The performance of artificial intelligence-driven technologies in diagnosing mental disorders: An umbrella review (Preprint)

2021 ◽  
Author(s):  
Alaa Abd-Alrazaq ◽  
Jens Schneider ◽  
Dari Alhuwail ◽  
Carla T Toro ◽  
Arfan Ahmed ◽  
...  

BACKGROUND Diagnosing mental disorders is usually not an easy task and requires a large amount of time and effort given the complex nature of mental disorders. Artificial intelligence (AI) has been successfully exploited in diagnosing many mental disorders. Numerous systematic reviews summarize the evidence on the accuracy of AI models in diagnosing different mental disorders. OBJECTIVE This umbrella review aims to synthesize results of previous systematic reviews on the performance of AI models in diagnosing mental disorders. METHODS To identify relevant systematic reviews, we searched 11 electronic databases, checked the reference list of the included reviews, and checked the reviews that cited the included reviews. Two reviewers independently selected the relevant reviews, extracted the data from them, and appraised their quality. We synthesized the extracted data using the narrative approach. Specifically, results of the included reviews were grouped based on the target mental disorders that the AI classifiers distinguish. RESULTS We included 15 systematic reviews of 852 citations identified by searching all databases. The included reviews assessed the performance of AI models in diagnosing Alzheimer’s disease (n=7), mild cognitive impairment (n=6), schizophrenia (n=3), bipolar disease (n=2), autism spectrum disorder (n=1), obsessive-compulsive disorder (n=1), post-traumatic stress disorder (n=1), and psychotic disorders (n=1). The performance of the AI models in diagnosing these mental disorders ranged between 21% and 100%. CONCLUSIONS AI technologies offer great promise in diagnosing mental health disorders. The reported performance metrics paint a vivid picture of a bright future for AI in this field. To expedite progress towards these technologies being incorporated into routine practice, we recommend that healthcare professionals in the field cautiously and consciously begin to explore the opportunities of AI-based tools for their daily routine. It would also be encouraging to see a greater number of meta-analyses and further systematic reviews on performance of AI models in diagnosing other common mental disorders such as depression and anxiety. CLINICALTRIAL CRD42021231558

2020 ◽  
Author(s):  
Md Mahbub Hossain ◽  
Neetu Purohit ◽  
Abida Sultana ◽  
Ping Ma ◽  
E. Lisako J. McKyer ◽  
...  

Objectives: Mental disorders are highly prevalent in eight South Asian countries, yet there is a gap of a synthesized overview of the prevalence of mental disorders in this region. This umbrella review aims to summarize the prevalence of mental disorders from systematic reviews and meta-analyses of South Asian studies.Materials and methods: A systematic search of 11 major databases and additional sources was conducted until December 11, 2019. Articles were included if they were systematic reviews or meta-analyses, reported the prevalence of mental disorders, and reported primary studies conducted in South Asian countries only. Results: Among 2591 citations, a total of 23 reviews met all the criteria of this umbrella review. The synthesized findings from those reviews suggest high prevalence rates for mental disorders, including depressive disorders, anxiety disorders, mood disorders, suicidal behavior and self-harm, schizophrenia, substance use disorders, neurodevelopmental disorders, dementia, and other mental health problems. Also, findings suggest a high burden of maternal depression, psychiatric comorbidities in chronic physical illnesses, and various mental disorders among children, elderly adults, refugees, and other vulnerable populations. Most studies were from India whereas evidence from Afghanistan, Bhutan, and Maldives was limited.Conclusion: The findings of this review are constrained with heterogeneity in prevalence estimations, methodologies, sampling issues, and limitations in the existing literature, which should be addressed in future research. The evidence synthesized in this review provides national and regional overview of the prevalence of mental disorders, which may inform better policymaking and practice advancing mental health in South Asia.


BMJ Open ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. e033634
Author(s):  
Luigi Marano ◽  
Daniele Fusario ◽  
Vinno Savelli ◽  
Luigi Verre ◽  
Alessandro Neri ◽  
...  

