Deep learning in mental health outcome research: a scoping review.
Ontology highlight
ABSTRACT:
SUBMITTER: Su C
PROVIDER: S-EPMC7293215 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Publications
Deep learning in mental health outcome research: a scoping review.
Su Chang C Xu Zhenxing Z Pathak Jyotishman J Wang Fei F
Translational psychiatry 20200422 1
Mental illnesses, such as depression, are highly prevalent and have been shown to impact an individual's physical health. Recently, artificial intelligence (AI) methods have been introduced to assist mental health providers, including psychiatrists and psychologists, for decision-making based on patients' historical data (e.g., medical records, behavioral data, social media usage, etc.). Deep learning (DL), as one of the most recent generation of AI technologies, has demonstrated superior perfor ...[more]
Similar Datasets
Project description:BackgroundA high risk of mental health or substance addiction issues among sexual and gender minority populations may have more nuanced characteristics that may not be easily discovered by traditional statistical methods.ObjectiveThis review aims to identify literature studies that used machine learning (ML) to investigate mental health or substance use concerns among the lesbian, gay, bisexual, transgender, queer or questioning, and two-spirit (LGBTQ2S+) population and direct future research in this field.MethodsThe MEDLINE, Embase, PubMed, CINAHL Plus, PsycINFO, IEEE Xplore, and Summon databases were searched from November to December 2020. We included original studies that used ML to explore mental health or substance use among the LGBTQ2S+ population and excluded studies of genomics and pharmacokinetics. Two independent reviewers reviewed all papers and extracted data on general study findings, model development, and discussion of the study findings.ResultsWe included 11 studies in this review, of which 81% (9/11) were on mental health and 18% (2/11) were on substance use concerns. All studies were published within the last 2 years, and most were conducted in the United States. Among mutually nonexclusive population categories, sexual minority men were the most commonly studied subgroup (5/11, 45%), whereas sexual minority women were studied the least (2/11, 18%). Studies were categorized into 3 major domains: web content analysis (6/11, 54%), prediction modeling (4/11, 36%), and imaging studies (1/11, 9%).ConclusionsML is a promising tool for capturing and analyzing hidden data on mental health and substance use concerns among the LGBTQ2S+ population. In addition to conducting more research on sexual minority women, different mental health and substance use problems, as well as outcomes and future research should explore newer environments, data sources, and intersections with various social determinants of health.
| S-EPMC8663464 | biostudies-literature
Project description:Mental and substance use disorders are a leading cause of disability worldwide. Despite this, there is a paucity of mental health research in low- and middle-income countries, especially in sub-Saharan Africa. We carried out a semi-systematic scoping review to determine the extent of mental health research in Botswana. Using a predetermined search strategy, we searched the databases Web of Science, PubMed, and EBSCOhost (Academic Search Complete, CINAHL with Full Text, MEDLINE, MEDLINE with Full Text, MLA International Bibliography, Open Dissertations) for articles written in English from inception to June 2020. We identified 58 studies for inclusion. The most researched subject was mental health aspects of HIV/AIDS, followed by research on neurotic and stress-related disorders. Most studies were cross-sectional and the earliest published study was from 1983. The majority of the studies were carried out by researchers affiliated to the University of Botswana, followed by academic institutions in the USA. There seems to be limited mental health research in Botswana, and there is a need to increase research capacity.
