed prediction models without external validation and 3 developed prediction models with external validation. The performance of ML models varied among the reviewed studies, with the highest reported values of accuracies and Area Under the Curve (AUC) ranging from 51.7 % to 100 % and 0.52 to 1, respectively. Over half of the studies that reported accuracy (12/21) or AUC (13/16) achieved values of ≥0.8. Our comparative analysis indicated that deep learning exhibited the highest predictive performance compared to other ML models. The most commonly identified discriminative imaging features were resting-state functional connectivity and grey matter volume within prefrontal-limbic structures.

LIMITATIONS

Small sample sizes, lack of external validation, heterogeneous study designs, and ML model development.

CONCLUSIONS

Most of the studies developed ML models capable of ML-based suicide identification, although ML models' predictive performance varied across the reviewed studies. Thus, further well-designed is necessary to uncover the true potential of different ML models in this field.

Racial/ethnic differences in adolescents' non-response to suicide attempt: Findings from the Youth Risk Behavior Survey, 2015-2019

Racial/ethnic minority adolescents are at greater risk of attempting suicide compared to their White counterparts. Yet, racial/ethnic minority adolescents are more likely to not respond to questions on suicidal behaviors. The objective of this study was to investigate the association between race/ethnicity and missing response to suicide attempt among adolescents in the United States. Data for this study were obtained the 2015-2019 national Youth Risk Behavior Survey (n = 40,360). The outcome variable investigated in this study was missing response to suicide attempt and the main explanatory variable was race/ethnicity. Two hierarchical binary logistic regression models were fitted to examine the association between race/ethnicity and missing response to suicide attempt. Of the 40,036 adolescents, 13.4% had missing response to suicide attempt. Controlling for the effects of demographic factors and symptoms of depression, adolescents who self-identified as non-Hispanic Black had more than threefold higher odds of having missing response to suicide attempt when compared to their non-Hispanic White counterparts (AOR = 3.62, p < .001, 95% CI = 2.45-5.34). Adolescent males and adolescents questioning their sexual identity had higher odds of having missing response to suicide attempt. Adolescents with depressive symptoms had lower odds of having missing response to suicide attempt. Missing response to suicide attempt among adolescents continues to differ by race/ethnicity and other demographic factors. The use of a single item in assessing suicide attempt history may be inadequate in capturing national estimates of adolescent suicide metrics.

Childhood trauma and social support affect symptom profiles through cortical thickness abnormalities in major depressive disorder: A structural equation modeling analysis

BACKGROUND

Childhood trauma, low social support, and alexithymia are recognized as risk factors for major depressive disorder (MDD). However, the mechanisms of risk factors, symptoms, and corresponding structural brain abnormalities in MDD are not fully understood. Structural equation modeling (SEM) has advantages in studying multivariate interrelationships. We aim to illustrate their relationships using SEM.

METHODS

313 MDD patients (213 female; mean age 42.49 years) underwent magnetic resonance imaging and completed assessments. We integrated childhood trauma, alexithymia, social support, anhedonia, depression, anxiety, suicidal ideation and cortical thickness into a multivariate SEM.

RESULTS

We first established the risk factors-clinical phenotype SEM with an adequate fit. Cortical thickness results show a negative correlation of childhood trauma with the left middle temporal gyrus (MTG) (p = 0.012), and social support was negatively correlated with the left posterior cingulate cortex (PCC) (p < 0.001). The final good fit SEM (χ2 = 32.92, df = 21, χ2/df = 1.57, CFI = 0.962, GFI = 0.978, RMSEA = 0.043) suggested two pathways, with left PCC thickness mediating the relationship between social support and suicidal ideation, and left MTG thickness mediating between childhood trauma and anhedonia/anxiety.

CONCLUSION

Our findings provide evidence for the impact of risk factor variables on the brain structure and clinical phenotype of MDD patients. Insufficient social support and childhood trauma might lead to corresponding cortical abnormalities in PCC and MTG, affecting the patient's mood and suicidal ideation. Future interventions should aim at these nodes.