IntroductionLaparoscopic surgery has been adopted in some parts of the world as an innovative approach to the resection of gastric cancers. However, in the modern era of surgical oncology, to overcome intrinsic limitations of the traditional laparoscopy, the robotic approach is advocated as able to facilitate the lymph node dissection and complex reconstruction after gastrectomy, to assure oncologic safety also in advanced gastric cancer patients. Previous meta-analyses highlighted a lower complication rate as well as bleeding in the robotic approach group when compared with the laparoscopic one. This potential benefit must be balanced against an increased time of intervention. The aim of this umbrella review is to provide a comprehensive overview of the literature for surgeons and policymakers in order to evaluate the potential benefits and harms of robotic gastrectomy (RG) compared with the laparoscopic approach for gastric cancer.Methods and analysisWe will perform a comprehensive search of the PubMed, Cochrane and Embase databases for all articles published up to May 2019 and reference list of relevant publications for systematic review and meta-analyses comparing the outcomes of RG and laparoscopic gastrectomy in patients with gastric cancer. Studies will be selected by two independent reviewers based on prespecified eligibility criteria and the quality will be assessed according to AMSTAR (A MeaSurement Tool to Assess systematic Reviews) checklist. All information will be collected using piloted and standardised data-extraction forms in DistillerSR developed following the Joanna Briggs Institute’s recommended extraction items.Ethics and disseminationThis umbrella review will inform clinical and policy decisions regarding the benefits and harms of RG for treating gastric cancer. The results will be disseminated through a peer-reviewed publication, conference presentations and the popular press. Formal ethical approval is not required as primary data will not be collected.PROSPERO registration numberCRD42019139906.


2021 ◽  
Vol 8 ◽  
Author(s):  
Ryan P. Lau ◽  
Teresa H. Kim ◽  
Jianyu Rao

Several advances in recent decades in digital imaging, artificial intelligence, and multiplex modalities have improved our ability to automatically analyze and interpret imaging data. Imaging technologies such as optical coherence tomography, optical projection tomography, and quantitative phase microscopy allow analysis of tissues and cells in 3-dimensions and with subcellular granularity. Improvements in computer vision and machine learning have made algorithms more successful in automatically identifying important features to diagnose disease. Many new automated multiplex modalities such as antibody barcoding with cleavable DNA (ABCD), single cell analysis for tumor phenotyping (SCANT), fast analytical screening technique fine needle aspiration (FAST-FNA), and portable fluorescence-based image cytometry analyzer (CytoPAN) are under investigation. These have shown great promise in their ability to automatically analyze several biomarkers concurrently with high sensitivity, even in paucicellular samples, lending themselves well as tools in FNA. Not yet widely adopted for clinical use, many have successfully been applied to human samples. Once clinically validated, some of these technologies are poised to change the routine practice of cytopathology.


2012 ◽  
Vol 22 (2) ◽  
pp. 155-162 ◽  
Author(s):  
S. Green-Hennessy

Aims.To assess the breadth of mental and substance coverage in the Cochrane review system.Methods.All mental health and substance entries were identified from the 2005 to April 2012 Cochrane Database of Systematic Reviews.Results.A total of 1019 entries focused on mental health or substance misuse, with 698 (68.5%) being completed reviews. One out of every five entries focused on serious mental illness/psychosis. Systematic reviews addressing unipolar depression, dementia and certain substance disorders also appeared well-represented. In contrast, a number of impairing disorders frequently seen in practice received less attention, with bipolar disorder, obsessive compulsive disorder (OCD), post-traumatic stress disorder (PTSD) and autism spectrum disorders each accounting for less than 2% of the entries. The majority of interventions reviewed involved medication (57.1%), although this was not the case for a number of childhood-onset disorders. Some diagnostic areas (sleep, anxiety, mood and substance) were addressed by multiple Cochrane review groups (CRGs).Conclusions.The Cochrane Collaboration is well poised to be a strong guiding influence to those seeking to employ evidence-based mental health care. Broadening its diagnostic coverage and diversifying types of intervention reviewed would probably further maximize its impact. A more centralized and directed approach of prioritizing topics could help ensure more comprehensive coverage.


