Detection of Minor and Major Depression through Voice as a Biomarker Using Machine Learning

Both minor and major depression have high prevalence and are important causes of social burden worldwide; however, there is still no objective indicator to detect minor depression. This study aimed to examine if voice could be used as a biomarker to detect minor and major depression. Ninety-three subjects were classified into three groups: the not depressed group (n = 33), the minor depressive episode group (n = 26), and the major depressive episode group (n = 34), based on current depressive status as a dimension. Twenty-one voice features were extracted from semi-structured interview recordings. A three-group comparison was performed through analysis of variance. Seven voice indicators showed differences between the three groups, even after adjusting for age, BMI, and drugs taken for non-psychiatric disorders. Among the machine learning methods, the best performance was obtained using the multi-layer processing method, and an AUC of 65.9%, sensitivity of 65.6%, and specificity of 66.2% were shown. This study further revealed voice differences in depressive episodes and confirmed that not depressed groups and participants with minor and major depression could be accurately distinguished through machine learning. Although this study is limited by a small sample size, it is the first study on voice change in minor depression and suggests the possibility of detecting minor depression through voice.

Does Interactive Ultrasound Intervention Relieve Minor Depressive Symptoms in Pregnancy? A Randomized Controlled Trial

BackgroundPerinatal depression, especially minor depression, is common during pregnancy and is likely to continue into the postpartum period. It impairs the mother’s health, infant’s neurodevelopment, and the mother-infant relationship. Screening for perinatal depression is recommended; however, there is no uniform alignment of how to treat depressive symptoms while simultaneously supporting the mother-infant relationship. Ultrasound screenings might be potential as an intervention method because it has shown to improve maternal-fetal attachment among pregnant women. Our aim is to develop a 4 dimensional-based (4D) interactive ultrasound intervention and test whether it relieves minor depressive symptoms and improves maternal-fetal attachment. Previous studies show that supporting the mother-infant relationship aids in relieving maternal depression. Until now, few studies have combined pregnancy ultrasound and psychological support. MethodsA controlled randomized setting was designed to assess whether interactive 4D-ultrasound intervention would decrease maternal depressive symptoms, strengthen maternal-fetal attachment, and mother-infant relationship. A sonographer and a psychologist specialized in infant mental health conduct the interventions. The focus of the session is to jointly observe the behavior of the fetus according to the mothers’ wishes. Altogether, 100 women scoring 10-15 in Edinburgh Pre/-Postnatal Depression Scale (EPDS) and with singleton pregnancy will be recruited using a web-based questionnaire. Half of the participants will be randomized to the intervention group and will receive three interactive ultrasound examinations. The primary outcome is the change in the mean EPDS score. EPDS measurements will be done at three time points: before and after the intervention and four to five months after delivery. The secondary outcomes are maternal representations that will be assessed using the Working Model of the Child Interview (WMCI) and prenatal attachment that will be assessed using the Maternal Antenatal Attachment Scale (MAAS) questionnaire. The postnatal mother-infant interaction will be assessed with the Parent-Child Early Relational Assessment (PCERA) and Maternal Postnatal Attachment Scale (MPAS). DiscussionUltrasound is widely used during pregnancy. The interactive approach is unique and it would be feasible as part of routine screenings and maternity clinic visits. Intervention decreasing depression and simultaneously supporting maternal-fetal attachment could be a valuable addition in treating minor depression among pregnant women. Trial registrationRegistered on January 5th 2018, ClinicalTrials.gov NCT03424642. https://clinicaltrials.gov/ct2/show/NCT03424642

