Cardioprotective potential of lithium and role of fractalkine in euthymic patients with bipolar disorder.

OBJECTIVE: Over a half century, lithium has been used as the first-line medication to treat bipolar disorder. Emerging clinical and laboratory studies suggest that lithium may exhibit cardioprotective effects in addition to neuroprotective actions. Fractalkine (CX3CL1) is a unique chemokine associated with the pathogenesis of mood disorders and cardiovascular diseases. Herein we aimed to ascertain whether lithium treatment is associated with favorable cardiac structure and function in relation to the reduced CX3CL1 among patients with bipolar disorder. METHODS: We recruited 100 euthymic patients with bipolar I disorder aged over 20 years to undergo echocardiographic study and measurement of plasma CX3CL1. Associations between lithium treatment, cardiac structure and function and peripheral CX3CL1 were analyzed according to the cardiovascular risk. The high cardiovascular risk was defined as (1) age ⩾ 45 years in men or ⩾ 55 years in women or (2) presence of concurrent cardiometabolic diseases. RESULTS: In the high cardiovascular risk group (n = 61), patients who received lithium as the maintenance treatment had significantly lower mean values of left ventricular internal diameters at end-diastole (Cohen's d = 0.65, p = 0.001) and end-systole (Cohen's d = 0.60, p = 0.004), higher mean values of mitral valve E/A ratio (Cohen's d = 0.51, p = 0.019) and superior performance of global longitudinal strain (Cohen's d = 0.51, p = 0.037) than those without lithium treatment. In addition, mean plasma levels of CX3CL1 in the high cardiovascular risk group were significantly lower among patients with lithium therapy compared with those without lithium treatment (p = 0.029). Multiple regression models showed that the association between lithium treatment and mitral value E/A ratio was contributed by CX3CL1. CONCLUSION: Data from this largest sample size study of the association between lithium treatment and echocardiographic measures suggest that lithium may protect cardiac structure and function in patients with bipolar disorder. Reduction of CX3CL1 may mediate the cardioprotective effects of lithium.

Using Text Mining and Data Visualization Approaches for Investigating Mental Illness from the Perspective of Traditional Chinese Medicine.

Background and Objectives. Anxiety and depressive disorders are the most prevalent mental disorders, and due to the COVID-19 pandemic, more people are suffering from anxiety and depressive disorders, and a considerable fraction of COVID-19 survivors have a variety of persistent neuropsychiatric problems after the initial infection. Traditional Chinese Medicine (TCM) offers a different perspective on mental disorders from Western biomedicine. Effective management of mental disorders has become an increasing concern in recent decades due to the high social and economic costs involved. This study attempts to express and ontologize the relationships between different mental disorders and physical organs from the perspective of TCM, so as to bridge the gap between the unique terminology used in TCM and a medical professional. Materials and Methods. Natural language processing (NLP) is introduced to quantify the importance of different mental disorder descriptions relative to the five depots and two palaces, stomach and gallbladder, through the classical medical text Huangdi Neijing and construct a mental disorder ontology based on the TCM classic text. Results. The results demonstrate that our proposed framework integrates NLP and data visualization, enabling clinicians to gain insights into mental health, in addition to biomedicine. According to the results of the relationship analysis of mental disorders, depots, palaces, and symptoms, the organ/depot most related to mental disorders is the heart, and the two most important emotion factors associated with mental disorders are anger and worry & think. The mental disorders described in TCM are related to more than one organ (depot/palace). Conclusion. This study complements recent research delving into co-relations or interactions between mental status and other organs and systems.

Peripheral inflammatory markers associated with brain volume reduction in patients with bipolar I disorder.

