Cross-platform Prediction of Depression Treatment Outcome Using Location Sensory Data on Smartphones

Research Highlights

In the literature, disagreement exists on the impact of Axis II comorbidity on the treatment outcome of depression. The aim of the present study was to examine in a naturalistic treatment setting the 1-year outcome and treatment characteristics of depressed adolescent outpatients with and without comorbid Axis II disorders. The 151 participants were interviewed for Axis I and II diagnoses at baseline and follow-up. Those diagnosed with a personality disorder were significantly more impaired at follow-up than those without. The given treatment did not differ between the two groups in length, intensity, or hospitalization, but the group with Axis II comorbidity received more psychotropic medication. The treatment outcome of depression was poorer for the group with Axis II disorders compared to those without. In conclusion, a personality disorder diagnosis is a sign of more severe overall symptoms. Special attention should be paid to Axis II traits when planning and conducting the treatment of adolescent depression.

In the literature, disagreement exists on the impact of Axis II comorbidity on the treatment outcome of depression. The aim of the present study was to examine in a naturalistic treatment setting the 1-year outcome and treatment characteristics of depressed adolescent outpatients with and without comorbid Axis II disorders. The 151 participants were interviewed for Axis I and II diagnoses at baseline and follow-up. Those diagnosed with a personality disorder were significantly more impaired at follow-up than those without. The given treatment did not differ between the two groups in length, intensity, or hospitalization, but the group with Axis II comorbidity received more psychotropic medication. The treatment outcome of depression was poorer for the group with Axis II disorders compared to those without. In conclusion, a personality disorder diagnosis is a sign of more severe overall symptoms. Special attention should be paid to Axis II traits when planning and conducting the treatment of adolescent depression.

Evidence suggests that childhood maltreatment may negatively affect not only the lifetime risk of depression but also clinically relevant measures of depression, such as course of illness and treatment outcome. The authors conducted the first meta-analysis to examine the relationship between childhood maltreatment and these clinically relevant measures of depression. The authors conducted searches in MEDLINE, PsycINFO, and Embase for articles examining the association of childhood maltreatment with course of illness (i.e., recurrence or persistence) and with treatment outcome in depression that appeared in the literature before December 31, 2010. Recurrence was defined in terms of number of depressive episodes. Persistence was defined in terms of duration of current depressive episode. Treatment outcome was defined in terms of either a response (a 50% reduction in depression severity rating from baseline) or remission (a decrease in depression severity below a predefined clinical significance level). A meta-analysis of 16 epidemiological studies (23,544 participants) suggested that childhood maltreatment was associated with an elevated risk of developing recurrent and persistent depressive episodes (odds ratio=2.27, 95% confidence interval [CI]=1.80–2.87). A meta-analysis of 10 clinical trials (3,098 participants) revealed that childhood maltreatment was associated with lack of response or remission during treatment for depression (odds ratio=1.43, 95% CI=1.11–1.83). Meta-regression analyses suggested that the results were not significantly affected by publication bias, choice of outcome measure, inclusion of prevalence or incidence samples, study quality, age of the sample, or lifetime prevalence of depression. Childhood maltreatment predicts unfavorable course of illness and treatment outcome in depression.

Accurate and up-to-date maps of built-up areas are crucial to support sustainable urban development. Earth Observation (EO) is a valuable data source to cover this demand. In particular, Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) missions offer new opportunities to map built-up areas on a global scale. Using Sentinel-2 images, recent urban mapping efforts achieved promising results by training Convolutional Neural Networks (CNNs) on available built-up data. However, these results strongly depend on the availability of local reference data for fully supervised training or assume that the application of CNNs to unseen areas (i.e. across-region generalization) produces satisfactory results. To alleviate these shortcomings, it is desirable to leverage Semi-Supervised Learning (SSL) algorithms that can take advantage of unlabeled data, especially because satellite data is plentiful. In this paper, we propose a novel Domain Adaptation (DA) approach using SSL that jointly exploits Sentinel-1 SAR and Sentinel-2 MSI to improve across-region generalization for built-up area mapping. Specifically, two identical sub-networks are incorporated into the proposed model to perform built-up area segmentation from SAR and optical images separately. Assuming that consistent built-up area segmentation should be obtained across data modality, we design an unsupervised loss for unlabeled data that penalizes inconsistent segmentation from the two sub-networks. Therefore, we propose to use complementary data modalities as real-world perturbations for consistency regularization. For the final prediction, the model takes both data modalities into account. Experiments conducted on a test set comprised of sixty representative sites across the world showed that the proposed DA approach achieves strong improvements (F1 score 0.694) over fully supervised learning from Sentinel-1 SAR data (F1 score 0.574), Sentinel-2 MSI data (F1 score 0.580) and their input-level fusion (F1 score 0.651). To demonstrate the effectiveness of DA, we also performed a comparison with two state-of-the-art products, namely GHS-BUILT-S2 and WSF 2019, on the test set. The comparison showed that our model is capable of producing built-up area maps with comparable or even better quality than the state-of-the-art global human settlement maps. Therefore, the multi-modal DA offers great potential to be adapted to produce easily updateable human settlements maps at a global scale.