A Systematic Review of MRI Studies and the "Emotional paiN and social Disconnect (END)" Brain Model of Suicidal Behavior in Youth

Introduction

Risk of suicidal ideation and suicidal behaviors greatly increases during adolescence, and rates have risen dramatically over the past two decades. However, few risk factors or biomarkers predictive of suicidal ideation or attempted suicide have been identified in adolescents. Neuroimaging correlates hold potential for early identification of adolescents at increased risk of suicidality and risk stratification for those at high risk of suicide attempt.

Methods

In this systematic review, we evaluated neural regions and networks associated with suicidal ideation and suicide attempt in adolescents derived from magnetic resonance imaging (MRI) studies. A total of 28 articles were included in this review.

Results

After descriptively synthesizing the literature, we propose the Emotional paiN and social Disconnect (END) model of adolescent suicidality and present two key neural circuits: (1) the emotional/mental pain circuit and (2) the social disconnect/distortion circuit. In the END model, the emotional pain circuit-consisting of the cerebellum, amygdala, and hippocampus-shows similar aberrations in adolescents with suicidal ideation as in those with a history of a suicide attempt (but to a smaller degree). The social disconnect circuit is unique to adolescent suicide attempters and includes the lateral orbitofrontal cortex (OFC), the temporal gyri, and the connections between them.

Conclusion

Our proposed END brain model of suicidal behavior in youth, if confirmed by future prospective studies, can have implications for clinical goals of early detection, risk stratification, and intervention development. Treatments that target emotional pain and social disconnect may be ideal interventions for reducing suicidality in adolescents.

Identifying suicide attempts, ideation, and non-ideation in major depressive disorder from structural MRI data using deep learning

The present study aims to identify suicide risks in major depressive disorders (MDD) patients from structural MRI (sMRI) data using deep learning. In this paper, we collected the sMRI data of 288 MDD patients, including 110 patients with suicide ideation (SI), 93 patients with suicide attempts (SA), and 85 patients without suicidal ideation or attempts (NS). And we developed interpretable deep neural network models to classify patients in three tasks including SA-versus-SI, SA-versus-NS, and SI-versus-NS, respectively. Furthermore, we interpreted the models by extracting the important features that contributed most to the classification, and further discussed these features or ROI/brain regions.

Machine learning based identification of structural brain alterations underlying suicide risk in adolescents

Suicide is the third leading cause of death for individuals between 15 and 19 years of age. The high suicide mortality rate and limited prior success in identifying neuroimaging biomarkers indicate that it is crucial to improve the accuracy of clinical neural signatures underlying suicide risk. The current study implements machine-learning (ML) algorithms to examine structural brain alterations in adolescents that can discriminate individuals with suicide risk from typically developing (TD) adolescents at the individual level. Structural MRI data were collected from 79 adolescents who demonstrated clinical levels of suicide risk and 79 demographically matched TD adolescents. Region-specific cortical/subcortical volume (CV/SCV) was evaluated following whole-brain parcellation into 1000 cortical and 12 subcortical regions. CV/SCV parameters were used as inputs for feature selection and three ML algorithms (i.e., support vector machine [SVM], K-nearest neighbors, and ensemble) to classify adolescents at suicide risk from TD adolescents. The highest classification accuracy of 74.79% (with sensitivity = 75.90%, specificity = 74.07%, and area under the receiver operating characteristic curve = 87.18%) was obtained for CV/SCV data using the SVM classifier. Identified bilateral regions that contributed to the classification mainly included reduced CV within the frontal and temporal cortices but increased volume within the cuneus/precuneus for adolescents at suicide risk relative to TD adolescents. The current data demonstrate an unbiased region-specific ML framework to effectively assess the structural biomarkers of suicide risk. Future studies with larger sample sizes and the inclusion of clinical controls and independent validation data sets are needed to confirm our findings.

Suicide risk stratification among major depressed patients based on a machine learning approach and whole-brain functional connectivity

BACKGROUND

Suicide risk stratification and individual-level prediction among major depressive disorder (MDD) is important but unrecognized. Here, we construct models to detect suicidality in MDD using machine learning (ML) and whole-brain functional connectivity (FC).

