Machine-learning-based classification of obstructive sleep apnea using 19-channel sleep EEG data.

OBJECTIVE: This study aimed to investigate the neurophysiological effects of obstructive sleep apnea (OSA) using multi-channel sleep electroencephalography (EEG) through machine learning methods encompassing various analysis methodologies including power spectral analysis, network analysis, and microstate analysis. METHODS: Twenty participants with apnea-hypopnea index (AHI) ≥ 15 and 18 participants with AHI <15 were recruited. Overnight polysomnography was conducted concurrently with 19-channel EEG. Preprocessed EEG data underwent computation of relative spectral power. A weighted network based on graph theory was generated; and indices of strength, path length, eigenvector centrality, and clustering coefficient were calculated. Microstate analysis was conducted to derive four topographic maps. Machine learning techniques were employed to assess EEG features capable of differentiating two groups. RESULTS: Among 71 features that showed significant differences between the two groups, seven exhibited good classification performance, achieving 88.3 % accuracy, 92 % sensitivity, and 84 % specificity. These features were power at C4 theta, P3 theta, P4 theta, and F8 gamma during NREM1 sleep and at Pz gamma during REM sleep from power spectral analysis; eigenvector centrality at F7 gamma during REM sleep from network analysis; and duration of microstate 4 during NREM2 sleep from microstate analysis. These seven EEG features were significantly correlated with polysomnographic parameters reflecting the severity of OSA. CONCLUSIONS: The application of machine learning techniques and various EEG analytical methods resulted in a model that showed good performance in classifying moderate to severe OSA and highlights the potential of EEG to serve as a biomarker of functional changes in OSA.

Electroencephalography-based endogenous phenotype of diagnostic transition from major depressive disorder to bipolar disorder.

The neuropathology of mood disorders, including the diagnostic transition from major depressive disorder (MDD) to bipolar disorder (BD), is poorly understood. This study investigated resting-state electroencephalography (EEG) activity in patients with MDD and those whose diagnosis changed from MDD to BD. Among sixty-eight enrolled patients with MDD, the diagnosis of 17 patients converted to BD during the study period. We applied machine learning techniques to differentiate the two groups using sensor- and source-level EEG features. At the sensor level, patients with BD showed higher theta band power at the AF3 channel and low-alpha band power at the FC5 channel compared to patients with MDD. At the source level, patients with BD showed higher theta band activity in the right anterior cingulate and low-alpha band activity in the left parahippocampal gyrus. These four EEG features were selected for discriminating between BD and MDD with the best classification performance showing an accuracy of 80.88%, a sensitivity of 76.47%, and a specificity of 82.35%. Our findings revealed distinct theta and low-alpha band activities in patients with BD and MDD. These differences could potentially serve as candidate neuromarkers for the diagnosis and diagnostic transition between the two distinct mood disorders.

P1 and N1 Characteristics in Individuals with Normal Hearing and Hearing Loss, and Cochlear Implant Users: A Pilot Study.

Background: It has been reported in many previous studies that the lack of auditory input due to hearing loss (HL) can induce changes in the brain. However, most of these studies have focused on individuals with pre-lingual HL and have predominantly compared the characteristics of those with normal hearing (NH) to cochlear implant (CI) users in children. This study examined the visual and auditory evoked potential characteristics in NH listeners, individuals with bilateral HL, and CI users, including those with single-sided deafness. Methods: A total of sixteen participants (seven NH listeners, four individuals with bilateral sensorineural HL, and five CI users) completed speech testing in quiet and noise and evoked potential testing. For speech testing, the Korean version of the Hearing in Noise Test was used to assess individuals' speech understanding ability in quiet and in noise (noise from the front, +90 degrees, and -90 degrees). For evoked potential testing, visual and auditory (1000 Hz, /ba/, and /da/) evoked potentials were measured. Results: The results showed that CI users understood speech better than those with HL in all conditions except for the noise from +90 and -90 degrees. In the CI group, a decrease in P1 amplitudes was noted across all channels after implantation. The NH group exhibited the highest amplitudes, followed by the HL group, with the CI group (post-CI) showing the lowest amplitudes. In terms of auditory evoked potentials, the smallest amplitude was observed in the pre-CI condition regardless of the type of stimulus. Conclusions: To the best of our knowledge, this is the first study that examined visual and auditory evoked potentials based on various hearing profiles. The characteristics of evoked potentials varied across participant groups, and further studies with CI users are necessary, as there are significant challenges in collecting and analyzing evoked potentials due to artifact issues on the CI side.

