-
Journal of Medical Internet Research Nov 2021Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life... (Review)
Review
BACKGROUND
Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD.
OBJECTIVE
This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes.
METHODS
The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed.
RESULTS
We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning-based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%.
CONCLUSIONS
This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.
Topics: Algorithms; Bipolar Disorder; Data Management; Humans; Machine Learning; Natural Language Processing
PubMed: 34806996
DOI: 10.2196/29749 -
Journal of Orthopaedic Trauma Jan 2018Management of high-grade acromioclavicular (AC) joint dislocations has been controversial. Recent studies suggest no difference in outcomes between operative and... (Comparative Study)
Comparative Study Meta-Analysis Review
OBJECTIVES
Management of high-grade acromioclavicular (AC) joint dislocations has been controversial. Recent studies suggest no difference in outcomes between operative and nonoperative management of Rockwood types III-V injuries. The objective of this meta-analysis is to compare outcomes between operative and nonoperative management of high-grade AC joint dislocations.
DATA SOURCES
Search was conducted using PubMed, Embase, and Cochrane databases through October 2016. A broad search strategy was used to identify English, comparative studies of AC joint dislocations.
STUDY SELECTION
Inclusion criteria included comparative studies of AC joint dislocations in adult patients with acute, high-grade AC dislocations.
DATA EXTRACTION
Two authors independently reviewed and assessed for bias according to the U.S. Preventative Task Force Quality Rating Criteria. Data were extracted for validated functional scores, clinical and radiographic outcomes, and complications.
DATA SYNTHESIS
Nineteen studies (n = 954) were included in the meta-analysis. Operative group had better cosmetic outcome (odds ratio [OR] = 0.05; P < 0.00001) and radiographic reduction (OR = 24.94; P < 0.0001). Constant scores favored the operative group, although the difference may not be clinically significant (MD = 3.14; P = 0.03). Nonoperative treatment was associated with faster return to work (MD = 4.17, P < 0.0001), lower implant complications (OR = 7.19, P < 0.0001), and reduced infection rate (OR = 3.65, P = 0.007). No difference was found for DASH Score, return to sport, radiologic evidence of osteoarthritis, and need for surgery after failed management.
CONCLUSIONS
No clinical difference in functional outcome scores was detected between operative and nonoperative management of high-grade AC joint dislocations. Patients in the nonoperative cohort had a more rapid return to work, but were associated with a poorer cosmetic outcome.
LEVEL OF EVIDENCE
Therapeutic Level III. See Instructions for Authors for a complete description of levels of evidence.
Topics: Acromioclavicular Joint; Humans; Joint Dislocations
PubMed: 29257778
DOI: 10.1097/BOT.0000000000001004 -
Diabetic Medicine : a Journal of the... Nov 2019Time preferences, i.e. individuals' degree of patience/impatience in intertemporal choice, have been found to be associated with suboptimal health behaviours and health...
AIM
Time preferences, i.e. individuals' degree of patience/impatience in intertemporal choice, have been found to be associated with suboptimal health behaviours and health outcomes such as smoking, physical inactivity, unhealthy food intake and obesity. In this systematic review, we aimed to synthesise reported associations between time preferences, diabetes self-management behaviours, including use of diabetes technology, and outcomes.
METHODS
We searched MEDLINE, EMBASE, PsycINFO, CINAHL, EconLit and all databases in the Web of Science Core Collection. Peer-reviewed studies of people with diabetes that included at least one diabetes-related behaviour or outcome and a measure of time preferences were included. Non-English language studies were excluded.
RESULTS
A total of 961 records were identified, of which 12 articles were included. Three studies analysed both time-consistent and time-inconsistent preferences, three studies solely analysed time-inconsistent preferences and six studies did not explicitly define a time preference model. Measured outcomes across studies included self-care activities, such as medication-taking, exercising and eating a healthy diet, and biomedical outcomes, such as HbA and diabetes-related complications. There were 10 cross-sectional studies and two panel-data studies. No studies explicitly analysed the relationship between time preferences and diabetes technology use.
CONCLUSIONS
Associations between measures of time preferences, diabetes self-management behaviours and clinical outcomes exist. Higher discount rates determined by both time-consistent and time-inconsistent models predict less diabetes-related self-care and worse outcomes. These findings may add to explanations of the observed variation in diabetes-related health and provide new insights for tailoring interventions and policies aimed at improving diabetes self-management.
