scholarly journals Machine learning in systematic reviews: comparing automated text clustering with Lingo3G and human researcher categorization in a rapid review

2021 ◽  
Author(s):  
Ashley Elizabeth Muller ◽  
Heather Melanie R. Ames ◽  
Patricia Sofia Jacobsen Jardim ◽  
Christopher James Rose
Keyword(s):  
Machine Learning ◽  
Systematic Reviews ◽  
Text Clustering ◽  
Rapid Review

scholarly journals Letter to the editor. Healthcare workers on the edge of sanity due to COVID-19: Rapid review of the results of systematic reviews and meta-analyzes

2021 ◽  
Vol 83 ◽  
pp. 21-24
Author(s):  
Ivan Lozada-Martínez ◽  
Maria Bolaño-Romero ◽  
Luis Moscote-Salazar ◽  
Daniela Torres-Llinas ◽  
Amit Agrawal
Keyword(s):  
Systematic Reviews ◽  
Healthcare Workers ◽  
Rapid Review ◽  
Letter To The Editor

scholarly journals Improving palliative and end-of-life care with machine learning and routine data: a rapid review

2019 ◽  
Vol 2 ◽  
pp. 13 ◽  
Author(s):  
Virginia Storick ◽  
Aoife O’Herlihy ◽  
Sarah Abdelhafeez ◽  
Rakesh Ahmed ◽  
Peter May
Keyword(s):  
Machine Learning ◽  
End Of Life ◽  
Full Text ◽  
Clinical Decision Making ◽  
Grey Literature ◽  
Routine Data ◽  
Rapid Review ◽  
Current Evidence ◽  
Cochrane Library ◽  
Eol Care

Introduction: Improving end-of-life (EOL) care is a priority worldwide as this population experiences poor outcomes and accounts disproportionately for costs. In clinical practice, physician judgement is the core method of identifying EOL care needs but has important limitations. Machine learning (ML) is a subset of artificial intelligence advancing capacity to identify patterns and make predictions using large datasets.  ML approaches have the potential to improve clinical decision-making and policy design, but there has been no systematic assembly of current evidence. Methods: We conducted a rapid review, searching systematically seven databases from inception to December 31st, 2018: EMBASE, MEDLINE, Cochrane Library, PsycINFO, WOS, SCOPUS and ECONLIT.  We included peer-reviewed studies that used ML approaches on routine data to improve palliative and EOL care for adults.  Our specified outcomes were survival, quality of life (QoL), place of death, costs, and receipt of high-intensity treatment near end of life.  We did not search grey literature and excluded material that was not a peer-reviewed article. Results: The database search identified 426 citations. We discarded 162 duplicates and screened 264 unique title/abstracts, of which 22 were forwarded for full text review.  Three papers were included, 18 papers were excluded and one full text was sought but unobtainable.  One paper predicted six-month mortality, one paper predicted 12-month mortality and one paper cross-referenced predicted 12-month mortality with healthcare spending.  ML-informed models outperformed logistic regression in predicting mortality but poor prognosis is a weak driver of costs.  Models using only routine administrative data had limited benefit from ML methods. Conclusion: While ML can in principle help to identify those at risk of adverse outcomes and inappropriate treatment near EOL, applications to policy and practice are formative.  Future research must not only expand scope to other outcomes and longer timeframes, but also engage with individual preferences and ethical challenges.

Low-calorie sweeteners and human health: a rapid review of systematic reviews

2020 ◽  
Author(s):  
Lesley Andrade ◽  
Kirsten M Lee ◽  
Allison C Sylvetsky ◽  
Sharon I Kirkpatrick
Keyword(s):  
Risk Factors ◽  
Systematic Reviews ◽  
Chronic Conditions ◽  
Disease Risk ◽  
Rapid Review ◽  
Anthropometric Measures ◽  
Low Calorie ◽  
Associated Risk Factors ◽  
Low Calorie Sweetener

Abstract Introduction Low-calorie sweeteners are increasingly prevalent in the food supply and their consumption has increased in recent decades. Although low-calorie sweeteners approved for use are considered safe from a toxicological perspective, their short- and long-term impacts on chronic disease risk remain uncertain. The aim of this review was to summarize the evidence from systematic reviews on low-calorie sweetener use and chronic conditions and risk factors in children and adults. Methods MEDLINE and the Cochrane Database of Systematic Reviews were searched to identify systematic reviews of randomized and nonrandomized studies that considered low-calorie sweeteners in relation to type 2 diabetes, cardiovascular disease, cancer, anthropometric measures, hypertension, hyperglycemia, hyperlipidemia, insulin resistance, and dental caries. Data were extracted from 9 reviews deemed of moderate or high quality on the basis of AMSTAR-2. Results Narrative synthesis suggested inconsistent evidence on low-calorie sweetener use in relation to chronic conditions and associated risk factors, with nonrandomized studies suggesting positive associations and randomized studies suggesting negative or no associations. Conclusion Continued research on the long-term health impacts of low-calorie sweeteners across all life stages is warranted.