How to Solve Clinical Challenges in Mood Disorders; Machine Learning Approaches Using Electrophysiological Markers.

Differentiating between the diagnoses of mood disorders and other psychiatric disorders, and predicting treatment response in depression has long been a concern for clinicians. Machine learning (ML) is one part of artificial intelligence that focuses on instructing computers to mimic the cognitive abilities of the human brain through training. This study will review the research on the use of ML techniques to differentiate diagnoses and predict treatment responses in mood disorders based on electroencephalography (EEG) data. There have been several attempts to differentiate between the diagnoses of bipolar disorder and major depressive disorder , mood disorders, and other psychiatric disorders using ML techniques found on EEG markers. Previous studies have shown that accuracy varies depending on which EEG markers are used, the sample size, and the ML technique. Also, precise and improved ML approaches can be developed by adapting the various feature selection and validation methods that reflect each disease's characteristics. Although ML faces some limitations and challenges in solving for consistent and improved accuracy in the diagnosis and treatment of mood disorders, it has a great potential to understand mood disorders better and provide valuable tools to personalize both identification and treatment.

Comparative analysis of resting-state EEG-based multiscale entropy between schizophrenia and bipolar disorder.

BACKGROUND: Studies that use nonlinear methods to identify abnormal brain dynamics in patients with psychiatric disorders are limited. This study investigated brain dynamics based on EEG using multiscale entropy (MSE) analysis in patients with schizophrenia (SZ) and bipolar disorder (BD). METHODS: The eyes-closed resting-state EEG data were collected from 51 patients with SZ, 51 patients with BD, and 51 healthy controls (HCs). Patients with BD were further categorized into type I (n = 23) and type II (n = 16), and then compared with patients with SZ. A sample entropy-based MSE was evaluated from the bilateral frontal, central, and parieto-occipital regions using 30-s artifact-free EEG data for each individual. Correlation analyses of MSE values and psychiatric symptoms were performed. RESULTS: For patients with SZ, higher MSE values were observed at higher-scale factors (i.e., 41-70) across all regions compared with both HCs and patients with BD. Furthermore, there were positive correlations between the MSE values in the left frontal and parieto-occipital regions and PANSS scores. For patients with BD, higher MSE values were observed at middle-scale factors (i.e., 13-40) in the bilateral frontal and central regions compared with HCs. Patients with BD type I exhibited higher MSE values at higher-scale factors across all regions compared with those with BD type II. In BD type I, positive correlations were found between MSE values in all left regions and YMRS scores. CONCLUSIONS: Patients with psychiatric disorders exhibited group-dependent MSE characteristics. These results suggest that MSE features may be useful biomarkers that reflect pathophysiological characteristics.

Differentiation between suicide attempt and suicidal ideation in patients with major depressive disorder using cortical functional network.

Studies exploring the neurophysiology of suicide are scarce and the neuropathology of related disorders is poorly understood. This study investigated source-level cortical functional networks using resting-state electroencephalography (EEG) in drug-naïve depressed patients with suicide attempt (SA) and suicidal ideation (SI). EEG was recorded in 55 patients with SA and in 54 patients with SI. Particularly, all patients with SA were evaluated using EEG immediately after their SA (within 7 days). Graph-theory-based source-level weighted functional networks were assessed using strength, clustering coefficient (CC), and path length (PL) in seven frequency bands. Finally, we applied machine learning to differentiate between the two groups using source-level network features. At the global level, patients with SA showed lower strength and CC and higher PL in the high alpha band than those with SI. At the nodal level, compared with patients with SI, patients with SA showed lower high alpha band nodal CCs in most brain regions. The best classification performances for SA and SI showed an accuracy of 73.39%, a sensitivity of 76.36%, and a specificity of 70.37% based on high alpha band network features. Our findings suggest that abnormal high alpha band functional network may reflect the pathophysiological characteristics of suicide and serve as a clinical biomarker for suicide.