2020 ◽  
Author(s):  
Janell Kwok ◽  
Hildigunnur Anna Hall ◽  
Aja Louise Murray ◽  
Bonnie Auyeung

Abstract BackgroundMaternal prenatal health has been shown to bean important influence on children’s developmental outcomes, which has led to an increased emphasis onprovidingmore information to supportclinical decisions in pregnancy. Several systematic reviewssuggest that analgesic drug use during pregnancy may haveneurodisruptive properties. However, no firm conclusions have yet been drawn onthe associations between prenatal analgesic drug use and children’s long-term development of neurodevelopmental disorderssuch as Autism Spectrum Disorder (ASD) or Attention-Deficit Hyperactivity Disorder (ADHD). Therefore, an umbrella review is proposed for the purpose of examining the associations between maternal analgesic drug use during pregnancy and diagnoses of neurodevelopmental disorders.MethodsIncluded systematic reviews will consist of studies examining the effect of maternal prenatal non-prescription analgesic drug use on children’s neurodevelopmental disorder status. Examined drugs will be restricted to those readilyaccessible and frequently used by pregnant women, and with characteristics that allow them to cross the placenta and directly affect fetal development. Outcomes will be restricted to formal clinical diagnoses of ASD and/or ADHD. Two reviewers will independently identify eligible reviews from six databases and a manual search of reference lists, consultation with field experts, and scan of pre-print archives.A third researcher will be consulted when consensus cannot be reached.Search strategy and data extraction will be based on the preferred reporting items for systematic review and meta-analysis (PRISMA) protocol and PRISMA-P checklist. Extracted data will also include short qualitative summaries by both reviewers. As part of quality assessment, astandardised measurement tool to assess systematic reviews (AMSTAR 2) will be used. A narrative synthesis is proposed to integrate findingsfrom different, potentially methodologically heterogeneousstudies. DiscussionThis umbrella review of associations between maternal prenatal use of non-prescription analgesic drugs andchildren’s neurodevelopmental disorders could allow for firmer conclusions to be drawn through the synthesis of all relevant published research. The synthesis of findings using high-quality evidence couldprovide more accurate healthcare information on the long-term effects of analgesic drugs on neurodevelopment, to better guide future clinical decisions during pregnancy. This review will also allow gaps and methodological differences in the literature to be identified, informing recommendations for future research.Systematic review registrationPROSPEROregistration number CRD42020179216.


2021 ◽  
Author(s):  
David Trembath ◽  
Kandice Varcin ◽  
Hannah Waddington ◽  
Rhylee Sulek ◽  
Cathy Bent ◽  
...  

Background: It is critical that the interventions children on the autism spectrum receive are evidence-based. Given the breadth of available non-pharmacological interventions, a synthesis of research evidence on interventions for children on the autism spectrum is needed.Methods: We completed an umbrella review of systematic reviews, published between 2010-2020, focusing on interventions for children aged 0-12 years. Only systematic reviews that included at least one primary study with a controlled group design were included. Interventions were classified as Behavioural, Developmental, Naturalistic Developmental Behavioural Interventions (NDBIs), Sensory-based, Technology-based, Animal-assisted, Cognitive Behaviour Therapy (CBT), Treatment and Education of Autistic and related Communication-handicapped Children (TEACCH), and ‘other’ (i.e., interventions that didn’t correspond to the other categories). Results: Evidence from 58 systematic reviews indicated positive therapeutic effects for Behavioural interventions, Developmental interventions, NDBIs, Technology-based interventions, and CBT on a range of child and family outcomes. Positive effects for Sensory-based interventions were reported for certain practices only and were limited to select child and family outcomes. A mix of inconsistent and null intervention effects on child and family outcomes were reported for TEACCH and Animal-assisted interventions. There were no consistent findings of the possible effects of intervention delivery (e.g., amount, agent, delivery format, delivery mode) or child characteristics (e.g., age, cognitive skills) on outcomes. Few studies measured outcomes beyond children’s characteristics and skills, to consider broader participation, quality of life, or family outcomes. Adverse effects were rarely reported, and findings were based predominantly on lower quality reviews and/or reviews with a mixture of study designs.Conclusions: There is evidence for the positive effects of a range of interventions, but not for a single best intervention for all children, nor an intervention conferring positive effects across all outcomes examined. The potential influence of intervention and child characteristics on outcomes remains a critical priority for future research.


Author(s):  
Md Mahbub Hossain ◽  
Nusrat Khan ◽  
Abida Sultana ◽  
Ping Ma ◽  
E. Lisako J. McKyer ◽  
...  