Topics: Alcohol Drinking; Diabetes Mellitus; Exercise; Health Behavior; Humans; Obesity; Patient Acceptance of Health Care; Patient Compliance; Patient Outcome Assessment; Self-Management; Time Factors
PubMed: 31392757
DOI: 10.1111/dme.14102 -
BMC Medical Informatics and Decision... Nov 2022Today, the use of data in administrative and clinical processes is quite challenging due to the large volume of data, data collection from various sources, and lack of...
BACKGROUND
Today, the use of data in administrative and clinical processes is quite challenging due to the large volume of data, data collection from various sources, and lack of data structure. As a data management tool, dashboards play an important role in timely visual display of critical information on key performances.
OBJECTIVES
This systematic review aimed to identify functional and non-functional requirements, as well as challenges of using dashboards in hospitals.
METHODS
In this systematic review, four databases, including the Web of Science, PubMed, EMBASE, and Scopus, were searched to find relevant articles from 2000 until May 30, 2020. The final search was conducted on May 30, 2020. Data collection was performed using a data extraction form and reviewing the content of relevant studies on the potentials and challenges of dashboard implementation.
RESULTS
Fifty-four out of 1254 retrieved articles were selected for this study based on the inclusion and exclusion criteria. The functional requirements for dashboards included reporting, reminders, customization, tracking, alert creation, and assessment of performance indicators. On the other hand, the non-functional requirements included the dashboard speed, security, ease of use, installation on different devices (e.g., PCs and laptops), integration with other systems, web-based design, inclusion of a data warehouse, being up-to-data, and use of data visualization elements based on the user's needs. Moreover, the identified challenges were categorized into four groups: data sources, dashboard content, dashboard design, implementation, and integration in other systems at the hospital level.
CONCLUSION
Dashboards, by providing information in an appropriate manner, can lead to the proper use of information by users. In order for a dashboard to be effective in clinical and managerial processes, particular attention must be paid to its capabilities, and the challenges of its implementation need to be addressed.
Topics: Humans; Hospitals; Databases, Factual
PubMed: 36348339
DOI: 10.1186/s12911-022-02037-8 -
Frontiers in Psychiatry 2021Individual participant data meta-analyses (IPD-MAs) include the raw data from relevant randomised clinical trials (RCTs) and involve secondary analyses of the data....
Individual participant data meta-analyses (IPD-MAs) include the raw data from relevant randomised clinical trials (RCTs) and involve secondary analyses of the data. Performed since the late 1990s, ~50 such meta-analyses have been carried out in psychiatry, mostly in the field of treatment. IPD-MAs are particularly relevant for three objectives: (1) evaluation of the average effect of an intervention by combining effects from all included trials, (2) evaluation of the heterogeneity of an intervention effect and sub-group analyses to approach personalised psychiatry, (3) mediation analysis or surrogacy evaluation to replace a clinical (final) endpoint for the evaluation of new treatments with intermediate or surrogate endpoints. The objective is to describe the interest and the steps of an IPD-MA method applied to the field of psychiatric therapeutic research. The method is described in three steps. First, the identification of the relevant trials with an explicit description of the inclusion/exclusion criteria for the RCT to be incorporated in the IPD-MA and a definition of the intervention, the population, the context and the relevant points (outcomes or moderators). Second, the data management with the standardisation of collected variables and the evaluation and the assessment of the risk-of-bias for each included trial and of the global risk. Third, the statistical analyses and their interpretations, depending on the objective of the meta-analysis. All steps are illustrated with examples in psychiatry for treatment issues, excluding study protocols. The meta-analysis of individual patient data is challenging. Only strong collaborations between all stakeholders can make such a process efficient. An "ecosystem" that includes all stakeholders (questions of interest prioritised by the community, funders, trialists, journal editors, institutions, …) is required. International medical societies can play a central role in favouring the emergence of such communities.
PubMed: 34393841
DOI: 10.3389/fpsyt.2021.644980 -
Otology & Neurotology : Official... Dec 2014The management options for otologic symptoms (i.e., hearing loss, otorrhea) in patients with fibrous dysplasia of the temporal bone (FDTB) include either observation or... (Review)
Review
OBJECTIVES
The management options for otologic symptoms (i.e., hearing loss, otorrhea) in patients with fibrous dysplasia of the temporal bone (FDTB) include either observation or otologic surgery. The objective of this review is to describe the hearing outcomes in patients with FDTB to compare surgical intervention and conservative management to determine an evidence-based approach to patient management.
DATA SOURCES
Cochrane Central Register of Controlled Trials (1995-April 5, 2013), MEDLINE (January 1948-April 5, 2013), EMBASE (January 1974-April 5, 2013), conference proceedings, and the reference lists of articles.