METHODS

A cross-sectional assessment was conducted on 200 subjects, including 126 MDD with high suicide risk (HSR; 73 patients with suicidal ideation [SI], 53 patients with suicidal attempts [SA]), 36 patients with low suicide risk (LSR) and 38 healthy controls (HCs). Whole-brain FC features were calculated, the least absolute shrinkage and selection operator (LASSO) method was used for feature selection. A support vector machine (SVM) was performed to build models to distinguish MDD from HCs, and for suicide risk stratification among MDD. Leave-one-out cross-validation (LOOCV) was performed for validation.

RESULTS

The models constructed using SVM on whole-brain FC had powerful classification efficiency in screening MDD from HCs (accuracy = 88.50 %), and in suicide risk stratification among MDD patients (with accuracy = 84.56 % and 74.60 % in classifying patients with HSR or LSR, and SA or SI, respectively). Subsequent analysis demonstrated that intra-network dysconnectivity in the sensorimotor network and inter-network dysconnectivity between the default and dorsal attention network could characterize HSR and SA in MDD, separately.

LIMITATIONS

This study was a single center cohort study without external validation.

CONCLUSION

These findings indicate ML approaches are useful in suicide risk stratification among MDD based on whole-brain FC, which may help to identify individuals with different suicide risks in MDD and provide an individual-level prediction.

Cortical hierarchy disorganization in major depressive disorder and its association with suicidality

Objectives

To explore the suicide risk-specific disruption of cortical hierarchy in major depressive disorder (MDD) patients with diverse suicide risks.

Methods

Ninety-two MDD patients with diverse suicide risks and 38 matched controls underwent resting-state functional MRI. Connectome gradient analysis and stepwise functional connectivity (SFC) analysis were used to characterize the suicide risk-specific alterations of cortical hierarchy in MDD patients.

Results

Relative to controls, patients with suicide attempts (SA) had a prominent compression from the sensorimotor system; patients with suicide ideations (SI) had a prominent compression from the higher-level systems; non-suicide patients had a compression from both the sensorimotor system and higher-level systems, although it was less prominent relative to SA and SI patients. SFC analysis further validated this depolarization phenomenon.

Conclusion

This study revealed MDD patients had suicide risk-specific disruptions of cortical hierarchy, which advance our understanding of the neuromechanisms of suicidality in MDD patients.

Brain grey and white matter structural associations with future suicidal ideation and behaviors in adolescent and young adult females with mood disorders

Background

To reduce suicide in females with mood disorders, it is critical to understand brain substrates underlying their vulnerability to future suicidal ideation and behaviors (SIBs) in adolescence and young adulthood. In an international collaboration, grey and white matter structure was investigated in adolescent and young adult females with future suicidal behaviors (fSB) and ideation (fSI), and without SIBs (fnonSIB).

Methods

Structural (n = 91) and diffusion-weighted (n = 88) magnetic resonance imaging scans at baseline and SIB measures at follow-up on average two years later (standard deviation, SD = 1 year) were assessed in 92 females [age(SD) = 16.1(2.6) years] with bipolar disorder (BD, 28.3%) or major depressive disorder (MDD, 71.7%). One-way analyses of covariance comparing baseline regional grey matter cortical surface area, thickness, subcortical grey volumes, or white matter tensor-based fractional anisotropy across fSB (n = 40, 43.5%), fSI (n = 33, 35.9%) and fnonSIB (n = 19, 20.6%) groups were followed by pairwise comparisons in significant regions (p < 0.05).

Results

Compared to fnonSIBs, fSIs and fSBs showed significant decreases in cortical thickness of right inferior frontal gyrus pars orbitalis and middle temporal gyrus, fSIs of left inferior frontal gyrus, pars orbitalis. FSIs and fSBs showed lower fractional anisotropy in left uncinate fasciculus and corona radiata, and fSBs in right uncinate and superior fronto-occipital fasciculi.