The Importance of Low-frequency Alpha (8-10 Hz) Waves and Default Mode Network in Behavioral Inhibition.

Objective: : Alpha wave of electroencephalography (EEG) is known to be related to behavioral inhibition. Both the alpha wave and default mode network (DMN) are predominantly activated during resting-state. To study the mechanisms of the trait inhibition, this research investigating the relations among alpha wave, DMN and behavioral inhibition in resting-state. Methods: : We explored the relationship among behavioral inhibition, resting-state alpha power, and DMN. Resting-state EEG, behavioral inhibition/behavioral activation scale (BIS/BAS), Barratt impulsivity scale, and no-go accuracy were assessed in 104 healthy individuals. Three groups (i.e., participants with low/middle/high band power) were formed based on the relative power of each total-alpha, low-alpha (LA), and high-alpha band. Source-reconstructed EEG and functional network measures of 25 DMN regions were calculated. Results: : Significant differences and correlations were found based on LA band power alone. The high LA group had significantly greater BIS, clustering coefficient, efficiency, and strength, and significantly lower path length than low/middle LA group. BIS score showed a significant correlation with functional network measures of DMN. Conclusion: : Our study revealed that LA power is related to behavioral inhibition and functional network measures of DMN of LA band appear to represent significant inhibitory function.

Influence of inter-stimulus interval on 40-Hz auditory steady-state response in patients with schizophrenia.

Decreased 40-Hz auditory steady-state response (ASSR) is believed to reflect abnormal gamma oscillation in patients with schizophrenia (SZ). However, previous studies have reported conflicting results due to variations in inter-stimulus interval (ISI) used. In this study, we aimed to investigate the influence of varying ISI on the 40-Hz ASSR, particularly for patients with SZ and healthy controls (HCs). Twenty-four SZ patients (aged 40.8 ± 13.9 years, male: n = 11) and 21 HCs (aged 33.3 ± 11.3 years, male: n = 8) were recruited. For every participant, 40-Hz ASSRs were acquired for three different stimulus types: 500, 2000, and 3500 ms of ISIs. Two conventional ASSR measures (total power and inter-trial coherence, ITC) were calculated. Several additional ASSR measures were also analyzed: (i) ISI-dependent power; (ii) power onset slope; (iii) power centroid latency; (iv) ISI-dependent ITC; (v) ITC onset slope (500, 2000, 3500 ms); (vi) ITC centroid latency (500, 2000, 3500 ms). As ISI increased, total power and ITC increased in patients with SZ but decreased in HCs. In addition, patients with SZ showed higher ISI-dependent ITC, which was positively correlated with the psychotic symptom severity. The abnormal ITC onset slope and centroid latency for the ISI-500 ms condition were associated with cognitive speed decline in patients with SZ. Our study confirmed that the 40-Hz ASSR could be severely influenced by ISI. Furthermore, our results showed that the additional ASSR measures (ISI-dependent ITC, ITC onset slope, ITC centroid latency) could represent psychotic symptom severity or impairment in cognitive function in patients with SZ.

Clinical Implication of Maumgyeol Basic Service-the 2 Channel Electroencephalography and a Photoplethysmogram-based Mental Health Evaluation Software.