| S-EPMC7607297 | biostudies-literature
Project description:BACKGROUND:Mental health issues among farmers are identified population health concerns. While one systematic review focused on suicide in farming populations in the United States, there have been no scoping studies examining mental health in farming communities worldwide. The objectives of this scoping review were to: provide a descriptive analysis of the literature pertaining to mental health outcomes in farming populations; describe the international scope of the research; and highlight published mental health services and interventions that have been evaluated. METHODS:Following Arksey and O'Malley's scoping review framework, five major health and science platforms were used to identify studies examining mental health outcomes in farming populations, worldwide. Studies that met a priori inclusion criteria that were published prior to December 31, 2017 were included in this review. Data synthesis and descriptive statistics were conducted using STATA 15® software; proportions were calculated by country. RESULTS:The initial literature search yielded 9,906 records. After title and abstract screening, 676 articles were reviewed in-full. Of these, 341 met a priori inclusion criteria. Studies included were conducted between 1979 and 2017; the majority (265; 77.7%) were published between 2002-2017. The most frequently measured outcomes were stress (41.9%), suicide (33.1%), and depression (32.6%). Over 70% of studies that examined stress described using quantitative research methods, most predominantly, cross-sectional designs (42.7%). Approximately 64% of studies that measured suicide reported using a quantitative approach; the largest proportion of included suicide studies (33.6%) described using cohort designs. Approximately 84% of studies that measured depression described using quantitative approaches; sixty percent of these studies reported using a cross-sectional study design. Twenty included studies described a mental health service or intervention (5.9%). CONCLUSIONS:This scoping review provides a critical overview of the literature examining mental health outcomes in farming populations worldwide. Given the importance of farming and agriculture, this review can be used to ensure future research complements existing work, avoids unnecessary overlap, and begins to tackle the less-studied mental health outcomes amongst farmers. These results can guide researchers to identified gaps in research and services, leading to a more informed approach to future work, and ultimately, a more comprehensive understanding of mental health among farmers worldwide.
| S-EPMC6894791 | biostudies-literature
Project description:Introduction:Various methods have been used to interpret the reports of pediatric polypharmacy across the literature. This is the first scoping review that explores outcome measures in pediatric polypharmacy research. Objectives:The aim of our study was to describe outcome measures assessed in pediatric polypharmacy research. Methods:A search of electronic databases was conducted in July 2017, including Ovid Medline, PubMed, Elsevier Embase, Wiley Cochrane Central Register of Controlled Trials (CENTRAL), EBSCO CINAHL, Ovid PsyclNFO, Web of Science Core Collection, ProQuest Dissertations and Thesis A&I. Data were extracted about study characteristics and outcome measures, and also synthesized by harms or benefits mentioned. Results:The search strategy initially identified 8169 titles and screened 4398 using the inclusion criteria after de-duplicating. After the primary screening, a total of 363 studies were extracted for the data analysis. Polypharmacy (prevalence) was identified as an outcome in 31.4% of the studies, prognosis-related outcomes in 25.6%, and adverse drug reactions in 16.5%. A total of 265 articles (73.0%) mentioned harms, including adverse drug reactions (26.4%), side effects (24.2%), and drug-drug interactions (20.9%). A total of 83 studies (22.9%) mentioned any benefit, 48.2% of which identified combination for efficacy, 24.1% combination for treatment of complex diseases, and 19.3% combination for treatment augmentation. Thirty-eight studies reported adverse drug reaction as an outcome, where polypharmacy was a predictor, with various designs. Conclusions:Most studies of pediatric polypharmacy evaluate prevalence, prognosis, or adverse drug reaction-related out-comes, and underscore harms related to polypharmacy. Clinicians should carefully weigh benefits and harms when introducing medications to treatment regimens.
| S-EPMC7123381 | biostudies-literature
Project description:Introduction:Globally, 10-20% of children and adolescents suffer from mental disorders, with half of all them starting by the age of 14 and three-quarters before the age of 25. In Nepal, 40% of the population is younger than 18 years of age, and as such there is a large proportion of the population that is at risk of developing a mental disorder. There has been a recent recognition of child and adolescent mental health problems in Nepal, although prior to this it had remained almost invisible on the health agenda. In response to growing concern, there is a need to conduct a review on children and adolescent mental health problems in Nepal. Objective:To review the existing studies on child and adolescent mental health problems in Nepal. Methodology:A scoping review approach was used to identify studies on child and adolescent mental problems in Nepal. A search of Medline and PubMed databases for articles published from the database inception to August 2018 was conducted. Results:Ten papers were identified, and they all together included 7876 participants. Two studies reported on Post traumatic Stress Symptoms (PTSS) and described a prevalence of 10.7% to 51% of earthquake-affected children and adolescents in the Kathmandu district of Nepal. Another study reported that 53.2% of former child soldiers met the cut-off score for PTSS. Two school surveys found that the prevalence of emotional and behavioural problems in school children ranged between 12.9 and 17.03%, whereas a study on emotional and behavioural disorders in homeless children reported a prevalence of 28.6%. The prevalence of Autism Spectrum Disorder (ASD) was estimated to be as high as three in every 1000 persons in Nepal by one study. The clinical prevalence of anxiety disorders was reported ranging from 18.8% to 24.4% while that of Attention Deficit Hyperactivity Disorder (ADHD) was 10-11.7% in various clinical samples of children and adolescents. Conclusion:Only a few studies on the prevalence of child and adolescent mental health in Nepal have been conducted. Clearly, there is a need for better study design and larger studies to understand more fully the prevalence of child and adolescent mental health disorders in Nepal, in order to adequately plan public health services accordingly.
