Action recommendations review in community-based therapy and depression and anxiety outcomes: a machine learning approach.

BACKGROUND: While the positive impact of homework completion on symptom alleviation is well-established, the pivotal role of therapists in reviewing these assignments has been under-investigated. This study examined therapists' practice of assigning and reviewing action recommendations in therapy sessions, and how it correlates with patients' depression and anxiety outcomes. METHODS: We analyzed 2,444 therapy sessions from community-based behavioral health programs. Machine learning models and natural language processing techniques were deployed to discern action recommendations and their subsequent reviews. The extent of the review was quantified by measuring the proportion of session dialogues reviewing action recommendations, a metric we refer to as "review percentage". Using Generalized Estimating Equations modeling, we evaluated the correlation between this metric and changes in clients' depression and anxiety scores. RESULTS: Our models achieved 76% precision in capturing action recommendations and 71.1% in reviewing them. Using these models, we found that therapists typically provided clients with one to eight action recommendations per session to engage in outside therapy. However, only half of the sessions included a review of previously assigned action recommendations. We identified a significant interaction between the initial depression score and the review percentage (p = 0.045). When adjusting for this relationship, the review percentage was positively and significantly associated with a reduction in depression score (p = 0.032). This suggests that more frequent review of action recommendations in therapy relates to greater improvement in depression symptoms. Further analyses highlighted this association for mild depression (p = 0.024), but not for anxiety or moderate to severe depression. CONCLUSIONS: An observed positive association exists between therapists' review of previous sessions' action recommendations and improved treatment outcomes among clients with mild depression, highlighting the possible advantages of consistently revisiting therapeutic homework in real-world therapy settings. Results underscore the importance of developing effective strategies to help therapists maintain continuity between therapy sessions, potentially enhancing the impact of therapy.

Response inhibition related neural oscillatory patterns show reliable early identification of bipolar from unipolar depression in a Go/No-Go task.

BACKGROUND: Response inhibition is a key neurocognitive factor contributing to impulsivity in mood disorders. Here, we explored the common and differential alterations of neural circuits associated with response inhibition in bipolar disorder (BD) and unipolar disorder (UD) and whether the oscillatory signatures can be used as early biomarkers in BD. METHODS: 39 patients with BD, 36 patients with UD, 29 patients initially diagnosed with UD who later underwent diagnostic conversion to BD, and 36 healthy controls performed a Go/No-Go task during MEG scanning. We carried out time-frequency and connectivity analysis on MEG data. Further, we performed machine learning using oscillatory features as input to identify bipolar from unipolar depression at the early clinical stage. RESULTS: Compared to healthy controls, patients had reduced rIFG-to-pre-SMA connectivity and delayed activity of rIFG. Among patients, lower beta power and higher peak frequency were observed in BD patients than in UD patients. These changes enabled accurate classification between BD and UD with an accuracy of approximately 80 %. CONCLUSIONS: The inefficiency of the prefrontal control network is a shared mechanism in mood disorders, while the abnormal activity of rIFG is more specific to BD. Neuronal responses during response inhibition could serve as a diagnostic biomarker for BD in early stage.

Adipocytokines levels as potential biomarkers for discriminating patients with a diagnosis of depressive disorder from healthy controls.

BACKGROUND: Depressive disorder is a complex mental health condition in which the etiopathogenesis involves several factors. Suitable biomarkers for the development of depression have not yet been established. Alterations in cytokines are assumed to be involved in the pathophysiology of depressive disorder. Adipokines (also known as adipocytokines) are important factors that not only regulate the energy balance but also regulate the inflammatory and immune responses. This study investigated the serum levels of adiponectin, leptin, resistin, chemerin, and fetuin A and the possible role of these adipokines in depressive disorder. METHODS: We recruited a total of 73 patients diagnosed with recurrent depressive disorder (rDD) and 54 age- and sex-matched healthy controls (HCs). Serum adipocytokines were determined using ELISA kits (R&D, USA). The serum levels of the investigated molecules between depressive patients and HCs were compared, and diagnostic values were evaluated using the receiver operating characteristic (ROC) curve method for discriminating depressive patients from HCs. Correlations between the molecules and clinical variables were also evaluated. RESULTS: Patients with rDD had lower levels of serum adiponectin and chemerin and higher levels of serum leptin, resistin and fetuin A (p < 0.05) vs. controls. Moreover, ROC curve analysis showed that the area under the curve (AUC) values of above set of adipocytkines were >0.7, with a sensitivity and specificity over 80% in discriminating patients with rDD from HCs. CONCLUSIONS: These results suggest that circulating adipocytokies may hold promise as biomarkers for the diagnosis of rDD.