Objective: Maumgyeol Basic service is a mental health evaluation and grade scoring software using the 2 channels EEG and photoplethysmogram (PPG). This service is supposed to assess potential at-risk groups with mental illness more easily, rapidly, and reliably. This study aimed to evaluate the clinical implication of the Maumgyeol Basic service. Methods: One hundred one healthy controls and 103 patients with a psychiatric disorder were recruited. Psychological evaluation (Mental Health Screening for Depressive Disorders [MHS-D], Mental Health Screening for Anxiety Disorders [MHS-A], cognitive stress response scale [CSRS], 12-item General Health Questionnaire [GHQ-12], Clinical Global Impression [CGI]) and digit symbol substitution test (DSST) were applied to all participants. Maumgyeol brain health score and Maumgyeol mind health score were calculated from 2 channel frontal EEG and PPG, respectively. Results: Participants were divided into three groups: Maumgyeol Risky, Maumgyeol Good, and Maumgyeol Usual. The Maumgyeol mind health scores, but not brain health scores, were significantly lower in the patients group compared to healthy controls. Maumgyeol Risky group showed significantly lower psychological and cognitive ability evaluation scores than Maumgyeol Usual and Good groups. Maumgyel brain health score showed significant correlations with CSRS and DSST. Maumgyeol mind health score showed significant correlations with CGI and DSST. About 20.6% of individuals were classified as the No Insight group, who had mental health problems but were unaware of their illnesses. Conclusion: This study suggests that the Maumgyeol Basic service can provide important clinical information about mental health and be used as a meaningful digital mental healthcare monitoring solution to prevent symptom aggravation.

Machine learning-based classification using electroencephalographic multi-paradigms between drug-naïve patients with depression and healthy controls.

BACKGROUND: Electroencephalography (EEG) is a supplementary diagnostic tool in psychiatry but lacks practical usage. EEG has demonstrated inconsistent diagnostic ability because major depressive disorder (MDD) is a heterogeneous psychiatric disorder with complex pathologies. In clinical psychiatry, it is essential to detect these complexities using multiple EEG paradigms. Though the application of machine learning to EEG signals in psychiatry has increased, an improvement in its classification performance is still required clinically. We tested the classification performance of multiple EEG paradigms in drug-naïve patients with MDD and healthy controls (HCs). METHODS: Thirty-one drug-naïve patients with MDD and 31 HCs were recruited in this study. Resting-state EEG (REEG), the loudness dependence of auditory evoked potentials (LDAEP), and P300 were recorded for all participants. Linear discriminant analysis (LDA) and support vector machine (SVM) classifiers with t-test-based feature selection were used to classify patients and HCs. RESULTS: The highest accuracy was 94.52 % when 14 selected features, including 12 P300 amplitudes (P300A) and two LDAEP features, were layered. The accuracy was 90.32 % when a SVM classifier for 30 selected features (14 P300A, 14 LDAEP, and 2 REEG) was layered in comparison to each REEG, P300A, and LDAEP, the best accuracies of which were 71.57 % (2-layered with LDA), 87.12 % (1-layered with LDA), and 83.87 % (6-layered with SVM), respectively. LIMITATIONS: The present study was limited by small sample size and difference in formal education year. CONCLUSIONS: Multiple EEG paradigms are more beneficial than a single EEG paradigm for classifying drug-naïve patients with MDD and HCs.

The Effectiveness of Virtual Reality Intervention for COVID-19-Related Psychological Distress: A Systematic Review.

OBJECTIVE: The prolonged coronavirus disease-2019 (COVID-19) pandemic is likely to cause psychological distress in people. This systematic review aimed to identify the effectiveness of virtual reality (VR)-based psychological intervention among individuals with psychological distress during the COVID-19 crisis. PubMed, Ovid MEDLINE, Cochrane Library, Web of Science, Embase, and PsycINFO databases were searched for articles published until July 2022. METHODS: The available citations were deduplicated and screened by two authors using the title and abstract information. Eligibility criteria were constructed according to the PICOT guidelines. Empirical studies of all designs and comparator groups were included if they appraised the impact of an immersive VR intervention on any standardized measure indicative of psychological distress (stress, anxiety, depression, and post-traumatic symptoms) or improvements in quality of life in participants, including COVID-19 patients, medical staff working with COVID-19 patients, and people who had experienced strict social distancing during the COVID-19 pandemic. RESULTS: The results were discussed using a narrative synthesis because of the heterogeneity between studies. Seven of the studies met the inclusion criteria. There were two randomized controlled trials and five uncontrolled studies on VR interventions. CONCLUSION: All studies reported significant improvement in a wide range of psychological distress during COVID-19, ranging from stress, anxiety, depression, and post-traumatic symptoms to quality of life, supporting the efficacy of VR-based psychological intervention. Our results suggest that VR intervention has potential to ameliorate COVID-19-related psychological distress with efficacy and safety.

