Machine-learning-based classification between post-traumatic stress disorder and major depressive disorder using P300 features

P300 parameters in major depressive disorder: A systematic review and meta-analysis

OBJECTIVES

Event-related potential measures have been extensively studied in mental disorders. Among them, P300 amplitude and latency reflect impaired cognitive abilities in major depressive disorder (MDD). The present systematic review and meta-analysis was conducted to investigate whether patients with MDD differ from healthy controls (HCs) with respect to P300 amplitude and latency.

METHODS

PubMed and Web of Science databases were searched from inception to 15 January 2023 for case-control studies comparing P300 amplitude and latency in patients with MDD and HCs. The primary outcome was the standard mean difference. A total of 13 articles on P300 amplitude and latency were included in the meta-analysis.

RESULTS

Random effect models indicated that MDD patients had decreased P300 amplitude, but similar latency compared to healthy controls. According to regression analysis, the effect size increased with the severity of depression and decreased with the proportion of women in the MDD samples. Funnel plot asymmetry was not significant for publication bias.

CONCLUSIONS

Decreased P300 amplitude may be a candidate diagnostic biomarker for MDD. However, prospective studies testing P300 amplitude as a monitoring biomarker for MDD are needed.

Testing the bipolar assumption of Singer-Loomis Type Deployment Inventory for Korean adults using classification and multidimensional scaling

In this study, we explored whether the Korean version of Singer Loomis Type Deployment Inventory II (K-SLTDI) captures the opposing tendencies of Jung's theory of psychological type. The types are Extroverted Sensing, Extroverted Intuition, Extroverted Feeling, Extroverted Thinking, Introverted Sensing, Introverted Intuition, Introverted Feeling, and Introverted Thinking. A nationwide online survey was conducted in South Korea. We performed multidimensional scaling and classification analyses based on 521 Korean adult profiles with eight psychological types to test the bipolarity assumption. The results showed that the Procrustes-rotated four-dimensional space successfully represented four types of opposing tendencies. Moreover, the bipolarity assumption in the four dimensions of Jungian typology was tested and compared between lower and higher psychological distress populations via cluster analysis. Lastly, we explored patterns of responses in lower and higher psychological distress populations using intersubject correlation. Both similarity analyses and classification results consistently support the theoretical considerations on the conceptualization of Jung's type in independent order that the types could be derived without bipolar assumption as Singer and Loomis expected in their Type Development Inventory. Limitations in our study include the sample being randomly selected internet users during the COVID-19 pandemic, despite excellence in the use of the internet in the general Korean population.

Systematic review of machine learning in PTSD studies for automated diagnosis evaluation

Post-traumatic stress disorder (PTSD) is frequently underdiagnosed due to its clinical and biological heterogeneity. Worldwide, many people face barriers to accessing accurate and timely diagnoses. Machine learning (ML) techniques have been utilized for early assessments and outcome prediction to address these challenges. This paper aims to conduct a systematic review to investigate if ML is a promising approach for PTSD diagnosis. In this review, statistical methods were employed to synthesize the outcomes of the included research and provide guidance on critical considerations for ML task implementation. These included (a) selection of the most appropriate ML model for the available dataset, (b) identification of optimal ML features based on the chosen diagnostic method, (c) determination of appropriate sample size based on the distribution of the data, and (d) implementation of suitable validation tools to assess the performance of the selected ML models. We screened 3186 studies and included 41 articles based on eligibility criteria in the final synthesis. Here we report that the analysis of the included studies highlights the potential of artificial intelligence (AI) in PTSD diagnosis. However, implementing AI-based diagnostic systems in real clinical settings requires addressing several limitations, including appropriate regulation, ethical considerations, and protection of patient privacy.

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.