A Brief Self-Report Measure to Assess Antidepressant Adherence Among Spanish-Speaking Latinos

P.2.f.016 Long-term outcomes in treatment of depression with venlafaxine ER 75–225 mg/d in the acute and continuation phases (PREVENT study)

Complementary Use of Tai Chi Chih Augments Escitalopram Treatment of Geriatric Depression: A Randomized Controlled Trial

Objective: Depression is a significant predictor of cancer death, but its impact on African Americans’ cancer treatment and treatment outcomes has not been well studied. This study examines the relationship between depression treatment, completion of cancer treatment, and treatment outcomes among African American cancer patients in comparison with Caucasian cancer patients in Northeast Ohio. Methods: Medical records for 34 depressed breast and prostate cancer patients (18 African Americans and 16 Caucasians) with duration of 5 to 8 years were reviewed. Data on the variables of baseline distress level, depression treatment status, completion of prescribed cancer treatment, and treatment outcome (i.e., cancer recurrence, metastasis, and death) were abstracted. Simple statistics (frequency) was performed on these variables for the African American and Caucasian patients that received depression treatment and those who did not, respectively. Results: In the study group, 30% of the African Americans with elevated baseline distress (≥4 on a 10-point Distress Thermometer) were treated for depression, as compared to 60% of the Caucasians. Three of five African Americans that reduced or discontinued chemotherapy or hormonal therapy did not receive depression treatment. At 5 to 8 years after an initial cancer diagnosis, two of the African Americans, one treated and the other untreated for depression, both had cancer recurrence. Another untreated African American in the study developed metastasis and then died. By contrast, none of the African Americans treated for depression developed metastasis or died. Conclusions: The findings suggest that under treatment of depression was associated with poor cancer treatment completion and treatment outcomes, especially in the African American group. Improving depression treatment of these patients deserves serious attention in future research.

The efficacy of antidepressant drug treatment in depression is unsatisfactory; 1 in 3 patients does not fully recover even after several treatment trials. Genetic factors and clinical characteristics contribute to the failure of a favorable treatment outcome. To identify genetic and clinical determinants of antidepressant drug treatment outcome in depression. Genomewide pharmacogenetic association study with 2 independent replication samples. We performed a genomewide association study in patients from the Munich Antidepressant Response Signature (MARS) project and in pooled DNA from an independent German replication sample. A set of 328 single-nucleotide polymorphisms highly related to outcome in both genomewide association studies was genotyped in a sample of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study. A total of 339 inpatients with a depressive episode (MARS sample), a further 361 inpatients with depression (German replication sample), and 832 outpatients with major depression (STAR*D sample). We generated a multilocus genetic variable that described the individual number of alleles of the selected single nucleotide polymorphisms associated with beneficial treatment outcome in the MARS sample ("response" alleles) to evaluate additive genetic effects on antidepressant drug treatment outcome. Multilocus analysis revealed a significant contribution of a binary variable that categorized patients as carriers of a high vs low number of response alleles in the prediction of antidepressant drug treatment outcome in both samples (MARS and STAR*D). In addition, we observed that patients with a comorbid anxiety disorder combined with a low number of response alleles showed the least favorable outcome. These results demonstrate the importance of multiple genetic factors combined with clinical features in the prediction of antidepressant drug treatment outcome, which underscores the multifactorial nature of this trait.

Studies Link Depression Treatment To Clinical Outcomes

Major depressive disorder is a relapsing syndrome with grave morbidity and mortality. Much like asthma, it has a genetic predisposition and environmental triggers. Specific antidepressant medications alone, tested in randomized, placebo-controlled studies, show that this is a treatable condition with 65%-70% clinical response. Treatment guidelines written for psychiatric patients and patients in primary care clarify the role of medications and psychotherapy. Physicians are compelled to treat syndromes that are serious and treatable, but barriers to diagnosis and treatment of major depressive disorder in cancer patients include two major barriers to quality medical care generally: uncertainty and cost. Given uncertainty about diagnosis and treatment, cancer physicians with limited time avoid questions about emotions. Cases of depression are often missed. Mental health specialists often work in systems that are separated from oncologists by location, organization, and insurance. Most successful interventions to improve treatment of depressive disorders require multiple strategies: clinical education, enhanced role of nurses, and integrated oncology and specialist care. Recent strategies in oncology settings are reviewed. Research concepts to improve outcomes in treatment of depression include staging of depressive disorder in cancer to reveal prognosis, evaluation of depression outcomes in the context of one tumor type, new organizational models in the acute cancer setting, use of the cancer protocol, and assessment of access to care of depression in cancer survivors. Major depressive disorder in cancer is staged by positive past history, comorbid anxiety disorder or substance abuse, use of specific cancer medications that destabilize mood, and active cancer or no evidence of disease.

Competence and adherence in an acceptance and values-based intervention: Effects on treatment outcome and early changes in depression

Interpersonal problems as a predictor of treatment outcome in adult depression: An individual participant data meta-analysis.

This randomized, placebo-controlled, double-blind, parallel study aimed to evaluate the effect of 3-month supplementation of bovine colostrum (BOV-COL; 8x400 mg per day) on the outcomes of depression treatment in hospitalized patients with substance use disorder (SUD). The hypothesis is that BOV-COL supplementation as an add-on treatment results in favorable alternations in selected blood inflammatory markers or neurotransmitters, leading to better depression treatment outcomes compared with placebo (PLA). Patients with a Minnesota Multiphasic Personality Inventory-2 score ≥60 points were enrolled. Twenty-nine participants (n=18 in the BOV-COL group and n=11 in the PLA group) completed the protocol. The mean Beck Depression Inventory-II score was significantly reduced after supplementation in both groups. However, the mean 17-point Hamilton Depression Rating Scale score was decreased in the BOV-COL group, but not in the PLA group. In the BOV-COL group, there was a reduction in interleukin (IL)-1, IL-6, IL-10, the IL-6:IL-10 ratio, IL-17, and tumor necrosis factor alpha (TNF-α), while in the PLA group only IL-6 decreased. Favorable alternations in the total count and differentials of white blood cell subsets were more pronounced in the BOV-COL. There were no changes in neurotransmitter concentrations. BOV-COL supplementation is a promising add-on therapy in patients with depression and SUD.