Depressive Disorder Remote Detection through Touchscreen Typing Behaviour.

Depressive Disorder (DD) is a leading cause of disability worldwide. Passive tools for screening the symptoms of DD are essential in monitoring and limiting the spread of the disease. From an alternative perspective, individuals' kinetic expression and activities, including smartphone interaction, reflect their mental status. Such widely available data in everyday life form a promising source of information on keystroke dynamics and their characteristics. This work explores how keystroke dynamics derived from touchscreen typing patterns have revealed the diagnosis of mental disorders, particularly depressive disorders. Different deep learning approaches were established to detect patients' depressive tendencies denoted by the self-reported Patient Health Questionnaire-9 (PHQ-9) score based on keystroke digital biomarkers. In particular, Convolutional Neural Networks (CNN), Long-Short-Term-Memory (LSTM), and CNN-LSTM models were examined and compared. The keystroke sequences are captured unobtrusively during routine interaction with touchscreen smartphones in a non-clinical setting. This study used 23,264 typing sessions provided by 10 DD patients and 14 healthy controls (HC). The proposed approach was investigated under two keystroke feature combinations and validated utilizing a leave-one-subject-out (LOSO) cross-validation scheme. The best-performing LSTM-with-hold-time (LSTM-HT) model achieved an Area Under Curve (AUC) of 0.86 with the correlated probabilities for subjects' status [95% confidence interval (CI):0.66-1.00, sensitivity/specificity (SE/SP) of 0.8/0.93].Clinical relevance- The findings of this research have the potential to contribute to improving digital tools for objectively screening mental disorders in the wild. Moreover, they would potentially provide the users and their attending psychiatrists with information regarding the evolution of their mental health.

[Recent approaches to the diagnosis and therapy of monopolar depression]. / Sovremennye podkhody k diagnostike i terapii monopolyarnoi depressii.

Unipolar depression is one of the most significant biomedical problems, which is associated with its high prevalence, a pronounced negative impact on the level of work capacity of the population, worsening of the course of most somatic and neurological diseases, and suicide risk. This review presents current data on approaches to the diagnosis of monopolar depression, both classical (clinical and psychometric) and using modern technologies. The existing approaches to the therapy of monopolar depression - psychopharmacologic, psychotherapeutic, and non-drug biological approaches - are discussed. The advantages of the selective serotonin reuptake inhibitor sertraline are presented, and its use as a first-line drug is justified.

[Depressive disorders in adolescents in outpatient psychiatric practice]. / Depressivnye rasstroistva u podrostkov v ambulatornoi psikhiatricheskoi praktike.

OBJECTIVE: To clarify the clinical features of depressive states in adolescent boys and girls (taking into account age and sex) seeking help from primary care specialists in outpatient psychiatric care. MATERIAL AND METHODS: The study included 158 patients (89 boys and 69 girls), aged 15-17, with depressive pathology of various genesis, observed in the adolescent office of one of the Moscow psychoneurological dispensary in 2015-2020. The main research methods were clinical-psychopathological, clinical-follow-up, statistical. RESULTS: An analysis of the data demonstrated that adolescent depression can be observed within different diagnostic categories. Most often they were noted in patients with affective disorders (43%, n=68), emerging personality disorders (29%, n=46), schizotypal disorder (13%, n=21). The nosological affiliation of depression and its severity were associated with sex. In young men, depressive states were more often detected in the structure of emerging personality disorder (59.6%) and schizotypal disorder (15.7%), depressive states within affective disorders were detected in 22.5% of cases. In girls, most of the depressive episodes (69.6%) developed in the structure of affective disorders, less often in personality disorders (20.3%), and schizotypal disorder (10.1%). Depressive episodes in girls were predominantly of moderate severity, in boys the most common were mild depressions. CONCLUSION: Adolescent depressions are a nosologically heterogeneous group of affective disorders, differing in clinical phenomenology and prognosis. They are noted within the pathology of the affective spectrum, affective phases and psychogenic reactions acting in the dynamics of emerging personality disorders, within the framework of psychopathological diathesis, schizotypal disorder. The influence of sex on the development of depressive disorders is determined by the nosological framework of the condition.

Trajectories of depressive symptoms 10 years after stroke and associated risk factors: a prospective cohort study.