AB0118 REMISSION OF ANXIETY AND DEPRESSIVE DISORDERS IMPROVES HAQ TREATMENT RESPONSE IN RHEUMATOID ARTHRITIS PATIENTS

Background:Anxiety and depressive disorders (ADD) significantly affect disease activity and functional disability in rheumatoid arthritis (RA) patients. Psychopharmacotherapy (PPT) of ADD attempts to improve RA disease activity and lower progression of functional limitations.Objectives:To determine factors associated with HAQ treatment response in antidepressants-treated RA-patients at five years endpoint.Methods:128 RA-patients (pts) were enrolled, 86% were women with a mean age of 47,4±11,3 (M±SD) yrs. All patients met the full ACR/EULAR 2010 criteria for RA. Functional limitations were assessed using Health Assessment Questionnaire (HAQ), mean HAQ was 1,42±0,78 at baseline. 69,4% RA-pts were already taking prednisone (9 [5; 10] mg/day (Me (25%; 75%)), 84,4% - cDMARDs, 7,8% - bDMARDs (anti-TNF-α – 6,3%, rituximab – 1,6%). ADD were diagnosed by psychiatrist in 123 (96,1%) of RA-pts in accordance with ICD-10 in semi-structured interview. Severity of depression and anxiety was evaluated with Montgomery–Asberg Depression Rating Scale (MADRS) and Hamilton Anxiety Rating Scale (HAM-A). RA-pts with ADD were divided into the following treatment groups: 1 – сDMARDs (n=39), 2 – сDMARDs + PPT (sertraline or mianserine) (n=43), 3 – сDMARDs + bDMARDs (n=32), 4 – сDMARDs + bDMARDs + PPT (sertraline or mianserine) (n=9). Biologics treatment duration varied from 1 to 6 years, antidepressants – from 6 to 96 weeks. Baseline HAQ scores were 1,39±0,75, 1,42±0,9, 1,58±0,76 and 1,38±0,83 in groups 1-4, respectively. At 5-yrs endpoint in 83 RA-pts differences between baseline and endpoint HAQ scores (Δ HAQ = endpoint HAQ – baseline HAQ) were assessed as HAQ treatment response with minimal clinically important difference (MCID) (Δ HAQ ≥ 0,22). HAQ response rates were 4,2%, 65,5%, 47,6% and 76,7% in groups 1-4, respectively, with the lowest response rate in group 1 (p<0,0001). Logistic regression analysis was conducted to determine factors associated with RA remission rate.Results:By univariate logistic regression, anxiety and depressive symptoms remission at 5-yrs endpoint, baseline HAQ and major depression, lower baseline age, BMI and DAS28, no minor depression and cardiovascular diseases at baseline were significantly (p≤0,2) associated with HAQ treatment response (table 1). These variables were subjected to multivariate stepwise logistic regression. Only remission of anxiety and depressive symptoms at 5-yrs endpoint (OR 6,6 (95%CI 1,78 – 24,43), p=0,005), higher baseline HAQ (OR 2,61 (95%CI 1,12 – 6,11), p=0,027) and lower baseline BMI (OR 0,9 (95%CI 0,85 – 0,96), p=0,001) were independently associated with HAQ treatment response at 5-years follow-up.Table 1.Factors associated with RA remission at 5 years (univariate logistic regression).FactorpOR95%CIlowupAnxiety and depressive symptoms remission at 5-yrs endpoint0,0075,01,56116,016Baseline HAQ0,012,6571,2645,588Baseline major depression0,1422,0820,7825,542Baseline age0,0980,9920,9821,002Body mass index (BMI)0,0480,9810,9631,0Baseline minor depression0,1670,5630,2491,273Cardiovascular diseases0,10,4170,1471,183Baseline DAS280,0080,0771,0712,096Conclusion:higher HAQ and lower BMI at baseline and remission of anxiety and depressive symptoms at 5-yrs endpoint are independently associated with HAQ treatment response (MCID) at 5-years follow-up.Disclosure of Interests:None declared

Pharmacological Restoration of mOod in HEART Failure: outcomes of the PRO-HEART trial

Background Depression is common in chronic heart failure (CHF) patients and is associated with increased morbidity and mortality. Anti-depressant medication has shown benefits in coronary artery disease but efficacy has not been demonstrated in CHF patients. Purpose To assess whether escitalopram is more effective than placebo in treating major and/or minor depression in patients with CHF. Methods This was a randomized, placebo-controlled, double-blind, parallel group study. Adult patients with systolic CHF (NYHA Class ≥2, nadir LVEF &lt;40%) were screened for depression using the Cardiac Depression Scale (CDS) for a score ≥95 (sensitivity 97% at 85% specificity for major Depression (MDD)) followed by a clinical diagnosis of major or minor depression using the SCID interview. Patients were randomised to active escitalopram or matching placebo for 6 months, stratified for major or minor depression. Blinded therapy started with 5mg with automatic uptitration to 10mg after 2 weeks and further uptitration to 20mg at 2 months if CDS score remained ≥95. The primary end-point was change in CDS score over 6 months with secondary end-point change in Hamilton Depression Rating Scale (HAM-D). Results Of 28 CHF patients (males = 25; mean age = 63.61±10.32), mean CHF diagnosis 5.8 years, ischaemic aetiology (n=18), entry LVEF 42.2±9.6%; eGFR 61.8±15.4, 14 were diagnosed with major and 14 with minor depression. Two-way Mixed Model ANOVA showed a significant improvement from baseline to 6 months in both CDS (F(1,25)=18.76, p&lt;0.001) and HAM-D (F(1,25)=17.32, p&lt;0.001), but no significant interaction between condition and change over time. Three-way Mixed Model ANOVA showed no interaction between baseline depression diagnosis (Major or Minor) and response to treatment by condition. There were 7 SAEs for hospitalisation, unrelated to study medications and no differences between groups on AE/SAEs. Conclusions Patients showed a significant improvement in depression with both placebo and active drug but with no benefit of escitalopram over placebo. This suggests that there is no additional benefit from antidepressant therapy for CHF patients beyond that conferred by placebo. Further research is needed to explore whether greater benefits might be achieved by combination therapies or in particular subgroups of depressed CHF patients. Funding Acknowledgement Type of funding source: Foundation. Main funding source(s): National Heart Foundation of Australia, Beyond Blue