BACKGROUND: Neuroinflammation and brain structural abnormalities are found in bipolar disorder (BD). Elevated levels of cytokines and chemokines have been detected in the serum and cerebrospinal fluid of patients with BD. This study investigated the association between peripheral inflammatory markers and brain subregion volumes in BD patients. METHODS: Euthymic patients with bipolar I disorder (BD-I) aged 20-45 years underwent whole-brain magnetic resonance imaging. Plasma levels of monocyte chemoattractant protein-1 (MCP-1), chitinase-3-like protein 1 (also known as YKL-40), fractalkine (FKN), soluble tumour necrosis factor receptor-1 (sTNF-R1), interleukin-1ß, and transforming growth factor-ß1 were measured on the day of neuroimaging. Clinical data were obtained from medical records and interviewing patients and reliable others. RESULTS: We recruited 31 patients with a mean age of 29.5 years. In multivariate regression analysis, plasma level YKL-40, a chemokine, was the most common inflammatory marker among these measurements displaying significantly negative association with the volume of various brain subareas across the frontal, temporal, and parietal lobes. Higher YKL-40 and sTNF-R1 levels were both significantly associated with lower volumes of the left anterior cingulum, left frontal lobe, right superior temporal gyrus, and supramarginal gyrus. A greater number of total lifetime mood episodes were also associated with smaller volumes of the right caudate nucleus and bilateral frontal lobes. CONCLUSIONS: The volume of brain regions known to be relevant to BD-I may be diminished in relation to higher plasma level of YKL-40, sTNF-R1, and more lifetime mood episodes. Macrophage and macrophage-like cells may be involved in brain volume reduction among BD-I patients.

Body mass index, residual psychotic symptoms, and inflammation associated with brain volume reduction in older patients with schizophrenia.

Obesity, aging, and pathophysiology of schizophrenia (SCZ) may collectively contribute to the gray matter loss in brain regions of SCZ. We attempted to examine the association between volumes of specific brain regions, body mass index (BMI), inflammatory markers, and clinical features in older SCZ patients. METHOD: Clinically stable outpatients with schizophrenia (DSM-IV) aged ≥50 years were recruited to undergo whole-brain magnetic resonance imaging. We measured patients' plasma levels of soluble tumor necrosis factor receptor-1, soluble interleukin (IL)-2 receptor (sIL-2R), IL-1ß, and IL-1 receptor antagonist (IL-1Ra). Clinical data were obtained from medical records and interviewing patients along with their reliable others. RESULTS: There were 32 patients with mean age 58.8 years in this study. Multivariate regression analysis found only higher BMI significantly associated with lower volume of total gray matter, bilateral orbitofrontal and prefrontal cortexes, and the right hippocampal and frontal cortexes. Increased intensity of residual symptoms (higher Positive and Negative Syndrome Scale scores) was related to lower volumes of frontal lobe, prefrontal cortex, insula, hippocampus, left hemisphere amygdala, and total white matter. The lower volume of left anterior cingulum was associated with older age and higher sIL-2R plasma level; and higher IL-1Ra level was associated with greater right anterior cingulate volume. Older age at illness onset was significantly associated with the smaller right insula volume. CONCLUSIONS: Higher BMI, more residual symptoms, and inflammatory activity in IL-2 and IL-1 systems may play a role in gray matter loss in various brain regions of schizophrenia across the life span.

The association between carotid atherosclerosis and treatment with lithium and antipsychotics in patients with bipolar disorder.

OBJECTIVES: Patients with bipolar disorder are at high risk of cardiovascular diseases. Among cardiovascular diseases, coronary heart disease and stroke are the leading causes of premature death and both share the pathogenesis of arterial atherosclerosis. Increased carotid intima-media thickness is sensitive for detecting early atherosclerosis and a practical index for predicting cardiovascular diseases. However, few studies investigated carotid intima-media thickness in adults with bipolar disorder. We attempted to determine the factors associated with carotid intima-media thickness in adults with bipolar disorder. METHODS: The euthymic out-patients with bipolar I disorder aged over 20 years were recruited to measure the carotid intima-media thickness value through B-mode carotid ultrasound. Those with any psychiatric disorder, acute or life-threatening medical condition were excluded. All clinical information was obtained by reviewing medical records and directly interviewing patients with reliable others. RESULTS: Of the 106 participants with a mean age of 44.5 years, 40.6% (N = 43) had concurrent cardiovascular/endocrine/metabolic diseases. A multivariate regression indicated that higher assumed daily lithium dosage was significantly associated with a decreased carotid intima-media thickness in the whole sample. In the young subgroup (⩽45 years old, N = 63), higher current daily lithium dosage and lower body mass index were associated with lower carotid intima-media thickness. In those without concurrent cardiovascular/endocrine/metabolic diseases, higher ratio of first-generation antipsychotics exposure in relation to illness chronicity was associated with higher carotid intima-media thickness, after controlling for body mass index or age. CONCLUSION: Lithium treatment may be associated with less progression in carotid intima-media thickness and the reduced risk for atherosclerosis in adults with bipolar disorder, including those with high cardiovascular disease risk. In addition to age and body mass index, antipsychotics may increase carotid intima-media thickness even in the low cardiovascular disease-risk patients.