PP66 Hospital Cleaning: Detergent Or Disinfectant-Detergent? A Rapid Review

2018 ◽  
Vol 34 (S1) ◽  
pp. 92-93
Author(s):  
Kathleen Harkin ◽  
Anne Dee
Keyword(s):  
Systematic Reviews ◽  
Adverse Outcomes ◽  
Controlled Vocabulary ◽  
Rapid Review ◽  
Cochrane Library ◽  
Microbial Resistance ◽  
Low Level ◽  
Healthcare Environment ◽  
Environmental Surfaces ◽  
Routine Cleaning

Introduction:Healthcare-associated infections (HAIs) are an important, potentially preventable reason to maintain a clean healthcare environment. However, guidelines from Europe and North America do not concur—European guidelines recommend using neutral detergent (followed by chlorine-based disinfection (CBD) if required), whilst North American guidelines recommend using detergent or hospital-grade disinfectant-detergents for routine cleaning or decontamination of noncritical healthcare environmental surfaces. The objective of this study was to compare the effectiveness on rates of HAIs of: (i) disinfectant-detergents versus detergents; and (ii) the active ingredient of many disinfectant-detergents—quaternary ammonium compounds (QAC)—versus CBD.Methods:A rapid review of systematic reviews was conducted using the following search terms: keywords and controlled vocabulary terms for the concepts of “healthcare environmental surfaces” AND (“QAC-based disinfectants” OR “disinfectant-detergents” OR “decontamination”) AND (“environmental contamination” OR “colonization” OR “HAIs”). The search filters included systematic reviews, guidelines, and technology reports. The following databases were searched: The Cochrane Library; PubMed; and health technology assessment and guideline websites for gray literature. Systematic reviews of studies comparing the effects of disinfectant-detergents with detergent, or comparing QAC with CBD, on rates of HAIs in the healthcare environment were included. Reviews on the cleaning or disinfection of body surfaces or disinfection of invasive medical devices were excluded. Quality assessment was not conducted. Data extraction was performed using a pro forma.Results:The literature search resulted in 356 titles. From ninety-four potentially relevant abstracts, fifty-seven full-texts were evaluated: fifty-one were excluded (eight non-English) and six were included. All review authors cautioned that the evidence was low level, methodologically poor, subject to confounding, and didn't address adverse outcomes. The reviews identified eight relevant primary studies, three of which compared disinfectant-detergents with detergent and found no difference in rates of HAI. Five studies compared QAC with CBD. All five demonstrated that CBD was superior to QAC and reduced Clostridium difficile infection rates in outbreak contexts. Furthermore, QAC may induce sporulation and microbial resistance.Conclusions:Low-level evidence suggested that: there is no advantage in using disinfectant-detergents for routine cleaning of noncritical surfaces; CBD is superior to QAC-based disinfection in reducing clostridial infections; and QAC agents may induce sporulation or microbial resistance.

scholarly journals Pharmacological treatment of hyperactive delirium in people with COVID-19: rethinking conventional approaches

2020 ◽  
Vol 10 ◽  
pp. 204512532094270
Author(s):  
Giovanni Ostuzzi ◽  
Chiara Gastaldon ◽  
Davide Papola ◽  
Andrea Fagiolini ◽  
Serdar Dursun ◽  
...  
Keyword(s):  
Intensive Care ◽  
Drug Interactions ◽  
Systematic Reviews ◽  
Pharmacological Treatment ◽  
Medical Condition ◽  
Regulatory Elements ◽  
Rapid Review ◽  
Cochrane Library ◽  
Future Research ◽  
Acute Psychosis