Adolescent ADHD and electrophysiological reward responsiveness: A machine learning approach to evaluate classification accuracy and prognosis

We evaluated event-related potential (ERP) indices of reinforcement sensitivity as ADHD biomarkers by examining, in N=306 adolescents (M_age=15.78, SD=1.08), the extent to which ERP amplitude and latency variables measuring reward anticipation and response (1) differentiate, in age- and sex-matched subsamples, (i) youth with vs. without ADHD, (ii) youth at-risk for vs. not at-risk for ADHD, and, in the with ADHD subsample, (iii) youth with the inattentive vs. the hyperactive/impulsive (H/I) and combined presentations. We further examined the extent to which ERP variables (2) predict, in the ADHD subsample, substance use (i) concurrently and (ii) prospectively at 18-month follow-up. Linear support vector machine analyses indicated ERPs weakly differentiate youth with/without (65%) - and at-risk for/not at-risk for (63%) - ADHD but better differentiate ADHD presentations (78%). Regression analyses showed in adolescents with ADHD, ERPs explain a considerable proportion of variance (50%) in concurrent alcohol use and, controlling for concurrent marijuana and tobacco use, explain a considerable proportion of variance (87 and 87%) in, and predict later marijuana and tobacco use. Findings are consistent with the dual-pathway model of ADHD. Results also highlight limitations of a dichotomous, syndromic classification and indicate differences in neural reinforcement sensitivity are a promising ADHD prognostic biomarker.

Heart and brain traumatic stress biomarker analysis with and without machine learning: A scoping review

The enigma of post-traumatic stress disorder (PTSD) is embedded in a complex array of physiological responses to stressful situations that result in disruptions in arousal and cognitions that characterise the psychological disorder. Deciphering these physiological patterns is complex, which has seen the use of machine learning (ML) grow in popularity. However, it is unclear to what extent ML has been used with physiological data, specifically, the electroencephalogram (EEG) and electrocardiogram (ECG) to further understand the physiological responses associated with PTSD. To better understand the use of EEG and ECG biomarkers, with and without ML, a scoping review was undertaken. A total of 124 papers based on adult samples were identified comprising 19 ML studies involving EEG and ECG. A further 21 studies using EEG data, and 84 studies employing ECG meeting all other criteria but not employing ML were included for comparison. Identified studies indicate classical ML methodologies currently dominate EEG and ECG biomarkers research, with derived biomarkers holding clinically relevant diagnostic implications for PTSD. Discussion of the emerging trends, algorithms used and their success is provided, along with areas for future research.

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.

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.

Enhanced Performance by Interpretable Low-Frequency Electroencephalogram Oscillations in the Machine Learning-Based Diagnosis of Post-traumatic Stress Disorder

Electroencephalography (EEG)-based diagnosis of psychiatric diseases using machine-learning approaches has made possible the objective diagnosis of various psychiatric diseases. The objective of this study was to improve the performance of a resting-state EEG-based computer-aided diagnosis (CAD) system to diagnose post-traumatic stress disorder (PTSD), by optimizing the frequency bands used to extract EEG features. We used eyes-closed resting-state EEG data recorded from 77 PTSD patients and 58 healthy controls (HC). Source-level power spectrum densities (PSDs) of the resting-state EEG data were extracted from 6 frequency bands (delta, theta, alpha, low-beta, high-beta, and gamma), and the PSD features of each frequency band and their combinations were independently used to discriminate PTSD and HC. The classification performance was evaluated using support vector machine with leave-one-out cross validation. The PSD features extracted from slower-frequency bands (delta and theta) showed significantly higher classification performance than those of relatively higher-frequency bands. The best classification performance was achieved when using delta PSD features (86.61%), which was significantly higher than that reported in a recent study by about 13%. The PSD features selected to obtain better classification performances could be explained from a neurophysiological point of view, demonstrating the promising potential to develop a clinically reliable EEG-based CAD system for PTSD diagnosis.

A combination of P300 and eye movement data improves the accuracy of auxiliary diagnoses of depression

BACKGROUND

Exploratory eye movements (EEMs) and P300 are often used to facilitate the clinical diagnosis of depression. However, There were few studies using the combination of EEMs and P300 to build a model for detecting depression and predicting a curative effect.

METHODS

Sixty patients were recruited for 2 groups: high frequency repetitive transcranial magnetic stimulation(rTMS) combined with paroxetine group and simple paroxetine group. Clinical efficacy was evaluated by the Hamilton Depression scale-24(HAMD-24), EEMs and P300. The classification model of the auxiliary diagnosis of depression and the prediction model of the two treatments were developed based on a machine learning algorithm.