Differences in outcomes between older community-dwelling patients with bipolar disorder and schizophrenia with illness onset at young age.

AIM: Older community-dwelling patients with severe mental illness (SMI), particularly those with illness onset at young age, constitute a group of survivors with unique long-term care needs. Using an Asian sample in Taiwan, we attempted to find out the differences in outcomes related to physical health, cognition, and social functioning between older community-dwelling adults with bipolar disorder and schizophrenia with early age onset. METHODS: Community-dwelling patients aged >50 years with bipolar I disorder or schizophrenia whose illness developed before the age of 40 years were recruited. Clinical data were obtained by reviewing all available medical records and by interviewing the patients and their reliable family members. Medical morbidities, Mini-Mental State Examination (MMSE), Cumulative Illness Rating Scale for Geriatrics (CIRS-G), and Global Assessment of Functioning (GAF) scores were compared between the two groups. RESULTS: In total, 113 bipolar patients and 104 schizophrenic ones (mean ages = 59.8 and 59.2 years, respectively) became the final subjects. The rates of cognitive impairment (MMSE score <24) were comparable in bipolar disorder (26.5%) and schizophrenia (24.0%) and the mean MMSE scores did not significantly differ from each other. The concurrence (54.9%) of cardiovascular disease (CVD) in the bipolar group was also similar to 51.0% in the schizophrenic one. In a multiple logistic regression analysis, the bipolar group exhibited significantly higher CIRS-G total scores (95% confidence interval (CI) for odds ratio (OR) = 1.01-1.27), body mass index (95% CI for OR = 1.02-1.21), and GAF scores (95% CI for OR = 1.04-1.14). CONCLUSION: Given better social functioning and the same cognitive function in older community-dwelling patients with bipolar disorder, they may remain at higher risk for obesity and medical morbidity than schizophrenic patients. Treatments targeting cognitive impairment and CVDs across their life span are both necessary to promote the health of community-dwellers with SMI.

High risk of silent stroke in older bipolar patients with typical-onset age.

AIM: Older patients with bipolar disorder (BD) are at a high risk of stroke. Silent stroke could be neglected in BD patients after middle age, particularly in those with illness onset at the young age. Therefore, we investigated the morbidity and related factors for stroke in older BD patients with typical-onset age. METHODS: Older patients with bipolar I disorder (age > 50 years) and their illness onset prior to the age of 40 years were recruited. After whole-brain magnetic resonance imaging was conducted, the patients were divided into stroke and non-stroke groups. Clinical data were obtained by reviewing all available medical records and directly interviewing the patients along with their reliable family members. RESULTS: We recruited 62 patients with a mean age of 60.4 years and illness onset at the mean age of 28.4 years. Cerebral infarction or old stroke was observed in 24 (38.7%) patients, including 22 without any reported clinical history of stroke. That is, silent stroke (n = 22) was detected in 36.7% of 60 patients without clinical history of stroke. The stroke group had significantly higher mean numbers of lifetime mood episodes (P = 0.006) than the non-stroke one. Logistic regression analysis showed that 10 or more prior mood episodes (odds ratio = 3.43, 95% confidence interval = 1.12-10.47, P < 0·04) was significantly associated with the occurrence of stroke. The two study groups did not exhibit any other differences in demographic and clinical variables, such as age, laboratory or physical measurements during the last acute psychiatric hospitalisation, body mass index, and substance use problems and concurrent medical diseases. CONCLUSIONS: High morbidity of stroke, particularly silent stroke, could be found in older bipolar patients with typical-onset age. In addition to traditional risk factors, the number of recurrent mood episodes in a lifetime may increase the risk of stroke in older BD patients.

State-dependent alterations of lipid profiles in patients with bipolar disorder.