People with coronavirus disease (COVID-19) might have several risk factors for delirium, which could in turn notably worsen the prognosis. Although pharmacological approaches for delirium are debated, haloperidol and other first-generation antipsychotics are frequently employed, particularly for hyperactive presentations. However, the use of these conventional treatments could be limited in people with COVID-19, due to the underlying medical condition and the risk of drug–drug interactions with anti-COVID treatments. On these premises, we carried out a rapid review in order to identify possible alternative medications for this particular population. By searching PubMed and the Cochrane Library, we selected the most updated systematic reviews of randomised trials on the pharmacological treatment of delirium in both intensive and non-intensive care settings, and on the treatment of agitation related to acute psychosis or dementia. We identified medications performing significantly better than placebo or haloperidol as the reference treatment in each population considered, and assessed the strength of association according to validated criteria. In addition, we collected data on other relevant clinical elements (i.e. common adverse events, drug-drug interactions with COVID-19 medications, daily doses) and regulatory elements (i.e. therapeutic indications, contra-indications, available formulations). A total of 10 systematic reviews were included. Overall, relatively few medications showed benefits over placebo in the four selected populations. As compared with placebo, significant benefits emerged for quetiapine and dexmedetomidine in intensive care unit (ICU) settings, and for none of the medications in non-ICU settings. Considering also data from indirect populations (agitation related to acute psychosis or dementia), aripiprazole, quetiapine and risperidone showed a potential benefit in two or three different populations. Despite limitations related to the rapid review methodology and the use of data from indirect populations, the evidence retrieved can pragmatically support treatment choices of frontline practitioners involved in the COVID-19 outbreak, and indicate future research directions for the treatment of delirium in particularly vulnerable populations.

scholarly journals RobotReviewer: evaluation of a system for automatically assessing bias in clinical trials

2015 ◽  
Vol 23 (1) ◽  
pp. 193-201 ◽  
Author(s):  
Iain J Marshall ◽  
Joël Kuiper ◽  
Byron C Wallace
Keyword(s):  
Machine Learning ◽  
Clinical Trials ◽  
Systematic Reviews ◽  
Risk Of Bias ◽  
Reasonable Accuracy ◽  
Bias Assessment ◽  
Cochrane Database ◽  
The Difference ◽  
Using Data ◽  
Unclear Risk

Abstract Objective To develop and evaluate RobotReviewer, a machine learning (ML) system that automatically assesses bias in clinical trials. From a (PDF-formatted) trial report, the system should determine risks of bias for the domains defined by the Cochrane Risk of Bias (RoB) tool, and extract supporting text for these judgments. Methods We algorithmically annotated 12,808 trial PDFs using data from the Cochrane Database of Systematic Reviews (CDSR). Trials were labeled as being at low or high/unclear risk of bias for each domain, and sentences were labeled as being informative or not. This dataset was used to train a multi-task ML model. We estimated the accuracy of ML judgments versus humans by comparing trials with two or more independent RoB assessments in the CDSR. Twenty blinded experienced reviewers rated the relevance of supporting text, comparing ML output with equivalent (human-extracted) text from the CDSR. Results By retrieving the top 3 candidate sentences per document (top3 recall), the best ML text was rated more relevant than text from the CDSR, but not significantly (60.4% ML text rated ‘highly relevant' v 56.5% of text from reviews; difference +3.9%, [−3.2% to +10.9%]). Model RoB judgments were less accurate than those from published reviews, though the difference was <10% (overall accuracy 71.0% with ML v 78.3% with CDSR). Conclusion Risk of bias assessment may be automated with reasonable accuracy. Automatically identified text supporting bias assessment is of equal quality to the manually identified text in the CDSR. This technology could substantially reduce reviewer workload and expedite evidence syntheses.

scholarly journals Machine learning in occupational safety and health: protocol for a systematic review

2021 ◽  
Vol 5 (1) ◽  
pp. 32-38
Author(s):  
Sara Maheronnaghsh ◽  
H. Zolfagharnasab ◽  
M. Gorgich ◽  
J. Duarte
Keyword(s):  
Machine Learning ◽  
Systematic Reviews ◽  
Occupational Safety ◽  
Occupational Safety And Health ◽  
Massive Data ◽  
Inclusion Criteria ◽  
Safety And Health ◽  
Intelligent Behavior ◽  
Methodological Practice ◽  
Meta Analyses

Industry 4.0 has shaped the way people look at the world and interact with it, especially concerning the work environment with respect to occupational safety and health (OSH). Machine learning (ML), as a branch of Artificial Intelligence (AI), can be effectively used to create expert systems to exhibit intelligent behavior to provide solutions to complicated problems and finally process massive data. Therefore, a study is proposed to provide the best methodological practice in the light of ML. Alongside the review of previous investigations, the following research aims to determine the ML approaches appropriate to OSH issues. In other words, highlighting specific ML methodologies, which have been employed successfully in others areas. Bearing this objective in mind, one can identify an appropriate ML technique to solve a problem in the OSH domain. Accordingly, several questions were designed to conduct the research. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) extension for Protocols and Systematic Reviews were used to draw the research outline. The chosen databases were SCOPUS, PubMed, Science Direct, Inspect, and Web of Science. A set of keywords related to the topic were defined, and both exclusion and inclusion criteria were determined. All of the eligible papers will be analyzed, and the extracted information will be included in an Excel form sheet. The results will be presented in a narrative-based form. Additionally, all tables summarizing the most important findings will be offered.

Sign in / Sign up

Export Citation Format

Share Document