•We surveyed the use of machine learning to inform predictive models in mood disorders.•We include studies that use machine learning algorithms to identify predictors of therapeutic outcomes in ...uni/bipolar depression.•Classification algorithms informed by neuroimaging, phenomenological, and genetic data were able to predict therapeutic outcomes with an overall accuracy of 0.82.•Predictive models integrating multiple data types performed better when compared to models with single lower-dimension data types (p <0.01).•Machine learning provides opportunity to parse clinical heterogeneity and characterize moderators of disease risk and trajectory.
No previous study has comprehensively reviewed the application of machine learning algorithms in mood disorders populations. Herein, we qualitatively and quantitatively evaluate previous studies of machine learning-devised models that predict therapeutic outcomes in mood disorders populations.
We searched Ovid MEDLINE/PubMed from inception to February 8, 2018 for relevant studies that included adults with bipolar or unipolar depression; assessed therapeutic outcomes with a pharmacological, neuromodulatory, or manual-based psychotherapeutic intervention for depression; applied a machine learning algorithm; and reported predictors of therapeutic response. A random-effects meta-analysis of proportions and meta-regression analyses were conducted.
We identified 639 records: 75 full-text publications were assessed for eligibility; 26 studies (n=17,499) and 20 studies (n=6325) were included in qualitative and quantitative review, respectively. Classification algorithms were able to predict therapeutic outcomes with an overall accuracy of 0.82 (95% confidence interval CI of 0.77, 0.87). Pooled estimates of classification accuracy were significantly greater (p < 0.01) in models informed by multiple data types (e.g., composite of phenomenological patient features and neuroimaging or peripheral gene expression data; pooled proportion 95% CI = 0.930.86, 0.97) when compared to models with lower-dimension data types (pooledproportion=0.680.62,0.74to0.850.81,0.88).
Most studies were retrospective; differences in machine learning algorithms and their implementation (e.g., cross-validation, hyperparameter tuning); cannot infer importance of individual variables fed into learning algorithm.
Machine learning algorithms provide a powerful conceptual and analytic framework capable of integrating multiple data types and sources. An integrative approach may more effectively model neurobiological components as functional modules of pathophysiology embedded within the complex, social dynamics that influence the phenomenology of mental disorders.
Excessive smartphone use has been associated with numerous psychiatric disorders. This study aimed to investigate the prevalence of smartphone addiction and its association with depression, anxiety, ...and attention-deficit hyperactivity disorder (ADHD) symptoms in a large sample of Korean adolescents.
A total of 4512 (2034 males and 2478 females) middle- and high-school students in South Korea were included in this study. Subjects were asked to complete a self-reported questionnaire, including measures of the Korean Smartphone Addiction Scale (SAS), Beck Depression Inventory (BDI), Beck Anxiety Inventory (BAI), and Conners-Wells' Adolescent Self-Report Scale (CASS). Smartphone addiction and non-addiction groups were defined using SAS score of 42 as a cut-off. The data were analyzed using multivariate logistic regression analyses.
338 subjects (7.5%) were categorized to the addiction group. Total SAS score was positively correlated with total CASS score, BDI score, BAI score, female sex, smoking, and alcohol use. Using multivariate logistic regression analyses, the odds ratio of ADHD group compared to the non-ADHD group for smartphone addiction was 6.43, the highest among all variables (95% CI 4.60-9.00).
Our findings indicate that ADHD may be a significant risk factor for developing smartphone addiction. The neurobiological substrates subserving smartphone addiction may provide insights on to both shared and discrete mechanisms with other brain-based disorders.
Cognitive dysfunction is a symptomatic domain identified across many mental disorders. Cognitive deficits in individuals with major depressive disorder (MDD) contribute significantly to occupational ...and functional disability. Notably, cognitive subdomains such as learning and memory, executive functioning, processing speed, and attention and concentration are significantly impaired during, and between, episodes in individuals with MDD. Most antidepressants have not been developed and/or evaluated for their ability to directly and independently ameliorate cognitive deficits. Multiple interacting neurobiological mechanisms (eg, neuroinflammation) are implicated as subserving cognitive deficits in MDD. A testable hypothesis, with preliminary support, posits that improving performance across cognitive domains in individuals with MDD may improve psychosocial function, workplace function, quality of life, and other patient-reported outcomes, independent of effects on core mood symptoms. Herein we aim to (1) provide a rationale for prioritizing cognitive deficits as a therapeutic target, (2) briefly discuss the neurobiological substrates subserving cognitive dysfunction, and (3) provide an update on current and future treatment avenues.