Objective Serum lipid levels may be associated with the affective severity of bipolar disorder, but data on lipid profiles in Asian patients with bipolar disorder and the lipid alterations in different states of opposite polarities are scant. We investigated the lipid profiles of patients in the acute affective, partial, and full remission state in bipolar mania and depression. Methods The physically healthy patients aged between 18 and 45 years with bipolar I disorder, as well as age-matched healthy normal controls were enrolled. We compared the fasting blood levels of glucose, cholesterol, triglyceride, low-density lipoprotein, and high-density lipoprotein of manic or depressed patients in the acute phase and subsequent partial and full remission with those of their normal controls. Results A total of 32 bipolar manic patients (12 women and 20 men), 32 bipolar depressed participants (18 women and 14 men), and 64 healthy control participants took part in this study. The mean cholesterol level in acute mania was significantly lower than that in acute depression (p < 0.025). The lowest rate of dyslipidemia (hypertriglyceridemia or low high-density lipoprotein cholesterol) was observed in acute bipolar mania. Conclusion Circulating lipid profiles may be easily affected by affective states. The acute manic state may be accompanied by state-dependent lower cholesterol and triglyceride levels relative to that in other mood states.

Antibody profiling of bipolar disorder using Escherichia coli proteome microarrays.

To profile plasma antibodies of patients with bipolar disorder (BD), an E. coli proteome microarray comprising ca. 4200 proteins was used to analyze antibody differences between BD patients and mentally healthy controls (HCs). The plasmas of HCs and patients aged 18-45 years with bipolar I disorder (DSM-IV) in acute mania (BD-A) along with remission (BD-R) were collected. The initial samples consisting of 19 BD-A, 20 BD-R, and 20 HCs were probed with the microarrays. After selecting protein hits that recognized the antibody differences between BD and HC, the proteins were purified to construct BD focus arrays for training diagnosis committees and validation. Additional six BD-A, six BD-R, six HCs, and nine schizophrenic disorder (SZ, as another psychiatric control) samples were individually probed with the BD focus arrays. The trained diagnosis committee in BD-A versus HC combined top six proteins, including rpoA, thrA, flhB, yfcI, ycdU, and ydjL. However, the optimized committees in BD-R versus HC and BD-A versus BD-R were of low accuracy (< 0.6). In the single blind test using another four BD-A, four HC, and four SZ samples, the committee of BD-A versus HC was able to classify BD-A versus HC and SZ with 75% sensitivity and 80% specificity that both HC and SZ were regarded as negative controls. The consensus motif of the six proteins, which form the committee of BD-A versus HC, is [KE]DIL[AG]L[LV]I[NL][IC][SVKH]G[LV][VN][LV] by Gapped Local Alignment of Motifs. We demonstrated that the E. coli proteome microarray is capable of screening BD plasma antibody differences and the selected proteins committee was successfully used for BD diagnosis with 79% accuracy.

Risk factors for early cardiovascular mortality in patients with bipolar disorder.

AIM: We attempted to determine risk factors, particularly pathophysiological changes, for early cardiovascular mortality in bipolar disorder (BD). METHODS: A total of 5416 inpatients with bipolar I disorder were retrospectively followed through record linkage for cause of death. A total of 35 patients dying from cardiovascular disease (CVD; ICD 9: 401-443) before the age of 65 years were identified. Two living BD patients and two mentally healthy adults were matched with each deceased patient as control subjects according to age (±2 years), sex, and date (±3 years) of the final/index admission or the date of general health screening. Data were obtained through medical record reviews. RESULTS: Eighty percent of CVD deaths occurred within 10 years following the index admission. Conditional logistic regression revealed that the variables most strongly associated with CVD mortality were the leukocyte count and heart rate on the first day of the index hospitalization, as the deceased BD patients were compared with the living BD controls. Systolic pressure on the first day of the index hospitalization can be substituted for heart rate as another risk factor for CVD mortality. CONCLUSION: It is suggested that systemic inflammation and sympathetic overactivity during the acute phase of BD may be risk factors for early CVD mortality.

Psychological Outcomes and Medical Morbidity of Patients With Bipolar Disorder and Co-Occurring Alcohol Use Disorder.

