A reduced P300 prospectively predicts increased depressive severity in adults with clinical depression

Decomposing loss aversion from a single neural signal

People often display stronger aversion to losses than appetite for equivalent gains, a widespread phenomenon known as loss aversion. The prevailing theory attributes loss aversion to a valuation bias that amplifies losses relative to gains. An alternative account attributes loss aversion to a response bias that avoids choices that might result in loss. By modeling the temporal dynamics of scalp electrical activity during decisions to accept or reject gambles within a sequential sampling framework, we decomposed valuation bias and response bias from a single event-related neural signal, the P3. Specifically, we found valuation bias manifested as larger sensitivity of P3 to losses than gains, which was localizable to reward-related brain regions. By contrast, response bias manifested as larger P3 preceding gamble acceptance than rejection and was localizable to motor cortex. Our study reveals the dissociable neural biomarkers of response bias and valuation bias underpinning loss-averse decisions.

Event-related potentials of social comparisons in depression and social anxiety

Social comparison is central in human life and can be especially challenging in depression and social anxiety. We assessed event-related potentials and emotions using a social comparison task in which participants received feedback on both their own and a co-player's performance, in participants with depression and/or social anxiety (n = 63) and healthy controls (n = 72). Participants reported more negative emotions for downward (being better than the co-player [participant correct, co-player wrong]) and upward (being worse than the co-player [participant wrong, co-player correct]) comparisons versus even outcomes, with these effects being stronger in depression and social anxiety. At the Medial Frontal Negativity, both controls and depressed participants showed a more negative amplitude for upward comparison versus both the participant and co-player performing wrong. Socially anxious subjects showed the opposite effect, possibly due to greater expectations about being worse than others. The P300 decreased for downward and upward comparisons compared to even outcomes, which may relate to the higher levels of conflict of social inequality. Depressed and socially anxious subjects showed a blunted P300 increase over time in response to the task outcomes, suggesting deficits in allocating resources for the attention of incoming social information. The LPP showed increased amplitude for downward and upward comparison versus the even outcomes and no group effect. Emotional findings suggest that social comparisons are more difficult for depressed and socially anxious individuals. Event-related potentials findings may shed light on the neural substrates of these difficulties.

Using the Beck Depression Inventory to Assess Anhedonia: A Scale Validation Study

Anhedonia is central to several psychological disorders and a frequent target of psychosocial and pharmacological treatments. We evaluated the psychometric properties of two widely used anhedonia measures derived from the Beck Depression Inventory: a 3-item (BDI-Anh3) and a 4-item version (BDI-Anh4). We evaluated these measures in a large undergraduate sample, a community sample, and a clinical sample. Both the BDI-Anh3 and the BDI-Anh4 showed adequate internal consistency, with BDI-Anh4 performing somewhat better, across the three samples. Both measures showed good convergent and discriminant validity, even after controlling for shared variance with other items on the BDI. These findings indicate that both measures have sufficient reliability and validity to support their use by researchers and clinicians.

Rapid improvements and subsequent effects in major depressive disorder patients with somatic pain using rTMS combined with sertraline

This study aims to explore changes in depression and pain for major depressive disorder (MDD) patients with somatic pain after repetitive transcranial magnetic stimulation (rTMS) using the event-related potentials (ERPs) technique. Eighty MDD patients with somatic pain were randomly assigned to drug therapy (DT) and combined therapy (CT) groups. CT group underwent intermittent theta burst stimulation over the left dorsolateral prefrontal cortex (DLPFC) with 800 pulses and 1 Hz over the right DLPFC with 800 pulses, 5 times a week for 3 weeks. All patients were given sertraline at 50-100 mg per day. All subjects were evaluated at baseline and at weeks three and six of therapy using the Hamilton Rating Scale for Depression (HAMD), Hamilton Anxiety Scale (HAMA), and Numerical Rating Scales (NRS), and the latency and amplitude of P300 and mismatch negativity (MMN) were measured. There were no significant differences in all indices between groups at baseline. At 3 weeks, HAMD subscale scores of Cognitive Impairment and NRS scores were significantly lower in the CT group than in the DT group. At 6 weeks, NRS and HAMD total scores in the CT group decreased significantly in the CT group compared with the DT group, especially for anxiety and pain, and the MMN and P300 latencies and P300 amplitude showed greater improvements. Our findings highlight that rTMS in combination with antidepressants is a rapid method of symptom improvement in patients with somatic pain with MDD and is helpful for cognitive impairment and anxiety.