BACKGROUND: Previous studies have investigated the risk factors for post-stroke depression at only one timepoint, neglecting its dynamic nature. We aimed to identify trajectories of post-stroke depression from multiple assessments and explore their risk factors. METHODS: We did a population-based cohort study with the South London Stroke Register (1995-2019). All stroke patients with three or more measurements of the Hospital Anxiety and Depression Scale were included. We identified trajectories of post-stroke depression over a 10-year follow-up using group-based trajectory modelling. We determined the optimal number and shape of trajectories based on the lowest Bayesian information criterion, average posterior probability of assignment of each group over 0·70, and inclusion of at least 5% of participants within each group. We used multinomial logistic regression adjusted for age, sex, ethnicity, comorbidity, physical disability, stroke severity, history of depression and cognitive impairment to explore associations with different trajectories. FINDINGS: The analysis comprised 1968 participants (mean age 64·9 years [SD 13·8], 56·6% male and 43·4% female, 65·1% white ethnicity, 30·7% severe disability and 32·7% severe stroke). We identified four patterns of symptoms: no depressive symptoms (14·1%, n=277), low symptoms (41·7%, n=820), moderate symptoms and symptoms worsening early and then improving (34·6%, n=681), and high and increasing symptoms (9·7%, n=190). Compared with no depressive symptom trajectory, patients with severe disability, severe stroke, pre-stroke depression, and cognitive impairment were more likely to be in the moderate and high symptom groups (adjusted odds ratios [ORs] 2·26 [95% CI 1·56-3·28], 1·75 [1·19-2·57], 2·20 [1·02-4·74], and 2·04 [1·25-3·32], respectively). Female sex was associated with high depression (OR 1·65 [1·13-2·41]), while older age (≥65 years) was associated with moderate depression (OR 1·82 [1·36-2·45]). In men, the ORs for patients with severe disability, severe stroke, pre-stroke depression, and cognitive impairment being in the high depression group were 1·91 (1·01-3·60), 2·41 (1·26-4·60), 2·57 (0·84-7·88), and 2·68 (1·28-5·60), respectively. In women, the ORs were 1·08 (0·52-2·23), 1·30 (0·60-2·79), 19·2 (2·35-156·05), and 3·80 (1·44-10·01), respectively. INTERPRETATION: Female sex and older age were associated with distinct courses of depressive symptoms. In men, high depressive symptom trajectory was associated with severe stroke and severe disability, which was not the case in women. These findings were limited to patients with three or more assessments, who tended to have less severe disabilities than excluded patients and might not generalise to all stroke survivors. FUNDING: National Institute for Health and Care Research (NIHR).

Increases in primary opioid use disorder diagnoses co-occurring with anxiety or depressive disorder diagnoses in mental health treatment in the United States, 2015-2019.

BACKGROUND: Opioid use disorders (OUDs) often co-occur with anxiety and depressive disorders. While the proportion of mental health (MH) treatment facilities providing substance use treatment has increased, the proportion of these facilities able to simultaneously treat MH and substance use decreased. This warrants investigation into the integrated treatment needs of persons with a primary OUD diagnosis treated in MH treatment facilities. METHODS: Using the Mental Health Client Level Data, we examined a sample of N = 83,975 adults with OUD as their primary diagnosis who received treatment from a MH treatment facility in the United States from 2015 to 2019. Joinpoint regression was used to examine annual trends of the number of individuals with co-occurring anxiety or depression diagnoses. RESULTS: Most of the sample were men (53.7%) and received treatment in a community-based program (93.3%). Approximately 17% of the sample had either an anxiety or depressive disorder diagnosis. Approximately 9% of our sample had an anxiety disorder diagnosis, and 10% had a depressive disorder diagnosis. An increase in the number of individuals with a co-occurring anxiety disorder diagnosis from 2015 to 2019 was identified (annual percent change (APC) = 61.4; 95% confidence interval (CI) = [10.0, 136.9]; p =.029). An increase in the number of individuals with a co-occurring depressive disorder diagnosis from 2015 to 2019 was identified (APC = 39.0; 95% CI = [7.4; 79.9]; p =.027). CONCLUSIONS: This study highlights increases in adults receiving MH treatment for OUD having co-occurring anxiety or depression diagnoses, furthering the importance of integrated dual disorder treatment.

Development of a mobile monitoring program for anxiety and depression in pregnancy and evaluation of 3-month results.