<p>With ever-increasing prevalence of various mental disorders worldwide, a comprehensive evaluation of the prevalence of co-occurring psychiatric disorders among individuals with autism spectrum disorder (ASD) is needed to strengthen the knowledge base. This umbrella review aims to summarize the current evidence on the prevalence of comorbid psychiatric disorders among people with ASD. A systematic search of 12 major databases and additional sources was conducted. Any systematically conducted narrative, qualitative, or meta-analytic review reporting the prevalence of psychiatric disorders among people with ASD with no age or geographical restriction were included. From a total of 2755 records, 26 articles representing 14 systematic reviews and 12 meta-analyses met the criteria of this review. The synthesized findings reveal a high burden of comorbid psychiatric disorders among people with ASD, including anxiety disorders, depressive disorders, bipolar and mood disorders, schizophrenia spectrum, suicidal behavior disorders, attention-deficit/hyperactivity disorder, disruptive, impulse-control and conduct disorders amongst diverse age groups, with a majority in younger participants. Most studies were conducted in developed nations, with limited evidence from low and middle-income countries. These synthesized findings provide high-quality evidence for clinical and policy-level decision-making from a global overview of the status of comorbid psychiatric disorders among people with ASD.</p>


2020 ◽  
Vol 66 (6) ◽  
pp. 528-541 ◽  
Author(s):  
Md Mahbub Hossain ◽  
Abida Sultana ◽  
Samia Tasnim ◽  
Qiping Fan ◽  
Ping Ma ◽  
...  

Background: Homelessness is a major problem that critically impacts the mental health and well-being of the affected individuals. This umbrella review aimed to evaluate the current evidence on the prevalence of mental disorders among homeless people from evidence-based systematic reviews and meta-analyses. Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and Joanna Briggs Institute (JBI) methodology for umbrella reviews. We searched 12 major databases and additional sources to identify systematically conducted reviews and meta-analyses reporting the prevalence of mental disorders among homeless populations. Results: We evaluated 1,277 citations and found 15 reviews meeting our criteria. Most studies were conducted among high-income countries with samples from different age groups. Studies reported high prevalence rates of depressive and anxiety disorders, schizophrenia spectrum and psychotic disorders, substance use disorders, suicidal behavior, bipolar and mood disorders, neurocognitive disorders and other mental disorders among homeless people. Moreover, studies also reported a high burden of co-occurring mental and physical health problems among the homeless experiencing mental disorders. Conclusion: This umbrella review synthesized the current evidence on the epidemiological burden of mental disorders in homelessness. This evidence necessitates advanced research to explore psychosocial and epidemiological correlates and adopt multipronged interventions to prevent, identify and treat mental disorders among homeless populations.


2020 ◽  
Author(s):  
Md Mahbub Hossain ◽  
Abida Sultana ◽  
Samia Tasnim ◽  
Qiping Fan ◽  
Ping Ma ◽  
...  

Introduction: Homelessness is a major problem that critically impacts the mental health and wellbeing of the affected individuals. This umbrella review aimed to evaluate the current evidence on the prevalence of mental disorders among homeless people from evidence-based systematic reviews and meta-analyses.Methods: We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and Joanna Briggs Institute (JBI) methodology for umbrella reviews. We searched 12 major databases and additional sources to identify systematically conducted reviews and meta-analyses reporting the prevalence of mental disorders among homeless populations.Results: We evaluated 1,277 citations and found 15 reviews meeting our criteria. Most studies were conducted among high-income countries with samples from different age groups. Studies reported high prevalence rates of depressive and anxiety disorders, schizophrenia spectrum and psychotic disorders, substance use disorders, suicidal behavior, bipolar and mood disorders, neurocognitive disorders, and other mental disorders among homeless people. Moreover, studies also reported a high burden of co-occurring mental and physical health problems among the homeless experiencing mental disorders.Conclusions: This umbrella review synthesized the current evidence on the epidemiological burden of mental disorders in homelessness. This evidence necessitates advanced research to explore psychosocial and epidemiological correlates and adopt multipronged interventions to prevent, identify, and treat mental disorders among homeless populations.


Sign in / Sign up

Export Citation Format

Share Document