Effort and Appetitive Responding in Depression: Examining Deficits in Motivational and Consummatory Stages of Reward Processing Using the Effort-Doors Task

Background

Reward sensitivity is a dimensional construct central to understanding the nature of depression. Psychophysiological research on this construct has primarily focused on the reward positivity, an event-related potential (ERP) that indexes consummatory reward sensitivity. This study extended prior research by focusing on ERPs that index the motivational component of reward.

Methods

A novel effort-for-reward task was used to elicit motivational and consummatory ERPs. Groups consisting of 34 participants with depression and 32 participants without depression were compared across a range of reward-related ERPs.

Results

Participants with depression exhibited reduced responsivity to effort completion cues following high effort expenditure, reduced anticipation of rewards after low effort expenditure (i.e., the stimulus preceding negativity), and reduced reward positivity following high effort expenditure. ERPs occurring prior to reward receipt accounted for unique variance in depression status and differentiated between subgroups of depressed individuals.

Conclusions

Findings support the utility of leveraging multiple ERPs that index separate reward processing deficits to better characterize depression and depressive subtypes.

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.

Deficits in doors P300 amplitude during adolescence associated with preschool-onset depression

The psychophysiological underpinnings of preschool-onset depression (PO-MDD) remain underexplored. Moreover, there is currently a limited understanding of the potential impact that PO-MDD might have on neurobiological functions later in development such as general cognitive domains and reward processing. Thus, the current study sought to examine potential neurophysiological differences, measured via electroencephalography (EEG), in adolescents with and without a history of PO-MDD. Participants and their caregivers (N = 138) from a large longitudinal study completed semi-structured clinical interviews at a baseline visit (ages 3-7) to determine PO-MDD status. At a follow-up visit approximately 11 years later, adolescents (ages 13-19) completed the doors gambling task while EEG was recorded to measure event-related potentials (ERPs) elicited by both the doors and feedback stimuli, to index cognitive and reward processing functions (i.e., doors-P300, gain/loss feedback-P300, and RewP). Adolescents with a history of PO-MDD exhibited significantly smaller doors-P300 compared with adolescents with no history of PO-MDD, whereas there were no group differences in gain/loss feedback-P300 or RewP. Additionally, reduced doors-P300 was independently associated with lower baseline income-to-needs ratio, older age, and female gender. The current study suggests that reduced doors-P300 amplitude during adolescence might reflect impaired neurophysiological development related to PO-MDD. Thus, the P300 derived from the doors stimuli might be a valuable neural measure to further our understanding of potential neurophysiological differences associated with early-onset childhood depression.

Reduced concentration performance and heartbeat-evoked potential in individuals with a history of a SARS-CoV-2 infection

The goal of characterizing long-term psychological and neural consequences of a SARS-CoV-2 infection has recently gained importance. Here, we examined the effect of a prior SARS-CoV-2 infection on neural markers of exteroceptive (P300) and interoceptive (heartbeat-evoked potential; HEP) signal processing, as well as on neuropsychological tests of attention, inhibition and episodic memory, in 23 adults with a self-reported history of SARS-CoV-2 infection versus 23 healthy controls. We found that the group with a prior infection showed decreased HEP (but not P300) amplitudes, as well as reduced attention/concentration performance. These results suggest that SARS-CoV-2 may damage neural structures of cardiac interoception, thereby potentially contributing to cognitive and psychological long-term deficits. Modulations of interoceptive processing after a SARS-CoV-2 infection are thus a promising target for future research.

Event-related potentials during the ultimatum game in people with symptoms of depression and/or social anxiety