Depression and one-year survival of patients with heart failure in China: analysis from the China-PEACE Prospective Heart Failure study

Background Depression is prevalent among patients with heart failure (HF), but data exploring association of depression with risk of death in patients with HF is scarce in China. We investigated the relationship between depression and all-cause mortality of heart failure in China. Methods In China PEACE 5p-HF Study, we prospectively enrolled patients primarily hospitalized with HF from 52 diverse hospitals throughout China during 2016–2018. All the patients were followed up for 1 year. About 10% patients in the cohort from 41 hospitals was included for the measurement of depression state at convenience. Depression was measured by the Patient Health Questionnaire-8 depression scale (PHQ-8) at baseline. Depression state was categorized into major depressive disorder (10–24 points), minor depression (5–10 points) and no depression (0–5 points). Cox proportional hazards regression analyses, controlling for established risk factors as age, gender, LVEF, NYHA, medication use and medical history, were used to evaluate how depression were related to end point of death from any cause. Results Total 584 patients were included in our analysis, with median age 69 (IQR 60–77) years, and 40.8% female. Among these patients, 36.0% had major depressive disorder (n=210), 33.9% had minor depression (n=198). There were 70 (12%) patients died within 1 year after discharge. Major depressive disorder was associated with higher all-cause mortality compared with no depression (hazard ratio=2.18, 95% confidence interval 1.36–3.50, p=0.001). While minor depression was not significantly associated with all-cause mortality. Conclusions Major depression is an independent risk factor for all-cause mortality in hospitalized patients with HF in China. It is necessary to screen for psychological health in hospitalized patients to targeting intervention. Funding Acknowledgement Type of funding source: Public Institution(s). Main funding source(s): National Key Research and Development Program from the Ministry of Science and Technology of China

Evaluation of the depressive state of mobile technical systems operator subjected to electromagnetic noise radiation

This paper presents the results of the work aimed at a study of the patterns of changes in the nonlinear electroencephalogram (EEG) parameters, including fractal dimension and self-similarity exponent, when the operator is irradiated with electromagnetic noise radiation. Together with the above-mentioned nonlinear parameters, a change in the spectral power density of the rhythmic components in EEG (delta-, theta-, alpha-, and beta-rhythms) has been studied. Investigation of the fractal dimension, self-similarity exponent, and spectral power density during irradiation was associated with possible changes of the parameters in the case of operator’s depression or minor depression. The radiation source was represented by a transistor electromagnetic-noise generator with the power of 30 mW operating over the frequency range of 5 GHz. The methods for calculation of the nonlinear parameters including fractal dimension and self-similarity exponent have been described. To realize the principal objectives of the work, the Java-based software was developed. The relevant literature demonstrating the changes in fractal dimension, self-similarity exponent, spectral power density of the delta-, theta-, alpha-, beta-rhythms in the case of depression and minor depression has been reviewed. Electroencephalograms were registered according to the “10/20” scheme using the MBN Neurocartograph electroencephalograph. The analyzed leads were Fp1, Fp2, T3, T4, P3, P4, O1, O2, F3, F4, C3, C4. As shown by the results of this work, there is no distinct depressive state of the operator exposed to electromagnetic noise radiation, judging by changes in the self-similarity exponent, fractal dimension, and spectral power density. However, when the operator was irradiated with electromagnetic noise radiation, the observed tendency in variation of the parameters was characteristic for minor depression.

Concomitants of Depressive Symptoms in Memory Clinic Patients

This paper investigates how depressive symptoms are related to a comprehensive range of factors including sex, age, education, family history with dementia, subjective cognitive complaints (SCC), objective cognitive impairment, and sleep quality. The sample consisted of 958 memory-clinic patients of a large innercity academic memory clinic in Germany. In line with studies from other countries, 53.1% suffered from minor depression and 11.1% from major depression. In the linear regression (25% explained variance), younger age, lower education, and bad sleep quality were found to be predictors of depressive symptoms, while sleep quality turned out to have the largest effect; SCC and objective memory impairment were insignificant. Results underline the importance of memory clinics as gatekeepers to manage depression beyond the assessment of dementia.