Conclusions

The study provides preliminary evidence of grey and white matter alterations in brain regions subserving emotional and behavioral regulation and perceptual processing in adolescent and young adult females with mood disorders with, versus without, future SIBs. Findings suggest potential targets to prevent SIBs in female adolescents and young adults.

Identification of suicidality in patients with major depressive disorder via dynamic functional network connectivity signatures and machine learning

Major depressive disorder (MDD) is a severe brain disease associated with a significant risk of suicide. Identification of suicidality is sometimes life-saving for MDD patients. We aimed to explore the use of dynamic functional network connectivity (dFNC) for suicidality detection in MDD patients. A total of 173 MDD patients, including 48 without suicide risk (NS), 74 with suicide ideation (SI), and 51 having attempted suicide (SA), participated in the present study. Thirty-eight healthy controls were also recruited for comparison. A sliding window approach was used to derive the dFNC, and the K-means clustering method was used to cluster the windowed dFNC. A linear support vector machine was used for classification, and leave-one-out cross-validation was performed for validation. Other machine learning methods were also used for comparison. MDD patients had widespread hypoconnectivity in both the strongly connected states (states 2 and 5) and the weakly connected state (state 4), while the dysfunctional connectivity within the weakly connected state (state 4) was mainly driven by suicidal attempts. Furthermore, dFNC matrices, especially the weakly connected state, could be used to distinguish MDD from healthy controls (area under curve [AUC] = 82), and even to identify suicidality in MDD patients (AUC = 78 for NS vs. SI, AUC = 88 for NS vs. SA, and AUC = 74 for SA vs. SI), with vision-related and default-related inter-network connectivity serving as important features. Thus, the dFNC abnormalities observed in this study might further improve our understanding of the neural substrates of suicidality in MDD patients.

Correlates of suicidality in young people with depressive disorders: A systematic review

OBJECTIVE

Depression is one of the most prevalent and disabling mental health conditions among young people worldwide. The health and economic burdens associated with depressive illness are substantial. Suicide and depression are closely intertwined, yet a diagnosis of depression itself lacks predictive specificity for suicidal behaviour. To better inform suicide prevention and early intervention strategies for young people, improved identification of modifiable intervention targets is needed. The objective of this review was to identify clinical, psychosocial and biological correlates of suicidality in young people diagnosed with a broad range of unipolar and bipolar depressive disorders.

METHOD

Systematic searches were conducted across MEDLINE, Embase and PsycINFO to identify studies of young people aged 15-25 years diagnosed with unipolar or bipolar depressive disorders. An assessment of suicidality was required for inclusion. Reporting followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 and Synthesis Without Meta-analysis guidelines.

RESULTS

We integrated findings from 71 studies including approximately 24,670 young people with clinically diagnosed depression. We identified 26 clinical, psychosocial and biological correlates of suicidality. Depression characteristics (type and severity), psychiatric comorbidity (particularly anxiety and substance use disorders) and neurological characteristics emerged as having the most evidence for being associated with suicidal outcomes. Our ability to pool data and conduct meaningful quantitative synthesis was hampered by substantial heterogeneity across studies and incomplete reporting; thus, meta-analysis was not possible.

CONCLUSION

Findings of this review reinforce the notion that suicidality is a complex phenomenon arising from the interplay of multiple contributing factors. Our findings question the utility of considering a diagnosis of depression as a specific risk factor for suicidality in young people. Suicidality itself is transdiagnostic; adoption of a transdiagnostic approach to investigating its aetiology and treatment is perhaps warranted. Future research investigating specific symptoms, or symptom networks, might help to further our understanding of suicidality among young people experiencing mental illness.