Cognitive dysfunction is a principal determinant of functional impairment in major depressive disorder (MDD) and often persists during periods of euthymia. Abnormalities in the glutamate system, ...particularly in N-methyl-d-aspartate receptors (NMDARs) activity, have been shown to contribute to both mood and cognitive symptoms in MDD. The current narrative review aims to evaluate the potential pro-cognitive effects of targeting the glycine site of NMDARs in the treatment of psychiatric disorders, with a special focus on how these results may apply to MDD. Literature databases were searched from inception to May 2018 for relevant pre-clinical and clinical studies evaluating antidepressant and pro-cognitive effects of NMDAR glycine site modulators in both MDD and non-MDD samples. Six glycine site modulators with pro-cognitive and antidepressant properties were identified: d-serine (co-agonist), d-cycloserine (partial agonist), d-alanine (co-agonist), glycine (agonist), sarcosine (co-agonist) and rapastinel (partial agonist). Preclinical animal studies demonstrated improved neuroplasticity and pro-cognitive effects with these agents. Numerous proof-of-concept clinical trials demonstrated pro-cognitive and antidepressant effects trans-diagnostically (e.g., in healthy participants, MDD, schizophrenia, anxiety disorders, major neurocognitive disorders). The generalizability of these clinical studies was limited by the small sample sizes and the paucity of studies directly evaluating cognitive effects in MDD samples, as most clinical trials were in non-MDD samples. Taken together, preliminary results suggest that the glycine site of NMDARs is a promising target to ameliorate symptoms of depression and cognitive dysfunction. Additional rigorously designed clinical studies are required to determine the cognitive effects of these agents in MDD.
•The NMDAR has been previously implicated in cognitive dysfunction in MDD•Pro-cognitive effects of targeting the glycine site of NMDARs was evaluated•Preclinical studies demonstrated improved neuroplasticity and pro-cognitive effects•Preliminary clinical trials demonstrated pro-cognitive and antidepressant effects•Preliminary results suggest that the glycine site of NMDARs is a promising target
•Numerous studies indicate that probiotics have anti-inflammatory effects.•Immune-inflammatory modulation may mediate the antidepressant effects of probiotics.•Probiotics may be more effective in ...depressed subgroups with elevated inflammation.•Future studies should parse out the heterogeneous effects of different probiotics.
During the past decade, there has been renewed interest in the relationship between brain-based disorders, the gut microbiota, and the possible beneficial effects of probiotics. Emerging evidence suggests that modifying the composition of the gut microbiota via probiotic supplementation may be a viable adjuvant treatment option for individuals with major depressive disorder (MDD). Convergent evidence indicates that persistent low-grade inflammatory activation is associated with the diagnosis of MDD as well as the severity of depressive symptoms and probability of treatment response. The objectives of this review are to (1) evaluate the evidence supporting an anti-inflammatory effect of probiotics and (2) describe immune system modulation as a potential mechanism for the therapeutic effects of probiotics in populations with MDD. A narrative review of studies investigating the effects of probiotics on systemic inflammation was conducted. Studies were identified using PubMed/Medline, Google Scholar, and clinicaltrials.gov (from inception to November 2017) using the following search terms (and/or variants): probiotic, inflammation, gut microbiota, and depression. The available evidence suggests that probiotics should be considered a promising adjuvant treatment to reduce the inflammatory activation commonly found in MDD. Several controversial points remain to be addressed including the role of leaky gut, the role of stress exposure, and the role of blood-brain-barrier permeability. Taken together, the results of this review suggest that probiotics may be a potentially beneficial, but insufficiently studied, antidepressant treatment intervention.
This study (registered with PROSPERO, CRD42018085967) compares the efficacy (i.e. pro‐cognitive effects) and acceptability of antidiabetic agents for Alzheimer's disease (AD) and mild cognitive ...impairment (MCI). Cochrane Library (CENTRAL), PubMed/MEDLINE, EMBASE and PsycINFO were searched from inception to January 15, 2018 for randomized controlled trials comparing antidiabetic agents with placebo and/or another active antidiabetic agent for the treatment of AD or MCI. Nineteen eligible studies (n = 4855) evaluating the effects of 6 different antidiabetic drugs (i.e. intranasal insulin, pioglitazone, rosiglitazone, metformin, sitagliptin and liraglutide) were included. The results of 29 pairwise comparisons indicated that cognition was significantly improved in subjects treated with antidiabetic agents compared with placebo. Pioglitazone 15 to 30 mg demonstrated the greatest efficacy compared to placebo in network meta‐analysis. No significant differences in acceptability were identified when comparing agents with each other and with placebo. The current findings indicate a pro‐cognitive class effect of antidiabetic agents in AD/MCI. Other antidiabetic agents should also be investigated in future studies.