RESULTS

The classification model with the greatest accuracy for patients with depression and healthy controls was 95.24% (AUC = 0.75, recall = 1.00, precision = 0.95, F1-score = 0.97). The root mean square error (RMSE) of the model for predicting the efficacy of high frequency rTMS combined with paroxetine was 3.54 (MAE [mean absolute error] = 2.56, R² = -0.53). The RMSE of the model for predicting the efficacy of paroxetine was 4.97 (MAE = 4.00, R² = -0.91).

CONCLUSION

Based on the machine learning algorithm, P300 and EEMs data was suitable for modeling to distinguish depression patients and healthy individuals. However, it was not suitable for predicting the efficacy of high frequency rTMS combined with paroxetine or to predict the efficacy of paroxetine.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

Machine-learning-based diagnosis of drug-naive adult patients with attention-deficit hyperactivity disorder using mismatch negativity

Relatively little is investigated regarding the neurophysiology of adult attention-deficit/hyperactivity disorder (ADHD). Mismatch negativity (MMN) is an event-related potential component representing pre-attentive auditory processing, which is closely associated with cognitive status. We investigated MMN features as biomarkers to classify drug-naive adult patients with ADHD and healthy controls (HCs). Sensor-level features (amplitude and latency) and source-level features (source activation) of MMN were investigated and compared between the electroencephalograms of 34 patients with ADHD and 45 HCs using a passive auditory oddball paradigm. Correlations between MMN features and ADHD symptoms were analyzed. Finally, we applied machine learning to differentiate the two groups using sensor- and source-level features of MMN. Adult patients with ADHD showed significantly lower MMN amplitudes at the frontocentral electrodes and reduced MMN source activation in the frontal, temporal, and limbic lobes, which were closely associated with MMN generators and ADHD pathophysiology. Source activities were significantly correlated with ADHD symptoms. The best classification performance for adult ADHD patients and HCs showed an 81.01% accuracy, 82.35% sensitivity, and 80.00% specificity based on MMN source activity features. Our results suggest that abnormal MMN reflects the adult ADHD patients' pathophysiological characteristics and might serve clinically as a neuromarker of adult ADHD.

Teasing apart trauma: neural oscillations differentiate individual cases of mild traumatic brain injury from post-traumatic stress disorder even when symptoms overlap

Post-traumatic stress disorder (PTSD) and mild traumatic brain injury (mTBI) are highly prevalent and closely related disorders. Affected individuals often exhibit substantially overlapping symptomatology - a major challenge for differential diagnosis in both military and civilian contexts. According to our symptom assessment, the PTSD group exhibited comparable levels of concussion symptoms and severity to the mTBI group. An objective and reliable system to uncover the key neural signatures differentiating these disorders would be an important step towards translational and applied clinical use. Here we explore use of MEG (magnetoencephalography)-multivariate statistical learning analysis in identifying the neural features for differential PTSD/mTBI characterisation. Resting state MEG-derived regional neural activity and coherence (or functional connectivity) across seven canonical neural oscillation frequencies (delta to high gamma) were used. The selected features were consistent and largely confirmatory with previously established neurophysiological markers for the two disorders. For regional power from theta, alpha and high gamma bands, the amygdala, hippocampus and temporal areas were identified. In line with regional activity, additional connections within the occipital, parietal and temporal regions were selected across a number of frequency bands. This study is the first to employ MEG-derived neural features to reliably and differentially stratify the two disorders in a multi-group context. The features from alpha and beta bands exhibited the best classification performance, even in cases where distinction by concussion symptom profiles alone were extremely difficult. We demonstrate the potential of using 'invisible' neural indices of brain functioning to understand and differentiate these debilitating conditions.