Aberrant Dynamic Functional Connectivity of Posterior Cingulate Cortex Subregions in Major Depressive Disorder With Suicidal Ideation

Accumulating evidence indicates the presence of structural and functional abnormalities of the posterior cingulate cortex (PCC) in patients with major depressive disorder (MDD) with suicidal ideation (SI). Nevertheless, the subregional-level dynamic functional connectivity (dFC) of the PCC has not been investigated in MDD with SI. We therefore sought to investigate the presence of aberrant dFC variability in PCC subregions in MDD patients with SI. We analyzed resting-state functional magnetic resonance imaging (fMRI) data from 31 unmedicated MDD patients with SI (SI group), 56 unmedicated MDD patients without SI (NSI group), and 48 matched healthy control (HC) subjects. The sliding-window method was applied to characterize the whole-brain dFC of each PCC subregion [the ventral PCC (vPCC) and dorsal PCC (dPCC)]. In addition, we evaluated associations between clinical variables and the aberrant dFC variability of those brain regions showing significant between-group differences. Compared with HCS, the SI and the NSI groups exhibited higher dFC variability between the left dPCC and left fusiform gyrus and between the right vPCC and left inferior frontal gyrus (IFG). The SI group showed higher dFC variability between the left vPCC and left IFG than the NSI group. Furthermore, the dFC variability between the left vPCC and left IFG was positively correlated with Scale for Suicidal Ideation (SSI) score in patients with MDD (i.e., the SI and NSI groups). Our results indicate that aberrant dFC variability between the vPCC and IFG might provide a neural-network explanation for SI and may provide a potential target for future therapeutic interventions in MDD patients with SI.

Pain avoidance and functional connectivity between insula and amygdala identifies suicidal attempters in patients with major depressive disorder using machine learning

Pain avoidance can effectively classify suicide attempters from non-attempters among patients with major depressive disorder (MDD). However, the neural circuits underlying pain processing in suicide attempters have not been described comprehensively. In Study 1, we recruited MDD patients with a history of suicide attempts (MDD-SA), and those without (MDD-NSA) to examine the patterns of psychological pain using the latent profile analysis. Further, in Study 2, participants including the MDD-SA, MDD-NSA, and healthy controls underwent resting-state functional magnetic resonance imaging. We used machine learning that included features of gray matter volume (GMV), the functional connectivity (FC) brain patterns of the region of interest, and behavioral data to identify suicide attempters. The results identified three latent classes of psychological pain in MDD patients: the low pain class (18.9%), the painful feeling class (37.2%), and the pain avoidance class (43.9%). Furthermore, the proportion of suicide attempters with high pain avoidance was the highest. The accuracy of multimodality classifiers (63%-92%) was significantly higher than that of brain-only classifiers (56%-85%) and behavior-only classifiers (64%-73%). Pain avoidance ranked first in the optimal feature set of the suicide attempt classification model. The crucial brain imaging features were FC between the left amygdala and right insula, right orbitofrontal and left thalamus, left anterior cingulate cortex and left insula, right orbitofrontal, amygdala, and the GMV of right thalamus. Additionally, the optimal feature set, including pain avoidance and crucial brain patterns of psychological pain neural circuits, was provided for the identification of suicide attempters.

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.

Artificial Intelligence Tools for Suicide Prevention in Adolescents and Young Adults

Background:

Artificial Intelligence is making a significant transformation in human lives. Its application in the medical and healthcare field has been also observed making an impact and improving overall outcomes. There has been a quest for similar processes in mental health due to the lack of observable changes in the areas of suicide prevention. In the last five years, there has been an emerging body of empirical research applying the technology of artificial intelligence (AI) and machine learning (ML) in mental health.

Objective:

To review the clinical applicability of the AI/ML-based tools in suicide prevention.

Methods:

The compelling question of predicting suicidality has been the focus of this research. We performed a broad literature search and then identified 36 articles relevant to meet the objectives of this review. We review the available evidence and provide a brief overview of the advances in this field.

Conclusion:

In the last five years, there has been more evidence supporting the implementation of these algorithms in clinical practice. Its current clinical utility is limited to using electronic health records and could be highly effective in conjunction with existing tools for suicide prevention. Other potential sources of relevant data include smart devices and social network sites. There are some serious questions about data privacy and ethics which need more attention while developing these new modalities in suicide research.

Performance scaling for structural MRI surface parcellations: a machine learning analysis in the ABCD Study

The use of predefined parcellations on surface-based representations of the brain as a method for data reduction is common across neuroimaging studies. In particular, prediction-based studies typically employ parcellation-driven summaries of brain measures as input to predictive algorithms, but the choice of parcellation and its influence on performance is often ignored. Here we employed preprocessed structural magnetic resonance imaging (sMRI) data from the Adolescent Brain Cognitive Development Study® to examine the relationship between 220 parcellations and out-of-sample predictive performance across 45 phenotypic measures in a large sample of 9- to 10-year-old children (N = 9,432). Choice of machine learning (ML) pipeline and use of alternative multiple parcellation-based strategies were also assessed. Relative parcellation performance was dependent on the spatial resolution of the parcellation, with larger number of parcels (up to ~4,000) outperforming coarser parcellations, according to a power-law scaling of between 1/4 and 1/3. Performance was further influenced by the type of parcellation, ML pipeline, and general strategy, with existing literature-based parcellations, a support vector-based pipeline, and ensembling across multiple parcellations, respectively, as the highest performing. These findings highlight the choice of parcellation as an important influence on downstream predictive performance, showing in some cases that switching to a higher resolution parcellation can yield a relatively large boost to performance.

The Potential Impact of Adjunct Digital Tools and Technology to Help Distressed and Suicidal Men: An Integrative Review

Suicidal men feel the need to be self-reliant and that they cannot find another way out of relationship or socioeconomic issues. Suicide prevention is of crucial importance worldwide. The much higher rate of suicide in men engenders action. The prelude is a subjective experience that can be very isolating and severely distressing. Men may not realize a change in their thinking and behaviors, which makes it more difficult to seek and get help, thereby interrupting a "downward spiral". Stoicism often prevents men from admitting to their personal struggle. The lack of "quality" connections and "non-tailored" therapies has led to a high number of men "walking out" on traditional clinical approaches. But there are complicated relationships in motivations and formative behaviors of suicide with regards to emotional state, psychiatric disorders, interpersonal life events and suicidal behavior method selection. Middle-aged and older men have alternated as the most at-risk of suicide. There is no one solution that applies to all men, but digital tools may be of assistance (e.g., video conferences, social networks, telephone calls, and emails). Digital interventions require higher levels of effectiveness for distress and suicidality but self-guided approaches may be the most suitable for men especially where linked with an integrated online suicide prevention platform (e.g., quick response with online chats, phone calls, and emails). Furthermore, technology-enabled models of care offer promise to advance appropriate linking to mental health services through better and faster understanding of the specific needs of individuals (e.g., socio-cultural) and the type and level of suicidality experienced. Long-term evidence for suicidality and its evaluation may benefit from progressing human computer-interaction and providing impetus for an eminent integrated digital platform.

Effects of polygenic risk for suicide attempt and risky behavior on brain structure in young people with familial risk of bipolar disorder

Bipolar disorder (BD) is associated with a 20-30-fold increased suicide risk compared to the general population. First-degree relatives of BD patients show inflated rates of psychopathology including suicidal behaviors. As reliable biomarkers of suicide attempts (SA) are lacking, we examined associations between suicide-related polygenic risk scores (PRSs)-a quantitative index of genomic risk-and variability in brain structures implicated in SA. Participants (n = 206; aged 12-30 years) were unrelated individuals of European ancestry and comprised three groups: 41 BD cases, 96 BD relatives ("high risk"), and 69 controls. Genotyping employed PsychArray, followed by imputation. Three PRSs were computed using genome-wide association data for SA in BD (SA-in-BD), SA in major depressive disorder (SA-in-MDD) (Mullins et al., 2019, The American Journal of Psychiatry, 176(8), 651-660), and risky behavior (Karlsson Linnér et al., 2019, Nature Genetics, 51(2), 245-257). Structural magnetic resonance imaging processing employed FreeSurfer v5.3.0. General linear models were constructed using 32 regions-of-interest identified from suicide neuroimaging literature, with false-discovery-rate correction. SA-in-MDD and SA-in-BD PRSs negatively predicted parahippocampal thickness, with the latter association modified by group membership. SA-in-BD and Risky Behavior PRSs inversely predicted rostral and caudal anterior cingulate structure, respectively, with the latter effect driven by the "high risk" group. SA-in-MDD and SA-in-BD PRSs positively predicted cuneus structure, irrespective of group. This study demonstrated associations between PRSs for suicide-related phenotypes and structural variability in brain regions implicated in SA. Future exploration of extended PRSs, in conjunction with a range of biological, phenotypic, environmental, and experiential data in high risk populations, may inform predictive models for suicidal behaviors.