| S-EPMC6689861 | biostudies-other
Project description:Background:A scoping review was conducted in order to map and determine the gaps in literature on the impact of simulation as an educational approach to improve mental health care outcomes. As it became apparent that no literature existed on this topic, the study aimed to examine the educational impact of simulation on mental health education. Methods:An established five-stage scoping methodology was used: (1) identification of the research question, (2) identification of relevant studies, (3) study selection, (4) charting the data and (5) collation, summarising and reporting of results. CINAHL, ProQuest, PubMed, MEDLINE, EMBASE and PsychINFO databases were searched. These databases were deemed to represent a majority of the literature while accommodating for the particular search strategy used for this review. Websites that provide grey literature were also searched for articles of relevance. Results:A total of 48 articles were included in this review, with a considerable portion of studies conducted in the USA and UK. Others were conducted in an array of locations including Australia, Canada, Iran and Taiwan. Of the included articles, seven groups of simulation methods (including standardised patients, virtual reality and manikins as patients) were evident, with standardised patients being most prominent. Conclusions:Literature is lacking to evidence the benefit of simulation on mental health patient outcomes. However, the available literature suggests a variety of simulation-based education, and training methods are currently being used within mental healthcare education. The findings do suggest some methods of simulation, such as the use of standardised patients, are more commonly used in education and have been deemed as effective to assist in mental health education. As no article specifically examining the mental health outcomes of patients treated by health professionals taught by simulation was identified, the educational outcomes outlined in this paper may be used to inform further research, incorporating mental health patient outcomes.
| S-EPMC5806484 | biostudies-literature
Project description:Background: To monitor population mental health, the identification of relevant indicators is pivotal. This scoping review provides a comprehensive overview of current indicators representing the various fields of public mental health core topics. It was conducted as a first step to build up a Mental Health Surveillance for Germany. Methods: We conducted a systematic MEDLINE search via PubMed. This search was supplemented by an extensive examination of the websites of relevant national as well as international institutions in the context of public mental health and an additional internet search via Google. To structure the data, an expert-based focus group identified superordinate topics most relevant to public mental health to which the identified indicators could be assigned to. Finally, the indicator set was screened for duplicates and appropriate content to arrive at a final set. Results: Within the various search strategies, we identified 13.811 records. Of these records, a total of 365 records were processed for indicator extraction. The extracted indicators were then assigned to 14 topics most relevant to public mental health as identified by the expert-based focus group. After the exclusion of duplicates and those indicators not meeting criteria of specificity and target group, the final set consisted of 192 indicators. Conclusion: The presented indicator set provides guidance in the field of current concepts in public mental health monitoring. As a comprehensive compilation, it may serve as basis for future surveillance efforts, which can be adjusted and condensed depending on the particular monitoring focus. Our work provides insights into established indicators included in former surveillance work as well as recent, not yet included indicators reflecting current developments in the field. Since our compilation mainly concludes indicators related to mental health in adults, it should be complemented with indicators specific to children and adolescents. Furthermore, our review revealed that indicators on mental health promotion and prevention are underrepresented in current literature of public mental health and should hence be focused on within future research and surveillance.
