Classification of Social Anxiety Disorder With Support Vector Machine Analysis Using Neural Correlates of Social Signals of Threat

Lifestyle factors and other predictors of common mental disorders in diagnostic machine learning studies: A systematic review

BACKGROUND

Machine Learning (ML) models have been used to predict common mental disorders (CMDs) and may provide insights into the key modifiable factors that can identify and predict CMD risk and be targeted through interventions. This systematic review aimed to synthesise evidence from ML studies predicting CMDs, evaluate their performance, and establish the potential benefit of incorporating lifestyle data in ML models alongside biological and/or demographic-environmental factors.

METHODS

This systematic review adheres to the PRISMA statement (Prospero CRD42023401194). Databases searched included MEDLINE, EMBASE, PsycInfo, IEEE Xplore, Engineering Village, Web of Science, and Scopus from database inception to 28/08/24. Included studies used ML methods with feature importance to predict CMDs in adults. Risk of bias (ROB) was assessed using PROBAST. Model performance metrics were compared. The ten most important variables reported by each study were assigned to broader categories to evaluate their frequency across studies.

RESULTS

117 studies were included (111 model development-only, 16 development and validation). Deep learning methods showed best accuracy for predicting CMD cases. Studies commonly incorporated features from multiple categories (n = 56), and frequently identified demographic-environmental predictors in their top ten most important variables (63/69 models). These tended to be in combination with psycho-social and biological variables (n = 15). Lifestyle data were infrequently examined as sole predictors of CMDs across included studies (4.27 %). Studies commonly had high heterogeneity and ROB ratings.

CONCLUSION

This review is the first to evaluate the utility of diagnostic ML for CMDs, assess their ROB, and evaluate predictor types. CMDs were able to be predicted, however studies had high ROB and lifestyle data were underutilised, precluding full identification of a robust predictor set.

Machine learning applied to functional magnetic resonance imaging in anxiety disorders

BACKGROUND

Brain functional abnormalities have been commonly reported in anxiety disorders, including generalized anxiety disorder, social anxiety disorder, panic disorder, agoraphobia, and specific phobias. The role of functional abnormalities in the discrimination of these disorders can be tested with machine learning (ML) techniques. Here, we aim to provide a comprehensive overview of ML studies exploring the potential discriminating role of functional brain alterations identified by functional magnetic resonance imaging (fMRI) in anxiety disorders.

METHODS

We conducted a search on PubMed, Web of Science, and Scopus of ML investigations using fMRI as features in patients with anxiety disorders. A total of 12 studies (resting-state fMRI n = 5, task-based fMRI n = 6, resting-state and task-based fMRI n=1) met our inclusion criteria.

RESULTS

Overall, the studies showed that, regardless of the classifiers, alterations in functional connectivity and aberrant neural activation involving the amygdala, anterior cingulate cortex, hippocampus, insula, orbitofrontal cortex, temporal pole, cerebellum, default mode network, dorsal attention network, sensory network, and affective network were able to discriminate patients with anxiety from controls, with accuracies spanning from 36 % to 94 %.

LIMITATIONS

The small sample size, different ML approaches and heterogeneity in the selection of regions included in the multivariate pattern analyses limit the conclusions of the present review.

CONCLUSIONS

ML methods using fMRI as features can distinguish patients with anxiety disorders from healthy controls, indicating that these techniques could be used as a helpful tool for the diagnosis and the development of more targeted treatments for these disorders.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Anxiety onset in adolescents: a machine-learning prediction

Recent longitudinal studies in youth have reported MRI correlates of prospective anxiety symptoms during adolescence, a vulnerable period for the onset of anxiety disorders. However, their predictive value has not been established. Individual prediction through machine-learning algorithms might help bridge the gap to clinical relevance. A voting classifier with Random Forest, Support Vector Machine and Logistic Regression algorithms was used to evaluate the predictive pertinence of gray matter volumes of interest and psychometric scores in the detection of prospective clinical anxiety. Participants with clinical anxiety at age 18-23 (N = 156) were investigated at age 14 along with healthy controls (N = 424). Shapley values were extracted for in-depth interpretation of feature importance. Prospective prediction of pooled anxiety disorders relied mostly on psychometric features and achieved moderate performance (area under the receiver operating curve = 0.68), while generalized anxiety disorder (GAD) prediction achieved similar performance. MRI regional volumes did not improve the prediction performance of prospective pooled anxiety disorders with respect to psychometric features alone, but they improved the prediction performance of GAD, with the caudate and pallidum volumes being among the most contributing features. To conclude, in non-anxious 14 year old adolescents, future clinical anxiety onset 4-8 years later could be individually predicted. Psychometric features such as neuroticism, hopelessness and emotional symptoms were the main contributors to pooled anxiety disorders prediction. Neuroanatomical data, such as caudate and pallidum volume, proved valuable for GAD and should be included in prospective clinical anxiety prediction in adolescents.

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

BACKGROUND

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Cognitive Neural Mechanism of Social Anxiety Disorder: A Meta-Analysis Based on fMRI Studies

Objective: The present meta-analysis aimed to explore the cognitive and neural mechanism of social anxiety disorder (SAD) from a whole-brain view, and compare the differences in brain activations under different task paradigms. Methods: We searched Web of Science Core Collection and other databases with the keywords related to social anxiety, social phobia, and functional magnetic resonance imaging (fMRI) for comparing persons with SAD to healthy controls and used the activation likelihood estimation method. Thirty-seven papers met the inclusion criteria, including 15 with emotional faces as stimuli, 8 presenting specific situations as stimuli, and 14 using other types of tasks as stimuli. Among these papers, 654 participants were in the SAD group and 594 participants were in the control group with 335 activation increase points and 115 activation decrease points. Results: Whole-brain analysis showed that compared with healthy controls, persons with SAD showed significantly lower activation of the left anterior cingulate gyrus (MNI coordinate: x = −6, y = 22, z = 38; p 0.001). Sub-group analysis based on task indicated that when performing tasks with emotional faces as stimuli, persons with SAD showed significantly lower activation of the left cerebellar slope and fusiform gyrus (MNI coordinate: x = −26, y = −68, z = −12; p 0.001), and significantly higher activation of the right supramarginal gyrus and angular gyrus, than healthy controls (MNI coordinate: x = 58, y = −52, z = 30; p 0.001). Conclusion: Individuals with social anxiety disorder show abnormal activation in the cingulate gyrus, which is responsible for the process of attention control, and task type can influence the activation pattern.