Titanium nitride (TiN) inclusions are easy to precipitate in the high temperature processing of titanium alloying steels, which tends to introduce numerous surface defects on the final continuous ...casting slabs. This study utilizes B2O3 to regulate the interfacial properties between the designed mold fluxes and TiN, with the aim to resolve above problems. The results show that the spreading behavior of the mold flux on the TiN substrate is enhanced, and the interfacial contact angle starts to drop at a lower temperature (from 1473 K for Sample 1 to 1343 K for Sample 4) with the addition of 0–9 wt.% B2O3, as the melting behavior of the designed mold fluxes has been improved. The interfacial reactions between the TiN substrate and molten fluxes are also promoted with the addition of B2O3, where more bubbles are observed in the tested mold fluxes samples. For Sample 1 without B2O3, quite a few TiN particles couldn’t be dissolved and remains in the matrix phase, where the major formed phase is perovskite (CaTiO3) that would deteriorate the high temperature properties of mold flux severely. However, most TiN particles have been dissolved in the optimized mold fluxes, as major of them have reacted with mold fluxes, resulted in the more generation of titanium oxides phase in the samples. In addition, the calculated phase diagram of CaO–SiO2–TiO2 slag system under different B2O3 contents indicates that the formation and precipitation of CaTiO3 can be effectively inhibited by the addition of B2O3.
Major Depressive Disorder (MDD) is a prevalent, chronic, disabling, and multidimensional mental disorder. Cognitive dysfunction represents a core diagnostic and symptomatic criterion of MDD, and is a ...principal determinant of functional non-recovery. Cognitive impairment has been observed to persist despite remission of mood symptoms, suggesting dissociability of mood and cognitive symptoms in MDD. Recurrent impairments in several domains including, but not limited to, executive function, learning and memory, processing speed, and attention and concentration, are associated with poor psychosocial and occupational outcomes. Attempts to restore premorbid functioning in individuals with MDD requires regular screenings and assessment of objective and subjective measures of cognition by clinicians. Easily accessible and cost-effective tools such as the THINC-integrated tool (THINC-it) are suitable for use in a busy clinical environment and appear to be promising for routine usage in clinical settings. However, antidepressant treatments targeting specific cognitive domains in MDD have been insufficiently studied. While select antidepressants, e.g., vortioxetine, have been demonstrated to have direct and independent pro-cognitive effects in adults with MDD, research on additional agents remains nascent. A comprehensive clinical approach to cognitive impairments in MDD is required. The current narrative review aims to delineate the importance and relevance of cognitive dysfunction as a symptomatic target for prevention and treatment in the phenomenology of MDD.
Interfacial properties play a key role in determining the solubility of solids in liquids for both low- and high-temperature processes. In this study, the interfacial interactions between inclusions ...comprising TiO
2
or TiN and the mold flux were investigated. The results of sessile drop tests show that the wettability of the mold flux on the TiO
2
substrate was better than that on the TiN substrate when the temperature was below 1503 K. However, the contact angle on the TiN substrate decreased more than that on the TiO
2
substrate when the temperature was above 1503 K due to the enhancement of the interfacial reaction. The thermodynamic calculations suggest that the reactions of TiN with O
2
and SiO
2
resulted in a bubbling phenomenon during the TiN sessile drop test. The scanning electron microscopy (SEM) and energy dispersive spectroscopy (EDS) results show that the final products of the interfacial interaction between the mold flux and the TiO
2
substrate comprised perovskites, whereas those for the TiN substrate comprised perovskites and SiTi.
Background
Although rare, severe systemic lupus erythematosus (SLE) flares requiring hospitalization account for most of the direct costs of SLE care. New machine learning (ML) methods may optimize ...lupus care by predicting which patients will have a prolonged hospital length of stay (LOS). Our study uses a machine learning approach to predict the LOS in patients admitted for lupus flares and assesses which features prolong LOS.
Methods
Our study sampled 5831 patients admitted for lupus flares from the National Inpatient Sample Database 2016–2018 and collected 90 demographics and comorbidity features. Four machine learning (ML) models were built (XGBoost, Linear Support Vector Machines, K Nearest Neighbors, and Logistic Regression) to predict LOS, and their performance was evaluated using multiple metrics, including accuracy, receiver operator area under the curve (ROC-AUC), precision-recall area under the curve (PR- AUC), and F1-score. Using the highest-performing model (XGBoost), we assessed the feature importance of our input features using Shapley value explanations (SHAP) to rank their impact on LOS.
Results
Our XGB model performed the best with a ROC-AUC of 0.87, PR-AUC of 0.61, an F1 score of 0.56, and an accuracy of 95%. The features with the most significant impact on the model were “the need for a central line,” “acute dialysis,” and “acute renal failure.” Other top features include those related to renal and infectious comorbidities.
Conclusion
Our results were consistent with the established literature and showed promise in ML over traditional methods of predictive analyses, even with rare rheumatic events such as lupus flare hospitalizations.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, OILJ, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK