Machine Learning Prediction of Quality of Life Improvement During Antidepressant Treatment of Patients With Major Depressive Disorder: A STAR*D and CAN-BIND-1 Report.

Background: Quality of life (QoL) is an important patient-centric outcome to evaluate in treatment of major depressive disorder (MDD). This work sought to investigate the performance of several machine learning methods to predict a return to normative QoL in patients with MDD after antidepressant treatment.Methods: Several binary classification algorithms were trained on data from the first 2 weeks of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study (n = 651, conducted from 2001 to 2006) to predict week 9 normative QoL (score ≥ 67, based on a community normative sample, on the Quality of Life Enjoyment and Satisfaction Questionnaire-Short Form [Q-LES-Q-SF]) after treatment with citalopram. Internal validation was performed using a STAR*D holdout dataset, and external validation was performed using the Canadian Biomarker Integration Network in Depression-1 (CAN-BIND-1) dataset (n = 175, study conducted from 2012 to 2017) after treatment with escitalopram. Feature importance was calculated using SHapley Additive exPlanations (SHAP).Results: Random Forest performed most consistently on internal and external validation, with balanced accuracy (area under the receiver operator curve) of 71% (0.81) on the STAR*D dataset and 69% (0.75) on the CAN-BIND-1 dataset. Random Forest Classifiers trained on Q-LES-Q-SF and Quick Inventory of Depressive Symptomatology-Self-Rated variables had similar performance on both internal and external validation. Important predictive variables came from psychological, physical, and socioeconomic domains.Conclusions: Machine learning can predict normative QoL after antidepressant treatment with similar performance to that of prior work predicting depressive symptom response and remission. These results suggest that QoL outcomes in MDD patients can be predicted with simple patient-rated measures and provide a foundation to further improve performance and demonstrate clinical utility.Trial Registration: ClinicalTrials.gov identifiers NCT00021528 and NCT01655706.

Hypothalamus volume and DNA methylation of stress axis genes in major depressive disorder: A CAN-BIND study report.

Dysfunction of the hypothalamic-pituitary-adrenal (HPA) axis is considered one of the mechanisms underlying the development of major depressive disorder (MDD), but the exact nature of this dysfunction is unknown. We investigated the relationship between hypothalamus volume (HV) and blood-derived DNA methylation in MDD. We obtained brain MRI, clinical and molecular data from 181 unmedicated MDD and 90 healthy control (HC) participants. MDD participants received a 16-week standardized antidepressant treatment protocol, as part of the first Canadian Biomarker Integration Network in Depression (CAN-BIND) study. We collected bilateral HV measures via manual segmentation by two independent raters. DNA methylation and RNA sequencing were performed for three key HPA axis-regulating genes coding for the corticotropin-binding protein (CRHBP), glucocorticoid receptor (NR3C1) and FK506 binding protein 5 (FKBP5). We used elastic net regression to perform variable selection and assess predictive ability of methylation variables on HV. Left HV was negatively associated with duration of current episode (ρ = -0.17, p = 0.035). We did not observe significant differences in HV between MDD and HC or any associations between HV and treatment response at weeks 8 or 16, overall depression severity, illness duration or childhood maltreatment. We also did not observe any differentially methylated CpG sites between MDD and HC groups. After assessing functionality by correlating methylation levels with RNA expression of the respective genes, we observed that the number of functionally relevant CpG sites differed between MDD and HC groups in FKBP5 (χ2 = 77.25, p < 0.0001) and NR3C1 (χ2 = 7.29, p = 0.007). Cross-referencing functionally relevant CpG sites to those that were highly ranked in predicting HV in elastic net modeling identified one site from FKBP5 (cg03591753) and one from NR3C1 (cg20728768) within the MDD group. Stronger associations between DNA methylation, gene expression and HV in MDD suggest a novel putative molecular pathway of stress-related sensitivity in depression. Future studies should consider utilizing the epigenome and ultra-high field MR data which would allow the investigation of HV sub-fields.

The use of cannabinoids for sleep: A critical review on clinical trials.

Cannabis and its pharmacologically active constituents, phytocannabinoids, have long been reported to have multiple medicinal benefits. One association often reported by users is sedation and subjective improvements in sleep. To further examine this association, we conducted a critical review of clinical studies examining the effects of cannabinoids on subjective and objective measures of sleep. PubMED, Web of Science, and Google Scholar were searched using terms and synonyms related to cannabinoids and sleep. Articles chosen included randomized controlled trials and open label studies. The Cochrane risk of bias tool was used to assess the quality of trials that compared cannabinoids with control interventions. The current literature focuses mostly on the use of tetrahydrocannabinol (THC) and/or cannabidiol (CBD) in the treatment of chronic health conditions such as multiple sclerosis, posttraumatic stress disorder (PTSD), and chronic pain. Sleep is often a secondary, rather than primary outcome in these studies. Many of the reviewed studies suggested that cannabinoids could improve sleep quality, decrease sleep disturbances, and decrease sleep onset latency. While many of the studies did show a positive effect on sleep, there are many limiting factors such as small sample sizes, examining sleep as a secondary outcome in the context of another illness, and relatively few studies using validated subjective or objective measurements. This review also identified several questions that should be addressed in future research. These questions include further elucidation of the dichotomy between the effects of THC and CBD, as well as identifying any long-term adverse effects of medicinal cannabinoid use. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Cannabidiol as a Novel Candidate Alcohol Use Disorder Pharmacotherapy: A Systematic Review.

There is substantial interest in the therapeutic potential of cannabidiol (CBD), a nonpsychoactive cannabinoid found in plants of the genus Cannabis. The goal of the current systematic review was to characterize the existing literature on this topic and to evaluate the credibility of CBD as a candidate pharmacotherapy for alcohol use disorder (AUD). Using a comprehensive search strategy, 303 unique potential articles were identified and 12 ultimately met criteria for inclusion (8 using rodent models, 3 using healthy adult volunteers, and 1 using cell culture). In both rodent and cell culture models, CBD was found to exert a neuroprotective effect against adverse alcohol consequences on the hippocampus. In rodent models, CBD was found to attenuate alcohol-induced hepatotoxicity, specifically, alcohol-induced steatosis. Finally, findings from preclinical rodent models also indicate that CBD attenuates cue-elicited and stress-elicited alcohol seeking, alcohol self-administration, withdrawal-induced convulsions, and impulsive discounting of delayed rewards. In human studies, CBD was well tolerated and did not interact with the subjective effects of alcohol. Collectively, given its favorable effects on alcohol-related harms and addiction phenotypes in preclinical models, CBD appears to have promise as a candidate AUD pharmacotherapy. This is further bolstered by the absence of abuse liability and its general tolerability. A clear limitation to the literature is the paucity of human investigations. Human preclinical and clinical studies are needed to determine whether these positive effects in model systems substantively translate into clinically relevant outcomes.

Non-pharmacological interventions for improving postpartum maternal sleep: A systematic review and meta-analysis.

Evidence suggests that poor postpartum sleep quality is a risk factor for the development of postpartum depression. As such, non-pharmacological interventions have been developed to help improve sleep in the postpartum period. The primary aims of this systematic review and meta-analysis were to determine if non-pharmacological interventions improved maternal sleep and to compare the effectiveness of different intervention types. Secondary aims included examining effects on maternal mood and infant sleep. We searched MEDLINE, EMBASE, CINAHL, PsycINFO, and Web of Science from their inceptions to September 2017 and found 15 eligible studies. Non-pharmacological sleep interventions were found to improve subjective reports of maternal sleep (Cohen's d = -0.54, 95%CI = -0.88 to -0.19). Massage (Cohen's d = -1.07 95%CI = -1.34 to -0.79) and exercise (Cohen's d = -0.82 95%CI = -1.28 to -0.37) interventions had the largest impact on maternal sleep quality. Positive effects on nocturnal infant sleep were found for interventions overall (Cohen's d = -0.27 95%CI = -0.52 to -0.02) but not for maternal depression (Cohen's d = -0.08 95%CI = -0.28 to 0.12). Despite evidence suggesting improvements in subjective maternal sleep, more research must be conducted on the durability of effects of non-pharmacological interventions using objective measures of sleep quality.

Vitex agnus castus for premenstrual syndrome and premenstrual dysphoric disorder: a systematic review.

The objective of this study was to evaluate whether Vitex agnus castus is a safe and effective treatment for PMS and premenstrual dysphoric disorder (PMDD) and to discuss the implications of these findings for clinical practice. A systematic review of literature was conducted using PubMed and Scielo databases. The inclusion criteria were randomized controlled trials (RCT) using V. agnus castus in individuals with PMS or PMDD that compared this intervention with placebo or an active comparator and included a description of blinding and dropouts/withdrawals. The search was conducted by two independent investigators who reached consensus on the included trials. A total of eight RCTs were included in this study. Most studies focused on PMS, and the diagnostic criteria of PMS and PMDD changed over the years. Three different preparations of V. agnus castus (VAC) were tested, and there was significant variability in the measurement of treatment outcomes between the studies. Nevertheless, all eight studies were positive for VAC in the treatment of PMS or PMDD and VAC was overall well tolerated. Main limitations were differences in definition of diagnostic criteria, the instruments used as main outcome measures, and different preparations of VAC extracts limit the comparison of results between studies. In conclusion, the RCTs using VAC for treatment of PMS/PMDD suggested that the VAC extract is a safe and efficacious alternative to be considered for the treatment of PMS/PMDD symptoms.