Depression and social anxiety are common disorders that have a profound impact on social functioning. The need for studying the neural substrates of social interactions in mental disorders using interactive tasks has been emphasized. The field of neuroeconomics, which combines neuroscience techniques and behavioral economics multiplayer tasks such as the Ultimatum Game (UG), can contribute in this direction. We assessed emotions, behavior, and Event-Related Potentials in participants with depression and/or social anxiety symptoms (MD/SA, n = 63, 57 females) and healthy controls (n = 72, 67 females), while they played the UG. In this task, participants received fair, mid-value, and unfair offers from other players. Mixed linear models were implemented to assess trial level changes in neural activity. The MD/SA group reported higher levels of sadness in response to mid-value and unfair offers compared to controls. In controls, the Medial Frontal Negativity associated with fair offers increased over time, while this dynamic was not observed in the MD/SA group. The MD/SA group showed a decreased P3/LPP in all offers, compared to controls. These results indicate an enhanced negative emotional response to unfairness in the MD/SA group. Neural results reveal a blunted response over time to positive social stimuli in the MD/SA group. Moreover, between-group differences in P3/LPP may relate to a reduced saliency of offers and/or to a reduced availability of resources for processing incoming stimuli in the MD/SA group. Findings may shed light into the neural substrates of social difficulties in these disorders.

Neural deficits in anticipatory and consummatory reward processing are uniquely associated with current depressive symptoms during adolescence

Deficits within the consummatory phase of reward processing are associated with increased depression symptoms and risk; however, few studies have also examined other aspects of reward processing in relation to depression. In the current study, a community sample of 121 adolescents (M_age  = 13.1, Min = 11.14; Max = 15.12; 54% male) completed self-report questionnaires to assess depressive symptoms and the monetary incentive delay (MID) task while EEG was recorded. Results indicated that a reduced cue-P300 as well as a reduced reward positivity (RewP) and feedback negativity (FN) to gain and loss feedback, respectively, were associated with increased depressive symptoms; on the other hand, SPN and feedback P300 were unrelated to depressive symptoms. An exploratory multiple regression analysis revealed that a reduced money cue-P300, a reduced RewP, and a reduced (i.e., less negative) FN, all explained unique variance in depressive symptoms. The current study demonstrates that reduced cue-P300, RewP, and FN amplitudes may reflect distinct deficits in reward processing among adolescents with increased depressive symptoms. Notably, this study is one of the first to leverage the MID task in adolescents in relation to depressive symptoms, allowing for a more in-depth view of the individual differences in reward processing among adolescents with increased depressive symptomatology.

Electrophysiological biomarkers and age characterize phenotypic heterogeneity among individuals with major depressive disorder

Introduction: Despite the high need for effective treatments for major depressive disorder (MDD), the development of novel medicines is hampered by clinical, genetic and biological heterogeneity, unclear links between symptoms and neural dysfunction, and tenuous biomarkers for clinical trial contexts of use. Methods: In this study, we examined the International Study to Predict Optimized Treatment in Depression (iSPOT-D) clinical trial database for new relationships between auditory event-related potential (ERP) responses, demographic features, and clinical symptoms and behavior, to inform strategies for biomarker-driven patient stratification that could be used to optimize future clinical trial design and drug development strategy in MDD. Results: We replicate findings from previous analyses of the classic auditory oddball task in the iSPOT-D sample showing smaller than typical N1 and P300 response amplitudes and longer P300 latencies for target and standard stimuli in patients with MDD, suggesting altered bottom-up sensory and top-down attentional processes. We further demonstrate that age is an important contributor to clinical group differences, affecting both topographic distribution of the clinically informative ERP responses and the types of the stimuli sensitive to group differences. In addition, the observed brain-behavior associations indicate that levels of anxiety and stress are major contributing factors to atypical sensory and attentional processing among patients with MDD, particularly in the older subgroups. Discussion: Our novel findings support the possibility of accelerated cognitive aging in patients with MDD and identify the frontal P300 latency as an additional candidate biomarker of MDD. These results from a large, well-phenotyped sample support the view that heterogeneity of the clinical population with MDD can be systematically characterized based on age and neural biomarkers of sensory and attentional processing, informing patient stratification strategies in the design of clinical trials.

Reduced P300 amplitude is consistently associated with trait anhedonia across repeated assessments