BACKGROUND: The aims of this study were to develop a mobile mental health application (app) to scan the symptoms of anxiety, depression, and related factors during pregnancy; examine the effect of the app on pregnant women; and determine the factors related to using such an app. METHODS: A software platform called Perinatal Anxiety Depression Monitoring Platform (PADIP) was developed. This study included 320 pregnant women: 160 in the PADIP group and 160 in the control group. The PADIP group was screened monthly for 3 months for depression, anxiety, and sleep quality, and instant feedback was provided on scale scores. RESULTS: During the follow-up period, there was a significant decrease in depression and anxiety scale scores in the PADIP group but no significant difference in scale scores in the control group. The interface used for the app was important for scale scores. It was preferred by pregnant women with a high education level, higher Perinatal Anxiety Screening Scale scores, and lower sleep quality scores. CONCLUSIONS: PADIP use was associated with a decrease in depression and anxiety scores of pregnant women. It was more useful for patients with higher education levels and a history of a psychiatric disorder, but further research is needed to develop a more comprehensive model.

Depression symptom outcomes and re-engagement among VA patients who discontinue care while symptomatic.

OBJECTIVE: Evaluate outcomes of Veterans who discontinued treatment with at least moderate ongoing depressive symptoms. METHOD: Veterans with elevated depression symptoms from 29 Department of Veterans Affairs facilities completed baseline surveys and follow-up assessments for one year. Analyses examined rates and predictors of treatment discontinuation, treatment re-engagement, and subsequent symptoms among patients who remained out of care. RESULTS: A total of 242 (17.8%; n = 1359) participants discontinued treatment while symptomatic, with Black participants, participants with less severe depression, and participants receiving only psychotherapy (versus combined psychotherapy and antidepressant medications) discontinuing at higher rates. Among all participants who discontinued treatment (n = 445), 45.8% re-engaged within the following six months with participants receiving combined treatment re-engaging at higher rates. Of participants who discontinued while symptomatic within the first 6 months of the study and did not return to care (n = 112), 68.8% remained symptomatic at 12 months. Lower baseline treatment expectancy and greater depression symptom severity were associated with remaining symptomatic while untreated. CONCLUSIONS: Black race, lower symptom severity, and treatment modality may help identify patients at higher risk for discontinuing care while symptomatic, whereas patients with lower treatment expectations may be at greater risk for remaining out of care despite continuing symptoms.

Maternal aggressive behavior in interactions with adolescent offspring: Proximal social-cognitive predictors in depressed and nondepressed mothers.

Maternal depressive symptoms are associated with elevations in harsh parenting behavior, including criticism, negative affect, and hostile or coercive behavior, and these behaviors contribute to associations between maternal depressive symptomatology and child functioning. We used multilevel survival analysis to examine social-cognitive processes as proximal predictors of the onset and offset of maternal aggressive behavior during interactions with their adolescent children. Low-income women (N = 180) were selected for either: (a) elevated depressive symptoms and a history of treatment for depression (depressed group) or (b) not more than mild levels of current depressive symptomatology, no history of depression treatment, and no current mental health treatment (nondepressed group). These women and their adolescent children (ages 11-14, M = 12.93; 96 male sex, as assigned at birth) participated in a dyadic problem-solving interaction and mothers completed a video-mediated recall procedure, in which they watched a segment of the interaction, labeled their adolescents' affect, and made attributions for their behavior. Mothers in the depressed group were more likely to initiate aggressive behavior and, once initiated, were less likely to transition out of it. Mothers in both groups were less likely to transition out of aggressive behavior when they made negative attributions for their adolescents' behavior. Findings point to promising cognitive and behavioral targets for intervention. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Body mass index on perinatal depression: A critical viewpoint.

I am pleased to submit a viewpoint titled "Body mass index on perinatal depression: A critical viewpoint" in response to an article by Ventriglio et al. titled, "The impact of body mass index on the pregnancy outcomes and risk of perinatal depression: Findings from a multicenter Italian study" for consideration for publication in your journal.

Understanding Perinatal Depression Care Gaps by Examining Care Access and Barriers in Perinatal Individuals With and Without Psychiatric History.