Increased cerebral oxidative damage and decreased antioxidant defenses in ovariectomized and sham-operated rats supplemented with vitamin A.

Previous studies have linked oxidative stress with aging and aging-related processes, including menopause. Abnormalities in the redox state similar to those observed in menopausal women can be modeled experimentally with rat ovariectomy. The aim of the present study was to investigate the effects of vitamin A (retinol palmitate) supplementation (500 or 1,500 IU kg(-1) day(-1) for 30 days) on behavioral parameters and brain redox profile in ovariectomized (OVX) and sham-operated rats. Ovariectomy caused pronounced uterine atrophy and decreased locomotor/exploratory activity. Moreover, we found increased hypothalamic and frontal cortex superoxide dismutase/catalase (SOD/CAT) ratio and decreased hippocampal thiol content, accompanied by increased frontal cortex lipid oxidative damage (TBARS) in OVX rats. Vitamin A at 1,500 IUkg(-1) day(-1) decreased exploratory behavior and decreased total hippocampal thiol content in sham-operated rats, increased hippocampal SOD/CAT ratio and decreased total antioxidant potential in the hippocampus of both sham and OVX groups, and increased cortical TBARS levels in OVX rats. Thus, vitamin A may induce a pro-oxidant state in discrete brain regions of sham-operated and OVX rats. These results suggest some caution regarding the use of high doses of vitamin A supplementation during menopause.

Preclinical and clinical evidence of antioxidant effects of antidepressant agents: implications for the pathophysiology of major depressive disorder.

Major depressive disorder (MDD) is a common mental disorder associated with a significant negative impact on quality of life, morbidity/mortality, and cognitive function. Individuals who suffer with MDD display lower serum/plasmatic total antioxidant potentials and reduced brain GSH levels. Also, F2-isoprostanes circulatory levels are increased in MDD subjects and are correlated with the severity of depressive symptoms. Urinary excretion of 8-OHdG seems to be higher in patients with MDD compared to healthy controls. Despite the fact that antidepressant drugs have been used for more than 50 years, their mechanism of action is still not fully understood. This paper examines preclinical (in vitro and animal model) and clinical literature on oxidative/antioxidant effects associated with antidepressant agents and discusses their potential antioxidant-related effects in the treatment of MDD. Substantial data support that MDD seems to be accompanied by elevated levels of oxidative stress and that antidepressant treatments may reduce oxidative stress. These studies suggest that augmentation of antioxidant defences may be one of the mechanisms underlying the neuroprotective effects of antidepressants in the treatment of MDD.

Non-hormonal treatment strategies for vasomotor symptoms: a critical review.

Hot flashes (or flushes) are the most commonly reported symptoms during the menopause transition and early postmenopausal years, particularly in Western societies; they affect 60-90% of women and can lead to significant physical discomfort and functional impairment. The emergence of hot flashes and night sweats (also known as vasomotor symptoms [VMS]) coincide with a period in life that is also marked by dynamic changes in hormone and reproductive function that interconnect with the aging process, changes in metabolism, lifestyle behaviours and overall health. Estrogen-based therapies have long been the treatment of choice for women suffering from VMS. More recent concerns over long-term safety of menopausal hormone treatments, however, have led physicians and patients to pursue non-hormonal strategies to alleviate their symptoms. In this article, we review most of the efficacy and safety data on non-hormonal treatments for VMS published over the past 20 years. We discuss the evidence for treating symptomatic women in different clinical scenarios, e.g. VMS with and without concomitant depression or VMS following the use of anti-estrogen therapies. Overall, efficacy data support the use of some psychotropic medications, including selective serotonin reuptake inhibitors, serotonin-norepinephrine reuptake inhibitors and gabapentin. Complementary and alternative methods for VMS also showed limited but promising results, although more definitive studies are warranted. Clinicians should therefore be able to tailor treatment strategies for those who are unable or unwilling to use hormones to alleviate VMS and improve overall functioning and quality of life.