STUDY SELECTION
Studies describing interventions or no intervention in patients with FDTB were included. Studies failing to report hearing outcomes were excluded.
DATA EXTRACTION
Two authors independently reviewed titles and abstracts, read full-text articles, assessed quality, and extracted data. The Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines were followed.
DATA SYNTHESIS
Seventy-two studies involving 215 patients were included. Thirty-one studies (n = 49 patients), including three case series and 28 case reports, had sufficient information for analysis of hearing outcomes (Level 4 evidence). The surgical intervention showing the best hearing outcomes was canaloplasty, with improvement in 84% of patients (n = 16 patients) and stable hearing thresholds in 18% (n = 3 patients).
CONCLUSION
The literature lacks consistent reporting of hearing outcomes after otologic surgery in FDTB. Level 4 evidence suggests that an improvement in hearing thresholds is achievable in most patients when the disease involves the external ear canal. A management algorithm is proposed using the available evidence.
Topics: Fibrous Dysplasia of Bone; Hearing Loss; Humans; Temporal Bone; Treatment Outcome
PubMed: 25280053
DOI: 10.1097/MAO.0000000000000602 -
Environmental Science & Technology Oct 2022Most soil quality measurements have been limited to laboratory-based methods that suffer from time delay, high cost, intensive labor requirement, discrete data... (Review)
Review
Most soil quality measurements have been limited to laboratory-based methods that suffer from time delay, high cost, intensive labor requirement, discrete data collection, and tedious sample pretreatment. Real-time continuous soil monitoring (RTCSM) possesses a great potential to revolutionize field measurements by providing first-hand information for continuously tracking variations of heterogeneous soil parameters and diverse pollutants in a timely manner and thus enable constant updates essential for system control and decision-making. Through a systematic literature search and comprehensive analysis of state-of-the-art RTCSM technologies, extensive discussion of their vital hurdles, and sharing of our future perspectives, this critical review bridges the knowledge gap of spatiotemporal uninterrupted soil monitoring and soil management execution. First, the barriers for reliable RTCSM data acquisition are elucidated by examining typical soil monitoring techniques (e.g., electrochemical and spectroscopic sensors). Next, the prevailing challenges of the RTCSM sensor network, data transmission, data processing, and personalized data management are comprehensively discussed. Furthermore, this review explores RTCSM data application for updating diverse strategies including high-fidelity soil process models, control methodologies, digital soil mapping, soil degradation, food security, and climate change mitigation. Finally, the significance of RTCSM implementation in agricultural and environmental fields is underscored through illuminating future directions and perspectives in this systematic review.
Topics: Agriculture; Environmental Pollutants; Soil
PubMed: 36121207
DOI: 10.1021/acs.est.2c03562 -
Frontiers in Public Health 2023Non-Fungible Tokens (NFTs) are digital assets that are verified using blockchain technology to ensure authenticity and ownership. NFTs have the potential to...
INTRODUCTION
Non-Fungible Tokens (NFTs) are digital assets that are verified using blockchain technology to ensure authenticity and ownership. NFTs have the potential to revolutionize healthcare by addressing various issues in the industry.
METHOD
The goal of this study was to identify the applications of NFTs in healthcare. Our scoping review was conducted in 2023. We searched the Scopus, IEEE, PubMed, Web of Science, Science Direct, and Cochrane scientific databases using related keywords. The article selection process was based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA).
RESULTS
After applying inclusion and exclusion criteria, a total of 13 articles were chosen. Then extracted data was summarized and reported. The most common application of NFTs in healthcare was found to be in health data management with 46% frequency, followed by supply chain management with 31% frequency. Furthermore, Ethereum is the main blockchain platform that is applied in NFTs in healthcare with 70%.
DISCUSSION
The findings from this review indicate that the NFTs that are currently used in healthcare could transform it. Also, it appears that researchers have not yet investigated the numerous potentials uses of NFTs in the healthcare field, which could be utilized in the future.
Topics: Humans; Data Management; Databases, Factual; Industry; Research Personnel; Technology
PubMed: 38074727
DOI: 10.3389/fpubh.2023.1266385 -
American Journal of Health Promotion :... Sep 2017The study objective was to conduct a systematic review of the effectiveness of integrated workplace interventions that combine health promotion with occupational health... (Review)
Review
OBJECTIVE
The study objective was to conduct a systematic review of the effectiveness of integrated workplace interventions that combine health promotion with occupational health and safety.
DATA SOURCE
Electronic databases (n = 8), including PsychInfo and MEDLINE, were systematically searched.