| S-EPMC8502920 | biostudies-literature
Project description:INTRODUCTION:The rising popularity of social media, since their inception around 20 years ago, has been echoed in the growth of health-related research using data derived from them. This has created a demand for literature reviews to synthesise this emerging evidence base and inform future activities. Existing reviews tend to be narrow in scope, with limited consideration of the different types of data, analytical methods and ethical issues involved. There has also been a tendency for research to be siloed within different academic communities (eg, computer science, public health), hindering knowledge translation. To address these limitations, we will undertake a comprehensive scoping review, to systematically capture the broad corpus of published, health-related research based on social media data. Here, we present the review protocol and the pilot analyses used to inform it. METHODS:A version of Arksey and O'Malley's five-stage scoping review framework will be followed: (1) identifying the research question; (2) identifying the relevant literature; (3) selecting the studies; (4) charting the data and (5) collating, summarising and reporting the results. To inform the search strategy, we developed an inclusive list of keyword combinations related to social media, health and relevant methodologies. The frequency and variability of terms were charted over time and cross referenced with significant events, such as the advent of Twitter. Five leading health, informatics, business and cross-disciplinary databases will be searched: PubMed, Scopus, Association of Computer Machinery, Institute of Electrical and Electronics Engineers and Applied Social Sciences Index and Abstracts, alongside the Google search engine. There will be no restriction by date. ETHICS AND DISSEMINATION:The review focuses on published research in the public domain therefore no ethics approval is required. The completed review will be submitted for publication to a peer-reviewed, interdisciplinary open access journal, and conferences on public health and digital research.
| S-EPMC6303712 | biostudies-other
Project description:IntroductionA 2011 paper proposed a working taxonomy of implementation outcomes, their conceptual distinctions and a two-pronged research agenda on their role in implementation success. Since then, over 1100 papers citing the manuscript have been published. Our goal is to compare the field's progress to the originally proposed research agenda, and outline recommendations for the next 10 years. To accomplish this, we are conducting the proposed scoping review.Methods and analysisOur approach is informed by Arksey and O'Malley's methodological framework for conducting scoping reviews. We will adhere to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews. We first aim to assess the degree to which each implementation outcome has been investigated in the literature, including healthcare settings, clinical populations and innovations represented. We next aim to describe the relationship between implementation strategies and outcomes. Our last aim is to identify studies that empirically assess relationships among implementation and/or service and client outcomes. We will use a forward citation tracing approach to identify all literature that cited the 2011 paper in the Web of Science (WOS) and will supplement this with citation alerts sent to the second author for a 6-month period coinciding with the WOS citation search. Our review will focus on empirical studies that are designed to assess at least one of the identified implementation outcomes in the 2011 taxonomy and are published in peer-reviewed journals. We will generate descriptive statistics from extracted data and organise results by these research aims.Ethics and disseminationNo human research participants will be involved in this review. We plan to share findings through a variety of means including peer-reviewed journal publications, national conference presentations, invited workshops and webinars, email listservs affiliated with our institutions and professional associations, and academic social media.
| S-EPMC8215242 | biostudies-literature
Project description:BackgroundSuicide and risk management protocols in mental health research aim to ensure patient safety, provide vital information on how to assess suicidal ideation, manage risk, and respond to unexpected and expected situations. However, there is a lack of literature that identifies specific components and strategies to include in suicide and risk management protocols (SRMPs) for mental health research. The goal of this scoping review was to review academic and grey literature to determine core components and associated strategies, which can be used to inform SRMPs in mental health research.Methods and analysisThe methodological framework outlined by Arksey and O'Malley was used for this scoping review. The search strategy, conducted by a medical librarian, was multidisciplinary and included seven databases. Two reviewers independently assessed eligibility criteria in each document and used a standardized charting form to extract relevant data. The extracted data were then examined using qualitative content analysis. Specifically, summative content analysis was used to identify the core components and strategies used in SRMPs. The data synthesis process was iterative.ResultsThis review included 36 documents, specifically 22 peer-reviewed articles and 14 documents from the grey literature. Five core components of SRMPs emerged from the reviewed literature including: training; educational resources for research staff; educational resources for research participants; risk assessment and management strategies; and clinical and research oversight. Potentials strategies for risk mitigation within each of the core components are outlined.ConclusionsThe five core components and associated strategies for inclusion in SRMPs will assist mental health researchers in conducting research safely and rigorously. Findings can inform the development of SRMPs and how to tailor them across various research contexts.
| S-EPMC7792084 | biostudies-literature