Identification of Major Psychiatric Disorders From Resting-State Electroencephalography Using a Machine Learning Approach

We aimed to develop a machine learning (ML) classifier to detect and compare major psychiatric disorders using electroencephalography (EEG). We retrospectively collected data from medical records, intelligence quotient (IQ) scores from psychological assessments, and quantitative EEG (QEEG) at resting-state assessments from 945 subjects [850 patients with major psychiatric disorders (six large-categorical and nine specific disorders) and 95 healthy controls (HCs)]. A combination of QEEG parameters including power spectrum density (PSD) and functional connectivity (FC) at frequency bands was used to establish models for the binary classification between patients with each disorder and HCs. The support vector machine, random forest, and elastic net ML methods were applied, and prediction performances were compared. The elastic net model with IQ adjustment showed the highest accuracy. The best feature combinations and classification accuracies for discrimination between patients and HCs with adjusted IQ were as follows: schizophrenia = alpha PSD, 93.83%; trauma and stress-related disorders = beta FC, 91.21%; anxiety disorders = whole band PSD, 91.03%; mood disorders = theta FC, 89.26%; addictive disorders = theta PSD, 85.66%; and obsessive-compulsive disorder = gamma FC, 74.52%. Our findings suggest that ML in EEG may predict major psychiatric disorders and provide an objective index of psychiatric disorders.

Virtual Reality-Based Treatment for Military Members and Veterans With Combat-Related Posttraumatic Stress Disorder: Protocol for a Multimodular Motion-Assisted Memory Desensitization and Reconsolidation Randomized Controlled Trial

Background

Military members are at elevated risk of operational stress injuries, including posttraumatic stress disorder (PTSD) and moral injury. Although psychotherapy can reduce symptoms, some military members may experience treatment-resistant PTSD. Multimodular motion-assisted memory desensitization and reconsolidation (3MDR) has been introduced as a virtual reality (VR) intervention for military members with PTSD related to military service. The 3MDR intervention incorporates exposure therapy, psychotherapy, eye movement desensitization and reconsolidation, VR, supportive counselling, and treadmill walking.

Objective

The objective of this study is to investigate whether 3MDR reduces PTSD symptoms among military members with combat-related treatment-resistant PTSD (TR-PTSD); examine the technology acceptance and usability of the Computer Assisted Rehabilitation ENvironment (CAREN) and 3MDR interventions by Canadian Armed Forces service members (CAF-SMs), veterans, 3MDR clinicians, and operators; and evaluate the impact on clinicians and operators of delivering 3MDR.

Methods

This is a mixed-methods waitlist controlled crossover design randomized controlled trial. Participants include both CAF-SMs and veterans (N=40) aged 18-60 years with combat-related TR-PTSD (unsuccessful experience of at least 2 evidence-based trauma treatments). Participants will also include clinicians and operators (N=12) who have been trained in 3MDR and subsequently utilized this intervention with patients. CAF-SMs and veterans will receive 6 weekly 90-minute 3MDR sessions. Quantitative and qualitative data will be collected at baseline and at 1, 3, and 6 months postintervention. Quantitative data collection will include multiomic biomarkers (ie, blood and salivary proteomic and genomic profiles of neuroendocrine, immune-inflammatory mediators, and microRNA), eye tracking, electroencephalography, and physiological data. Data from outcome measures will capture self-reported symptoms of PTSD, moral injury, resilience, and technology acceptance and usability. Qualitative data will be collected from audiovisual recordings of 3MDR sessions and semistructured interviews. Data analysis will include univariate and multivariate approaches, and thematic analysis of treatment sessions and interviews. Machine learning analysis will be included to develop models for the prediction of diagnosis, symptom severity, and treatment outcomes.

Results

This study commenced in April 2019 and is planned to conclude in April 2021. Study results will guide the further evolution and utilization of 3MDR for military members with TR-PTSD and will have utility in treating other trauma-affected populations.

Conclusions

The goal of this study is to utilize qualitative and quantitative primary and secondary outcomes to provide evidence for the effectiveness and feasibility of 3MDR for treating CAF-SMs and veterans with combat-related TR-PTSD. The results will inform a full-scale clinical trial and stimulate development and adaptation of the protocol to mobile VR apps in supervised clinical settings. This study will add to knowledge of the clinical effectiveness of 3MDR, and provide the first comprehensive analysis of biomarkers, technology acceptance and usability, moral injury, resilience, and the experience of clinicians and operators delivering 3MDR.

Trial Registration

ISRCTN Registry 11264368; http://www.isrctn.com/ISRCTN11264368.

International Registered Report Identifier (IRRID)

DERR1-10.2196/20620