Understanding how event-related potentials (ERPs) change following repeated assessments is critical to advance our understanding of neural mechanisms implicated in psychopathology. Specifically, it is unclear if associations between ERPs and individual differences can be reproduced when repeatedly measured within the same participants, or if clinical characteristics impact ERP trajectories over repeated assessments. The present study assessed P300 amplitude and latency from a flanker task at four time points over one month (M = 7.24 days between assessments [SD = 1.02]) in 79 female undergraduates to examine how P300 amplitude/latency changes across repeated assessments, the presence of associations between within- and between-subjects measures of current depressive symptoms and the P300, and if between-subjects depressive symptoms moderated change in P300 over repeated assessment. Results using multilevel modeling indicated a significant reduction in P300 amplitude and latency across assessments. Individuals with increased trait anhedonia (i.e., between-subjects) exhibited reduced P300 amplitudes across assessments; there were no associations of within-subjects fluctuations in anhedonia symptoms and P300 amplitude across assessments. There was also no interaction between number of assessments and between-subjects anhedonia in relation to P300 amplitude. Unlike anhedonia, between-subjects dysphoria was unrelated to P300. These results demonstrate a relatively specific and consistent association between an attenuated P300 amplitude and trait anhedonia across repeated assessments - data that may further suggest that flanker P300 amplitude reflects hedonic and motivational processes.

The P300 and late positive potential in pregnancy prospectively predict increases in depressive and anxious symptoms in the early postpartum period

Postnatal depression and anxiety disorders pose a major burden on maternal mental health. While psychosocial risk factors for perinatal depression and anxiety are well-researched, there is a dearth of research examining neural biomarkers of risk for postnatal increases in depression and anxiety. Previous studies suggest two different event-related potentials, the P300 and the late positive potential (LPP), may predict the course of depressive and anxious symptoms in non-perinatal populations. In a sample of 221 perinatal women, the present study utilized an emotional interrupt task administered in pregnancy to examine whether antenatal P300 and LPP amplitudes may predict change in depressive and anxious symptoms from pregnancy to the early postpartum period. Zero-order correlations and linear regressions revealed that a reduced antenatal P300 to target stimuli and an enhanced LPP to positive infant images were uniquely associated with postnatal depressive and anxiety symptoms, respectively, and that these ERPs were independent predictors beyond antenatal self-report measures of psychological symptoms. Furthermore, individuals with increased depressive symptoms in pregnancy exhibited a stronger negative association between antenatal P300 amplitude and postnatal depressive symptoms. The present findings underscore the possibility that the measurement of ERPs during pregnancy could serve as a screening tool for risk for perinatal depression and anxiety, and thereby assist with identifying at-risk individuals who might benefit from prevention efforts.

Depression reduces neural correlates of reward salience with increasing effort over the course of the progressive ratio task

BACKGROUND

Depressive disorders have been associated with altered effort-cost decision making (ECDM) in behavioral investigations, such as a decreased willingness to expend effort for reward attainment. However, little is known about neural mechanisms implicated in altered ECDM.

METHODS

The study investigates neural correlates of reward attainment during a progressive ratio task in participants with a current depressive disorder (n = 65) and never-depressed healthy individuals (n = 44). On each trial, participants completed an increasing number of button presses to attain a fixed monetary reward, indicated by an auditory reward signal. Participants could decide to quit the task anytime (breakpoint). EEG was recorded during the task and P300 amplitudes were examined in response to the auditory signal of reward attainment.

RESULTS

There was no difference in breakpoint, as both groups completed comparable numbers of button presses. In contrast, results from mixed-effects models of trial-level ERP responses indicated depression-related effects on P300 amplitudes over the course of the task. Generally, the reward-locked P300 increased with ascending effort expenditure; however, compared to healthy participants, individuals with current depression were characterized by an attenuated trajectory of the reward-locked P300, pointing towards decreased reactivity to reward attainment with increasing effort.

LIMITATIONS

Sample size and reward magnitude were possibly not large enough to detect differences in breakpoint.

CONCLUSIONS

The results of the current study demonstrate that the investigation of reward-related P300 trajectory may represent an informative novel addition to the progressive ratio task, which could help shed light on depression-related alterations in motivation and ECDM.

The P300, loneliness, and depression in older adults

Depression is associated with high levels of cognitive impairment and increased loneliness among older adults. The current study examines associations between a reliable and robust neural marker of cognitive impairment (i.e., the P300 event-related brain potential [ERP]), loneliness, and depression and assesses the role of loneliness in the P300─depression relationship. In a community sample of 70 older adults between 61 and 75 years, we evaluated cross-sectional associations between depressive symptoms (Geriatric Depression Scale), loneliness (NIH Toolbox), and P300 amplitude measured from the electroencephalogram during a go/no-go task. Results indicated that reduced go and no-go P300 amplitudes were associated with increased depressive symptom severity, with the most unique variance accounted for by a reduced no-go P300 amplitude. Notably, loneliness significantly moderated the no-go P300-depressive symptom severity relationship, such that there was no relationship between the no-go P300 and depressive symptom severity among older adults reporting low levels of loneliness. This finding provides insight into the possibility that social support may offer protection against the depressogenic effects of poor inhibitory control in older adults. Taken together, this study provides a novel examination of the relationships between depression, loneliness, and the P300 ERP in older adults, with important implications for understanding the role of neural inhibition and loneliness in relation to depressive symptomatology.