Decoding the temporal dynamics of affective scene processing.

Natural images containing affective scenes are used extensively to investigate the neural mechanisms of visual emotion processing. Functional fMRI studies have shown that these images activate a large-scale distributed brain network that encompasses areas in visual, temporal, and frontal cortices. The underlying spatial and temporal dynamics, however, remain to be better characterized. We recorded simultaneous EEG-fMRI data while participants passively viewed affective images from the International Affective Picture System (IAPS). Applying multivariate pattern analysis to decode EEG data, and representational similarity analysis to fuse EEG data with simultaneously recorded fMRI data, we found that: (1) ∼80 ms after picture onset, perceptual processing of complex visual scenes began in early visual cortex, proceeding to ventral visual cortex at ∼100 ms, (2) between ∼200 and ∼300 ms (pleasant pictures: ∼200 ms; unpleasant pictures: ∼260 ms), affect-specific neural representations began to form, supported mainly by areas in occipital and temporal cortices, and (3) affect-specific neural representations were stable, lasting up to ∼2 s, and exhibited temporally generalizable activity patterns. These results suggest that affective scene representations in the brain are formed temporally in a valence-dependent manner and may be sustained by recurrent neural interactions among distributed brain areas.

Association between the loudness dependence of auditory evoked potentials and age in patients with schizophrenia and depression.

OBJECTIVE: Although serotonergic dysfunction is significantly associated with major depressive disorder (MDD) and schizophrenia (SCZ), comparison of serotonergic dysfunction in both diseases has received little attention. Serotonin hypotheses have suggested diminished and elevated serotonin activity in MDD and SCZ, respectively. However, the foundations underlying these hypotheses are unclear regarding changes in serotonin neurotransmission in the aging brain. The loudness dependence of auditory evoked potentials (LDAEP) reflects serotonin neurotransmission. The present study compared the LDAEP between patients with SCZ or MDD and healthy controls (HCs). We further examined whether age was correlated with the LDAEP and clinical symptoms. METHODS: This prospective clinical study included 105 patients with SCZ (n = 54) or MDD (n = 51). Additionally, 35 HCs were recruited for this study. The LDAEP was measured on the midline channels via 62 electroencephalography channels. RESULTS: Patients with SCZ or MDD showed a significantly smaller mean LDAEP than those in HCs. The LDAEP was positively correlated with age in patients with SCZ or MDD. CONCLUSIONS: Changes in central serotonergic activity could be indicated by evaluating the LDAEP in patients with SCZ or MDD. Age-related reductions in serotonergic activity may be screened using the LDAEP in patients with SCZ or MDD.

A clinical trial of a patient-customized virtual reality intervention for tinnitus.

Virtual reality (VR) has recently been used as a clinical treatment because it can efficiently simulate situations that are difficult to control in real-world settings. In our study, we assessed the potential of VR in patients with chronic subjective tinnitus. An evaluation of its clinical benefits was performed based on analyses of patient electroencephalograms (EEGs) and by questionnaire responses after 6-8 weeks of patient involvement in our VR-based alleviation program. Clinical trials were performed at a tertiary academic hospital. Nineteen patients (aged 33-64 years) who visited our hospital with chronic subjective tinnitus over 3 months were enrolled in the study. The intervention consisted of trashing the tinnitus avatar in VR. We expected that the patients would have the subjective feeling of controlling tinnitus through our intervention. The VR environment comprised four different sessions in four different settings: a bedroom, a living room, a restaurant, and a city street. We analyzed changes in the source activities of the prefrontal regions related to tinnitus in these patients using standardized low-resolution brain electromagnetic tomography. The Tinnitus Handicap Inventory (THI), the total score (from 50.11 to 44.21, P = 0.046) and the grade (from 3.16 to 2.79, P = 0.035) were significantly improved after the VR-based tinnitus treatment program (P < 0.05). The Pittsburgh Sleep Quality Index also showed improved outcomes (P = 0.025). On the other hand, a Tinnitus Handicap Questionnaire, Quality of Life Assessment (WHO-QOL), Hospital Anxiety and Depression Scale, Profile of Mood States revealed no significant change after the intervention. The baseline EEG data showed that brain activity in the orbitofrontal cortex significantly increased in the alpha and theta frequency bands. Furthermore, patients who showed a THI score improvement after the intervention showed specific increases in brain activity for the theta and high beta bands in the orbitofrontal cortex. Our findings suggest that the virtual reality-based program, as in parts of cognitive behavioral treatment, may help to alleviate tinnitus-related distress in patients with chronic subjective tinnitus.