Background: Depression affects one in seven perinatal individuals and remains underdiagnosed and undertreated. Individuals with a psychiatric history are at an even greater risk of perinatal depression, but it is unclear how their experiences with the depression care pathway may differ from individuals without a psychiatric history. Methods: We conducted a secondary analysis evaluating care access and barriers to care in perinatal individuals who screened positive for depression using the Edinburgh Postnatal Depression Scale (N = 280). Data were analyzed from the PRogram in Support of Moms (PRISM) study, a cluster randomized controlled trial of two interventions for perinatal depression. Results: Individuals with no prepregnancy psychiatric history (N = 113), compared with those with a history (N = 167), were less likely to be screened for perinatal depression, and less likely to be offered a therapy referral, although equally likely to attend if referred. When examining how these differences affected outcomes, those without a psychiatric history had 46% lower odds of attending therapy (95% confidence interval [CI]: 0.19-1.55), 79% lower odds of taking medication (95% CI: 0.08-0.54), and 80% lower odds of receiving any depression care (95% CI: 0.08-0.47). Barriers were similar across groups, except for concerns regarding available treatments and beliefs about self-resolution of symptoms, which were more prevalent in individuals without a psychiatric history. Conclusions: Perinatal individuals without a prepregnancy psychiatric history were less likely to be screened, referred, and treated for depression. Differences in screening and referrals resulted in missed opportunities for care, reinforcing the urgent need for universal mental health screening and psychoeducation during the perinatal period. Clinical Trial Registration No.: NCT02935504.

Burnout and depression: Points of convergence and divergence.

BACKGROUND: Debate is ongoing as to whether burnout can be differentiated from depression. This study evaluated whether burnout and depression could be distinguished using a new burnout measure and other variables. METHODS: Scores on the Sydney Burnout Measure (SBM) were compared between participants with self-diagnosed burnout (BO-all group; n = 622) and clinically-diagnosed depression (DEP-all group; n = 90). The latter group was split into melancholic (DEP-mel; n = 56) and non-melancholic (DEP-nonmel; n = 34) depression subgroups for subsequent analyses. Differences in reporting of depressive symptoms and causal attributions were also evaluated. RESULTS: While total SBM scores showed poor differentiation, the BO-all group had lower social withdrawal and higher empathy loss subscale scores than the depression groups. Odds ratios were significant for several of the depressive symptoms and causal attribution items when comparing the BO-all group to the DEP-all and DEP-mel groups, while only a few items were significant when comparing the BO-all and DEP-nonmel groups. LIMITATIONS: Participants in the depression group were assigned by clinician-based depression diagnoses, rather than by a standardised diagnostic interview, and the group had a relatively small sample size. Participants in the burnout group were self-diagnosed and not assessed for comorbid psychiatric diagnoses. CONCLUSIONS: There were some nuanced symptoms differences between burnout and depression, but many of the SBM symptoms were not specific to burnout. Results also suggested that burnout overlaps more with non-melancholic than melancholic depression, and that differentiation of burnout and depression may rely more on weighting causal factors over symptoms.

Changes in employment status and income before and after newly diagnosed depressive disorders in Taiwan: a matched cohort study using controlled interrupted time series analysis.

AIMS: We explored long-term employment status and income before and after depression diagnosis among men and women and at different working ages in Taiwan. METHODS: Data from 2006 to 2019 were obtained from the National Health Insurance Research Database (NHIRD). Individuals with newly diagnosed depressive disorder aged 15 to 64 years during the study period were identified. An equal number of individuals without depression were matched for their demographic and clinical characteristics. Employment outcomes included employment status, which was categorized into employed or unemployed, and annual income. Based on the occupation categories and monthly insurance salary recorded in the Registry for Beneficiaries of the NHIRD, a subject was defined as unemployed if he or she differed from the income earner or the occupation category was unemployed. Monthly income was defined as zero for unemployed subjects and proxied as monthly insurance salary for others. Annual income was the sum of monthly income in each observation year. RESULTS: A total of 420,935 individuals with depressive disorder were included in the study, and an equal number of individuals with not diagnosed depression served as controls. Employment rate and income were lower in the depression group than in the control group before the year of diagnosis, with a difference of 5.7% in employment rate and USD 1,173 in annual income. This gap increased considerably after the year of diagnosis (7.3% in employment rate and USD 1,573 in annual incomes) and further widened in the subsequent years (8.1% in employment rate and USD 2,006 in annual incomes in the 5th following year). The drops in the employment rate and income caused by depression were more evident in men and older age groups than in women and younger age groups, respectively. However, the reduction in employment rate and income in the following years after the diagnosis was more considerable among younger age groups. CONCLUSIONS: The effect of depression on employment status and income was significant during the year of diagnosis and continued afterwards. The effect on employment outcomes varied between genders and across all age groups.