OBJECTIVE: Patients with bipolar disorder are at a high risk for comorbid alcohol use disorder, and both disorders are associated with poor outcomes and multiple morbidities. This study aimed to explore not only the psychosocial functioning and psychopathological outcomes but also the medical morbidity of patients with bipolar disorder with and without alcohol use disorder. METHODS: Outpatients with bipolar I disorder (DSM-IV) were recruited from a psychiatric teaching hospital in Taiwan (N = 393). Data on psychiatric symptoms, psychosocial functioning, and physical health were obtained through interviews with patients and collaterals, patient self-report, and medical record reviews. RESULTS: Participants had a mean age of 41.1 years (SD = 11.9) and were mostly female (n = 255, 64.9%). Fewer than 10% (n = 34, 8.7%) met criteria for alcohol use disorder, and these participants were more likely to be male, to smoke, and to have a history of rapid cycling, higher mean body mass index, and higher incidences of gastrointestinal and hepatobiliary morbidities. A multiple logistic regression analysis revealed that patients with, versus those without, alcohol use disorder were more prone to gastrointestinal diseases (adjusted OR = 4.25, 95% CI [1.44-12.53], p <.01), hepatobiliary diseases (adjusted OR = 3.14, 95% CI [1.20-8.25], p <.025), and history of rapid cycling (adjusted OR = 2.53, 95% CI [0.91-7.01], p <.075). CONCLUSIONS: Comorbid alcohol use disorders may have a stronger impact on physical health than on psychosocial or psychopathological outcomes of patients with bipolar disorder.

Neuroprogressive effects of lifetime illness duration in older adults with bipolar disorder.

OBJECTIVE: The aim of the present study was to examine the long-term effects of bipolar disorder (BD) on brain structure (gray matter volumes). METHODS: Fifty-four adults with BD [mean (standard deviation) age = 64.4 (5.4) years] underwent brain MR imaging along with comprehensive clinical assessment. Total gray matter, hippocampal, and amygdala volumes were extracted using methods developed through the Geriatric Neuroimaging Laboratory at the University of Pittsburgh (Pittsburgh, PA, USA). RESULTS: Lower total gray matter volumes were related to longer duration of BD, even when controlling for current age and cerebrovascular accident (CVA) risk/burden. Additionally, longer exposure to antipsychotic medication was related to lower gray matter volumes. Lower hippocampal volumes were related to total years of antipsychotic agent exposure and CVA risk/burden scores. Older age was related to lower total gray matter, hippocampal, and amgydala volumes. CONCLUSIONS: Our study of older adults with BD supports the understanding that BD is a neuroprogressive disorder with a longer duration of illness and more antipsychotic agent exposure related to lower gray matter volume.

Persistent inflammation and its relationship to leptin and insulin in phases of bipolar disorder from acute depression to full remission.

OBJECTIVE: A proinflammatory phase with various immunomodulatory mechanisms has been noted in bipolar mania and major depression. Weight gain and increased production of leptin may be associated with immunomodulation and insulin resistance in bipolar disorder. However, immunomodulation and its linkage with leptin and insulin in the depressive episode of bipolar disorder remain unclear. We investigated alterations in inflammatory markers and their relationship with leptin and insulin levels in patients with phases of bipolar disorder from acute depression to full remission. METHODS: Thirty-two physically healthy bipolar I depressed patients aged <45 years and age- and sex-matched healthy controls participated in this study. We measured their circulating levels of leptin, insulin, high-sensitivity C-reactive protein (hs-CRP), soluble interleukin-2 receptor (sIL-2R), soluble interleukin-6 receptor (sIL-6R), soluble tumor necrosis factor receptor 1 (sTNF-R1), and interleukin-1 receptor antagonist (IL-1Ra) in three phases, i.e., acute depression, subsequent partial remission, and full remission. RESULTS: In acute depression, subsequent partial remission, and full remission, patients with bipolar disorder had significantly higher mean levels of hs-CRP, IL-1Ra, sTNF-R1, and sIL-2R compared with control subjects. The IL-1Ra and sTNF-R1 levels in various affective phases were significantly correlated to body mass index, leptin level, circulating lipids, and medication status. The sIL-2R levels in the three affective phases were all independent of other inflammatory markers and clinical and laboratory variables. Patients showed no alteration of sIL-6R levels through the depressive episode. CONCLUSIONS: Patients with bipolar disorder in depressive episodes may exhibit persistent inflammation with elevated levels of hs-CRP, IL-1Ra, sTNF-R1, and sIL-2R but not sIL-6R from the acute phases to full remission. Only sIL-2R production seems to be tightly linked with the pathophysiology of bipolar depression and is independent of insulin and leptin levels.

Bladder pain syndrome/interstitial cystitis is associated with anxiety disorder.