Alteration of cortical functional networks in mood disorders with resting-state electroencephalography.

Studies comparing bipolar disorder (BD) and major depressive disorder (MDD) are scarce, and the neuropathology of these disorders is poorly understood. This study investigated source-level cortical functional networks using resting-state electroencephalography (EEG) in patients with BD and MDD. EEG was recorded in 35 patients with BD, 39 patients with MDD, and 42 healthy controls (HCs). Graph theory-based source-level weighted functional networks were assessed via strength, clustering coefficient (CC), and path length (PL) in six frequency bands. At the global level, patients with BD and MDD showed higher strength and CC, and lower PL in the high beta band, compared to HCs. At the nodal level, compared to HCs, patients with BD showed higher high beta band nodal CCs in the right precuneus, left isthmus cingulate, bilateral paracentral, and left superior frontal; however, patients with MDD showed higher nodal CC only in the right precuneus compared to HCs. Although both MDD and BD patients had similar global level network changes, they had different nodal level network changes compared to HCs. Our findings might suggest more altered cortical functional network in patients with BD than in those with MDD.

Stress-related cognitive style is related to volumetric change of the hippocampus and FK506 binding protein 5 polymorphism in post-traumatic stress disorder.

BACKGROUND: Patients with post-traumatic stress disorder (PTSD) show a different stress-related cognitive style compared with healthy controls (HC). The FK506 binding protein 5 gene (FKBP5), one of the PTSD known risk factors, is involved in the stress response through the hypothalamic-pituitary-adrenal axis and brain volumetric alterations. The present study aimed to uncover the neural correlates of stress-related cognitive styles through the analysis of the regional brain volumes and FKBP5 genotype in patients with PTSD compared with HC. METHODS: In this study, 51 patients with PTSD and 94 HC were assessed for stress-related cognitive styles, PTSD symptoms severity, and genotype of FKBP5 single nucleotide polymorphisms, and underwent T1-weighted structural magnetic resonance imaging. Diagnosis-by-genotype interaction for regional brain volumes was examined in 16 brain regions of interest. RESULTS: Patients with PTSD showed significantly higher levels of catastrophizing, ruminative response, and repression, and reduced distress aversion and positive reappraisal compared with HC (p < 0.001). Significant diagnosis-by-genotype interactions for regional brain volumes were observed for bilateral hippocampi and left frontal operculum. A significant positive correlation between the severity of the repression and left hippocampal volume was found in a subgroup of patients with PTSD with FKBP5 rs3800373 (AA genotype) or rs1360780 (CC genotype). CONCLUSIONS: The present study showed the influences of FKBP5 genotype on the distorted cognitive styles in PTSD by measuring the volumetric alteration of hippocampal regions, providing a possible role of the hippocampus and left frontal operculum as significant neurobiological correlates of PTSD.

Machine Learning-Based Electroencephalographic Phenotypes of Schizophrenia and Major Depressive Disorder.