Understanding complex functional wiring patterns in major depressive disorder through brain functional connectome

Brain function relies on efficient communications between distinct brain systems. The pathology of major depressive disorder (MDD) damages functional brain networks, resulting in cognitive impairment. Here, we reviewed the associations between brain functional connectome changes and MDD pathogenesis. We also highlighted the utility of brain functional connectome for differentiating MDD from other similar psychiatric disorders, predicting recurrence and suicide attempts in MDD, and evaluating treatment responses. Converging evidence has now linked aberrant brain functional network organization in MDD to the dysregulation of neurotransmitter signaling and neuroplasticity, providing insights into the neurobiological mechanisms of the disease and antidepressant efficacy. Widespread connectome dysfunctions in MDD patients include multiple, large-scale brain networks as well as local disturbances in brain circuits associated with negative and positive valence systems and cognitive functions. Although the clinical utility of the brain functional connectome remains to be realized, recent findings provide further promise that research in this area may lead to improved diagnosis, treatments, and clinical outcomes of MDD.

Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review

Artificial intelligence (AI) for medical imaging is a technology with great potential. An in-depth understanding of the principles and applications of magnetic resonance imaging (MRI), machine learning (ML), and deep learning (DL) is fundamental for developing AI-based algorithms that can meet the requirements of clinical diagnosis and have excellent quality and efficiency. Moreover, a more comprehensive understanding of applications and opportunities would help to implement AI-based methods in an ethical and sustainable manner. This review first summarizes recent research advances in ML and DL techniques for classifying human brain magnetic resonance images. Then, the application of ML and DL methods to six typical neurological and psychiatric diseases is summarized, including Alzheimer's disease (AD), Parkinson's disease (PD), major depressive disorder (MDD), schizophrenia (SCZ), attention-deficit/hyperactivity disorder (ADHD), and autism spectrum disorder (ASD). Finally, the limitations of the existing research are discussed, and possible future research directions are proposed.

Incidence Trends and Risk Prediction Nomogram for Suicidal Attempts in Patients With Major Depressive Disorder

Background: Major depressive disorder (MDD) is often associated with suicidal attempt (SA). Therefore, predicting the risk factors of SA would improve clinical interventions, research, and treatment for MDD patients. This study aimed to create a nomogram model which predicted correlates of SA in patients with MDD within the Chinese population. Method: A cross-sectional survey among 474 patients was analyzed. All subjects met the diagnostic criteria of MDD according to the International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10). Multi-factor logistic regression analysis was used to explore demographic information and clinical characteristics associated with SA. A nomogram was further used to predict the risk of SA. Bootstrap re-sampling was used to internally validate the final model. Integrated Discrimination Improvement (IDI) and Akaike Information Criteria (AIC) were used to evaluate the capability of discrimination and calibration, respectively. Decision Curve Analysis (DCA) and the Receiver Operating Characteristic (ROC) curve was also used to evaluate the accuracy of the prediction model. Result: Multivariable logistic regression analysis showed that being married (OR = 0.473, 95% CI: 0.240 and 0.930) and a higher level of education (OR = 0.603, 95% CI: 0.464 and 0.784) decreased the risk of the SA. The higher number of episodes of depression (OR = 1.854, 95% CI: 1.040 and 3.303) increased the risk of SA in the model. The C-index of the nomogram was 0.715, with the internal (bootstrap) validation sets was 0.703. The Hosmer-Lemeshow test yielded a P-value of 0.33, suggesting a good fit of the prediction nomogram in the validation set. Conclusion: Our findings indicate that the demographic information and clinical characteristics of SA can be used in a nomogram to predict the risk of SA in Chinese MDD patients.