AIM: Recent research demonstrated that bladder pain syndrome/interstitial cystitis (BPS/IC) is associated with many coexisting physical and psychiatric conditions. In this study, we explored the potential association between anxiety disorder (AD) and BPS/IC using a case-controlled population-based approach in Taiwan. METHODS: Data on the sampled subjects analyzed in this study were retrieved from the Longitudinal Health Insurance Database 2000. Our study included 396 female cases with BPS/IC and 1,980 randomly selected female controls. We excluded subjects who had a history of major psychosis (except AD) or a substance-related disorder. A conditional logistic regression was performed to calculate the odds ratio (OR) for the association between a previous diagnosis of AD and IC/BPS. RESULTS: Of the 2,376 sampled subjects, 136 (5.72%) had received an AD diagnosis. AD was found in 64 (16.16%) cases and in 72 (3.64%) controls (P < 0.001). The conditional logistic regression analysis (conditioned on age group and the index year) suggested that compared to controls, the OR for prior AD among cases was 4.59 (95% confidence interval (CI) = 2.32-9.08, P < 0.001). After adjusting for chronic pelvic pain, irritable bowel syndrome, fibromyalgia, migraines, sicca syndrome, allergies, asthma, and an overactive bladder, the OR for prior AD among cases was 4.37 (95% CI = 2.16-8.85, P < 0.001) compared to the controls. CONCLUSIONS: There was an association between AD and BPS/IC, even after taking demographic characteristics, medical co-morbidities, and substance-related disorders into consideration. Results of this study should alert clinicians to evaluate and monitor the presence of BPS/IC in patients with AD.

Association of lipids and inflammatory markers with left ventricular wall thickness in patients with bipolar disorder.

BACKGROUND: Individuals with bipolar disorder (BD) face a high risk of heart failure and left ventricular (LV) dysfunction. Despite strong evidence that high LV relative wall thickness (RWT) is a risk marker for heart failure, few studies have evaluated LV RWT and aggravating factors in individuals with BD. METHODS: We recruited 104 participants (52 patients with BD and 52 age- and sex-matched mentally healthy controls) to undergo echocardiographic imaging and biochemistry, high-sensitivity C-reactive protein (hs-CRP), and blood cell count measurements. LV RWT was estimated using the following equation: (2 × LV posterior wall end-diastolic thickness)/LV end-diastolic diameter. Clinical data were obtained through interviews and chart reviews. RESULTS: The BD group exhibited a significantly greater LV RWT (Cohen's d = 0.53, p = 0.003) and a less favorable mitral valve E/A ratio (Cohen's d = 0.54, p = 0.023) and LV global longitudinal strain (Cohen's d = 0.57, p = 0.047) than did the control group. Multiple linear regression revealed that in the BD group, serum triglyceride levels (ß = 0.466, p = 0.001), platelet-to-lymphocyte ratios (ß = 0.324, p = 0.022), and hs-CRP levels (ß = 0.289, p = 0.043) were all significantly and positively associated with LV RWT. LIMITATIONS: This study applied a cross-sectional design, meaning that the direction of causation could not be inferred. CONCLUSIONS: Patients with BD are at a risk of heart failure, as indicated by their relatively high LV RWT. Lipid levels and systemic inflammation may explain this unfavorable association.

Depression assessment using integrated multi-featured EEG bands deep neural network models: Leveraging ensemble learning techniques.

Mental Status Assessment (MSA) holds significant importance in psychiatry. In recent years, several studies have leveraged Electroencephalogram (EEG) technology to gauge an individual's mental state or level of depression. This study introduces a novel multi-tier ensemble learning approach to integrate multiple EEG bands for conducting mental state or depression assessments. Initially, the EEG signal is divided into eight sub-bands, and then a Long Short-Term Memory (LSTM)-based Deep Neural Network (DNN) model is trained for each band. Subsequently, the integration of multi-band EEG frequency models and the evaluation of mental state or depression level are facilitated through a two-tier ensemble learning approach based on Multiple Linear Regression (MLR). The authors conducted numerous experiments to validate the performance of the proposed method under different evaluation metrics. For clarity and conciseness, the research employs the simplest commercialized one-channel EEG sensor, positioned at FP1, to collect data from 57 subjects (49 depressed and 18 healthy subjects). The obtained results, including an accuracy of 0.897, F1-score of 0.921, precision of 0.935, negative predictive value of 0.829, recall of 0.908, specificity of 0.875, and AUC of 0.8917, provide evidence of the superior performance of the proposed method compared to other ensemble learning techniques. This method not only proves effective but also holds the potential to significantly enhance the accuracy of depression assessment.