Background: Psychiatric diagnosis is formulated by symptomatic classification; disease-specific neurophysiological phenotyping could help with its fundamental treatment. Here, we investigated brain phenotyping in patients with schizophrenia (SZ) and major depressive disorder (MDD) by using electroencephalography (EEG) and conducted machine-learning-based classification of the two diseases by using EEG components. Materials and Methods: We enrolled healthy controls (HCs) (n = 30) and patients with SZ (n = 34) and MDD (n = 33). An auditory P300 (AP300) task was performed, and the N1 and P3 components were extracted. Two-group classification was conducted using linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Positive and negative symptoms and depression and/or anxiety symptoms were evaluated. Results: Considering both the results of statistical comparisons and machine learning-based classifications, patients and HCs showed significant differences in AP300, with SZ and MDD showing lower N1 and P3 than HCs. In the sum of amplitudes and cortical sources, the findings for LDA with classification accuracy (SZ vs. HCs: 71.31%, MDD vs. HCs: 74.55%), sensitivity (SZ vs. HCs: 77.67%, MDD vs. HCs: 79.00%), and specificity (SZ vs. HCs: 64.00%, MDD vs. HCs: 69.67%) supported these results. The SVM classifier showed reasonable scores between SZ and HCs and/or MDD and HCs. The comparison between SZ and MDD showed low classification accuracy (59.71%), sensitivity (65.08%), and specificity (54.83%). Conclusions: Patients with SZ and MDD showed deficiencies in N1 and P3 components in the sum of amplitudes and cortical sources, indicating attentional dysfunction in both early and late sensory/cognitive gating input. The LDA and SVM classifiers in the AP300 are useful to distinguish patients with SZ and HCs and/or MDD and HCs.

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.

Influence of FKBP5 Variants and Childhood Trauma on Brain Volume in Non-clinical Individuals.

The present study aimed to investigate the possible influence of childhood trauma and its interaction effect with 10 single-nucleotide polymorphisms (SNPs) of the FK506-binding protein 51 (FKBP5) gene on brain volume in non-clinical individuals. One hundred forty-four non-clinical volunteers (44 men and 100 women) were genotyped with respect to 10 variants (rs9296158, rs3800373, rs1360780, rs9470080, rs4713916, rs4713919, rs6902321, rs56311918, rs3798345, and rs9380528) of FKBP5. Participants underwent magnetic resonance imaging (MRI) scan and psychological assessments such as the childhood Trauma Questionnaire (CTQ), Hospital Anxiety and Depression Scale, rumination response scale, and quality of life assessment instrument. Individuals with the high CTQ score showed enlarged volume of the left orbitofrontal cortex (OFC) if they have childhood trauma-susceptible genotype of FKBP5 rs3800373, rs1360780, rs4713916, rs4713919, rs6902321, and rs3798345 and enlarged volume of the left middle temporal gyrus (MTG) if they have childhood trauma-susceptible genotype of FKBP5 rs3800373, rs1360780, rs4713916, and rs3798345. Among those with the childhood trauma-susceptible genotype, the left OFC and left MTG showed significant negative correlations with positive feelings about life, and the left OFC showed significant positive correlations with negative cognition. This is one of the few studies to identify the volume alteration of the left OFC and the left MTG for the FKBP5 gene-childhood trauma interaction in non-clinical individuals.

Auditory evoked potentials and suicidal behaviors in patients with major depressive disorders.

Loudness dependence of auditory evoked potentials (LDAEP) has been proposed as a biological marker of central serotonergic activity related to suicides. This study's objective was to analyze the difference in LDAEP between depressed patients with suicide attempts (SA) and suicidal ideation (SI). It included 130 participants (45 depressed patients with SA, 49 depressed patients with SI, and 36 healthy controls) aged > 18 years who exhibited LDAEP during electroencephalography. Psychological characteristics and event-related potentials of the three groups were compared. There was no significant difference in LDAEP between major depressive disorder (MDD) patients with SA and SI (p = 0.59). MDD patients with SI, who attempted suicide had significantly lower LDAEP than healthy controls (p = 0.01 and p = 0.01, respectively). However, the significance disappeared when psychological characteristics were controlled. Our results suggest that LDAEP might not be possible biomarkers for suicidal behaviors in patients with MDD. Further studies to assess the biological basis of suicide and identify the underlying dimensions that mediate the relationship between the biological basis and suicidal behaviors will be needed.