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.

Neural correlates of abnormal cognitive conflict resolution in major depression: An event-related potential study

Abnormal cognitive conflict resolution has been considered as a critical element of executive dysfunctions inpatient with major depression (MD). Further clarifying whether there was a deficit at perceptual encoding stage or the early response-execution stage in conflict control function by event-related potential (ERP) technique in MD would be helpful in understanding the neural mechanism of MD. Participants included twenty-six depressed patients and twenty-six healthy controls (HCs). All participants measured with Hamilton Depression Scale (17-item edition, HAMD) and a Simon task. Electroencephalograms were synchronously recorded when performing the Simon task. The method of residue iteration decomposition was used to analyze the lateralized readiness potential (LRP) and P300 components, which contributed to divides ERP components into a stimulus-locked component (S-cluster), a response-locked component (R-cluster) and an intermediate component cluster (C-cluster) by using latency variability and time markers. Results showed that reactive times (RTs) for both groups were fastest in congruent trials, and slowest in incongruent trials; however, there is no difference in RTs under the three conditions between two groups. Accuracy Rate (ACC) for both groups were the highest in neutral trials, and the lowest in incongruent trials; ACC in MD group were all lower than that of HC group under three conditions. ERP data analyses showed that depressed patients had a deficit in activating the correct response, as reflected by reduced amplitudes of R-LRP, but no abnormality in LRP-S and P300-C. In conclusion, patients with MD present conflict control dysfunction (i.e., abnormal cognitive conflict resolution) at the early response-execution stage, not at perceptual encoding stage, which may be reflected by the reduced R-LRP amplitudes. The abnormal cognitive conflict resolution in activating the correct response might constitute an interesting treatment target.

Blunted Flanker P300 Demonstrates Specificity to Depressive Symptoms in Females during Adolescence

Recent research suggests that depressive disorders in adults are characterized by reductions in flanker P300 amplitude, and that a reduced flanker P300 may also predict worst depressive trajectories over time. The current study extended this work to adolescence-and to evaluate the specificity of the relationship between flanker P300 to depressive symptoms versus anxiety symptoms, and whether the association between flanker P300 and depressive symptoms was moderated by biological sex. To this end, P300 amplitude, depression, anxiety, and sex were assessed in a large sample of 619 adolescents aged 11 to 14. Participants completed a speeded response flanker task while EEG was recorded, as well as self-reported measures of current depression and anxiety symptoms. Reduced P300 amplitude was related to both heightened depression and anxiety symptoms in zero-order correlations. Regression-based analyses suggest that reduced P300 was uniquely related to depressive symptoms. Furthermore, this negative association between P300 and depression was apparent in female adolescents, but not male adolescents. In sum, the current study suggests that flanker P300 amplitude may potentially serve as a neural marker specific to depression in females during adolescence.

The impact of a single session of aerobic exercise on positive emotional reactivity in depression: Insight into individual differences from the late positive potential

Depression has been characterized by a broad disengagement from the environment, as reflected by dampened positive and negative emotional reactivity. Research has shown that acute exercise may enhance positive emotional reactivity in healthy adults. It is unknown whether it can alter positive emotional reactivity in depression. In the present study, positive emotional reactivity was assessed using the late positive potential (LPP) event-related potential before and after 30 min of moderate-intensity aerobic exercise in 43 adults with current or a lifetime history of depression (Mage = 32.74 years; Min/Max = 18/59) and 18 never-depressed healthy adults (Mage = 37.94 years; Min/Max = 21/61). Acute exercise increased the LPP for healthy adults; the LPP did not change among those with current or a lifetime history of depression. A secondary aim was to identify moderators of change in positive emotional reactivity among subgroups of adults with current depression. Compared to adults with impaired mood reactivity, those with intact mood reactivity had a pre-to-post increase in the LPP. The current study provides preliminary support for the LPP as a neural indicator of exercise efficacy and highlights individual differences in response to acute exercise in depression.

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.