STUDY INCLUSION AND EXCLUSION CRITERIA
Studies included were those that reported on workplace interventions that met the consensus definition of an "integrated approach," published in English, in the scientific literature since 1990.
DATA EXTRACTION
Data extracted were occupation, worksite, country, sample size, intervention targets, follow-up period, and results reported. Quality was assessed according to American College of Occupational and Environmental Medicine Practice Guidelines.
DATA SYNTHESIS
Heterogeneity precluded formal meta-analyses. Results were classified according to the outcome(s) assessed into five categories (health promotion, injury prevention, occupational health and safety management, psychosocial, and return-on-investment). Narrative synthesis of outcomes was performed.
RESULTS
A total of 31 eligible studies were identified; 23 (74%) were (quasi-)experimental trials. Effective interventions were most of those aimed at improving employee physical or mental health. Less consistent results were reported from integrated interventions targeting occupational health and safety management, injury prevention, or organizational cost savings.
CONCLUSION
Integrated approaches have been posed as comprehensive solutions to complex issues. Empirical evidence, while still emerging, provides some support for this. Continuing investment in, and evaluation of, integrated approaches are worthwhile.
Topics: Cost-Benefit Analysis; Developed Countries; Health Promotion; Health Status; Humans; Mental Health; Occupational Health; Occupations; Safety Management; Workplace; Wounds and Injuries
PubMed: 26730561
DOI: 10.4278/ajhp.141027-LIT-542 -
Autoimmunity Reviews May 2024Estimate the global prevalence of anti-Ro52-kDa/SSA (TRIM21) autoantibodies in systemic sclerosis (SSc), and describe the associated clinical phenotype, through a... (Meta-Analysis)
Meta-Analysis Review
Prevalence of anti-Ro52-kDa/SSA (TRIM21) antibodies and associated clinical phenotype in systemic sclerosis: Data from a French cohort, a systematic review and meta-analysis.
OBJECTIVES
Estimate the global prevalence of anti-Ro52-kDa/SSA (TRIM21) autoantibodies in systemic sclerosis (SSc), and describe the associated clinical phenotype, through a systematic review and meta-analysis of published reports and new data from our French cohort.
METHODS
Anti-TRIM21 seropositivity and associated SSc characteristics were assessed in a cross-sectional study including 300 patients of Lille University Hospital. A systematic review of the literature was performed in Pubmed and Embase, followed by a meta-analysis, using data on prevalence, clinical/demographical/biological characteristics of SSc patients and the type of assay used for anti-TRIM21 antibodies detection (PROSPERO n° CRD42021223719).
FINDINGS
In the cross-sectional study, anti-TRIM21 antibodies prevalence was 26% [95%CI: 21; 31]. Anti-centromere antibodies were the most frequent SSc specific autoantibodies coexisting with anti-TRIM21. Patients with anti-TRIM21 antibodies were more frequently women (91% vs 77%, p = 0.006), more likely to present an associated Sjögren's syndrome (19% vs 7%, p < 0.001), had a higher rate of pulmonary arterial hypertension (PAH) (15% vs 6%, p = 0.017) and a greater frequency of digestive complications such as dysphagia (12% vs 5%, p = 0.038) or nausea/vomiting (10% vs 3%, p = 0.009) than anti-TRIM21 negative patients. Thirty-five articles corresponding to a total of 11,751 SSc patients were included in the meta-analysis. In this population, the overall seroprevalence of anti-TRIM21 antibodies was 23% [95%CI: 21; 27] with a high degree of heterogeneity (I: 93% Phet: <0.0001), partly explained by the methods of detection. Anti-TRIM21 seropositivity was positively associated with female sex (OR: 1.60 [95%CI: 1.25, 2.06]), limited cutaneous subset (OR: 1.29 [1.04, 1.61]), joint manifestations (OR: 1.33 [1.05, 1.68]), pulmonary hypertension (PH) (OR: 1.82 [1.42, 2.33]), and interstitial lung disease (ILD) (OR: 1.31 [1.07, 1.60]).
INTERPRETATION
Anti-TRIM21 antibodies frequently co-exist with usual SSc antibodies, but are independently associated to a higher risk of cardio-pulmonary complications. The presence of these autoantibodies should therefore be considered when assessing the risk of developing PH and ILD, and deserves further studies on appropriate screening and follow-up of patients.
Topics: Humans; Scleroderma, Systemic; Autoantibodies; Ribonucleoproteins; France; Phenotype; Antibodies, Antinuclear; Prevalence; Female; Cross-Sectional Studies; Male
PubMed: 38555075
DOI: 10.1016/j.autrev.2024.103536