Active Machine Learning in Systematic Literature Reviews: Bias, Fixes, and Appropriate Use

2018 ◽  
Vol 2018 (1) ◽  
Author(s):  
Cara Henning ◽  
Michelle Cawley ◽  
Heidi Hubbard ◽  
Arun Varghese
Keyword(s):  
Machine Learning ◽  
Appropriate Use ◽  
Literature Reviews

A systematic review of machine learning-based missing value imputation techniques

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tressy Thomas ◽  
Enayat Rajabi
Keyword(s):  
Machine Learning ◽  
Selection Process ◽  
Evaluation Metrics ◽  
Correct Prediction ◽  
Data Sets ◽  
Data Set ◽  
Missing Value ◽  
Content Type ◽  
Missing Value Imputation ◽  
Literature Reviews

PurposeThe primary aim of this study is to review the studies from different dimensions including type of methods, experimentation setup and evaluation metrics used in the novel approaches proposed for data imputation, particularly in the machine learning (ML) area. This ultimately provides an understanding about how well the proposed framework is evaluated and what type and ratio of missingness are addressed in the proposals. The review questions in this study are (1) what are the ML-based imputation methods studied and proposed during 2010–2020? (2) How the experimentation setup, characteristics of data sets and missingness are employed in these studies? (3) What metrics were used for the evaluation of imputation method?Design/methodology/approachThe review process went through the standard identification, screening and selection process. The initial search on electronic databases for missing value imputation (MVI) based on ML algorithms returned a large number of papers totaling at 2,883. Most of the papers at this stage were not exactly an MVI technique relevant to this study. The literature reviews are first scanned in the title for relevancy, and 306 literature reviews were identified as appropriate. Upon reviewing the abstract text, 151 literature reviews that are not eligible for this study are dropped. This resulted in 155 research papers suitable for full-text review. From this, 117 papers are used in assessment of the review questions.FindingsThis study shows that clustering- and instance-based algorithms are the most proposed MVI methods. Percentage of correct prediction (PCP) and root mean square error (RMSE) are most used evaluation metrics in these studies. For experimentation, majority of the studies sourced the data sets from publicly available data set repositories. A common approach is that the complete data set is set as baseline to evaluate the effectiveness of imputation on the test data sets with artificially induced missingness. The data set size and missingness ratio varied across the experimentations, while missing datatype and mechanism are pertaining to the capability of imputation. Computational expense is a concern, and experimentation using large data sets appears to be a challenge.Originality/valueIt is understood from the review that there is no single universal solution to missing data problem. Variants of ML approaches work well with the missingness based on the characteristics of the data set. Most of the methods reviewed lack generalization with regard to applicability. Another concern related to applicability is the complexity of the formulation and implementation of the algorithm. Imputations based on k-nearest neighbors (kNN) and clustering algorithms which are simple and easy to implement make it popular across various domains.

scholarly journals Managing alarm systems for quality and safety in the hospital setting

2018 ◽  
Vol 7 (3) ◽  
pp. e000202 ◽  
Author(s):  
Tita Alissa Bach ◽  
Lars-Martin Berglund ◽  
Eva Turk
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Grey Literature ◽  
Hospital Setting ◽  
Integrated Approach ◽  
Clinical Environment ◽  
Alarm Systems ◽  
Literature Reviews ◽  
Technical Factors ◽  
Quality In Healthcare

ObjectiveTo provide an overview of documented studies and initiatives that demonstrate efforts to manage and improve alarm systems for quality in healthcare by human, organisational and technical factors.MethodsA literature review, a grey literature review, interviews and a review of alarm-related standards (IEC 60601-1-8, IEC 62366-1:2015 and ANSI/Advancement of Medical Instrumentation HE 75:2009/2013) were conducted. Qualitative analysis was conducted to identify common themes of improvement elements in the literature and grey literature reviews, interviews and the review of alarm-related standards.Results21 articles and 7 publications on alarm quality improvement work were included in the literature and grey literature reviews, in which 10 themes of improvement elements were identified. The 10 themes were categorised into human factors (alarm training and education, multidisciplinary teamwork, alarm safety culture), organisational factors (alarm protocols and standard procedures, alarm assessment and evaluation, alarm inventory and prioritisation, and sharing and learning) and technical factors (machine learning, alarm configuration and alarm design). 26 clinicians were interviewed. 9 of the 10 themes were identified from the interview responses. The review of the standards identified 3 of the 10 themes. The study findings are also presented in a step-by-step guide to optimise implementation of the improvement elements for healthcare organisations.ConclusionsImproving alarm safety can be achieved by incorporating human, organisational and technical factors in an integrated approach. There is still a gap between alarm-related standards and how the standards are translated into practice, especially in a clinical environment that uses multiple alarming medical devices from different manufacturers. Standardisation across devices and manufacturers and the use of machine learning in improving alarm safety should be discussed in future collaboration between alarm manufacturers, end users and regulators.

“Hasta la vista, baby” – will machine learning terminate human literature reviews in entrepreneurship?

2021 ◽  
pp. 1-30
Author(s):  
Sebastian Robledo ◽  
Andrés Mauricio Grisales Aguirre ◽  
Mathew Hughes ◽  
Fabian Eggers
Keyword(s):  
Machine Learning ◽  
Literature Reviews

scholarly journals Development of a web-based application using machine learning algorithms to facilitate systematic literature reviews

2017 ◽  
Vol 28 ◽  
pp. v518
Author(s):  
H-L. Wong ◽  
T. Luechtefeld ◽  
A. Prawira ◽  
Z. Patterson ◽  
J. Workman ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Web Based ◽  
Literature Reviews

scholarly journals Iterative Guided Machine Learning-Assisted Systematic Literature Reviews: A Diabetes Case Study

2021 ◽  
Author(s):  
John Zimmerman ◽  
Robin Soler ◽  
Lavinder James ◽  
Murphy Sarah ◽  
Atkins Charisma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Scientific Literature ◽  
Relevant Information ◽  
Text Analytics ◽  
Inclusion Criteria ◽  
Literature Reviews ◽  
Study Test ◽  
Model Training

Abstract Background: Systematic Reviews (SR), studies of studies, use a formal process to evaluate the quality of scientific literature and determine ensuing effectiveness from qualifying articles to establish consensus findings around a hypothesis. Their value is increasing as the conduct and publication of research and evaluation has expanded and the process of identifying key insights becomes more time consuming. Text analytics and Machine Learning (ML) techniques may help overcome this problem of scale while still maintaining the level of rigor expected of SRs.Methods: In this article, we discuss an approach that uses existing examples of SRs to build and test a method for assisting the SR title and abstract pre-screening by reducing the initial pool of potential articles down to articles that meet inclusion criteria. Our approach differs from previous approaches to using ML as a SR tool in that it incorporates ML configurations guided by previously conducted SRs, and human confirmation on ML predictions of relevant articles during multiple iterative reviews on smaller tranches of citations. We applied the tailored method to a new SR review effort to validate performance. Results: the case study test of the approach proved a sensitivity (recall) in finding relevant articles during down selection that may rival many traditional processes. Conclusions: We believe this iterative method can help overcome bias in initial ML model training by having humans reinforce ML models with new and relevant information, and is an applied step towards transfer learning for ML in SR.

scholarly journals Smart literature review: a practical topic modelling approach to exploratory literature review

2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Claus Boye Asmussen ◽  
Charles Møller
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Topic Modelling ◽  
Learning Methods ◽  
The Past ◽  
Machine Learning Methods ◽  
Literature Reviews ◽  
Modelling Approach

Abstract Manual exploratory literature reviews should be a thing of the past, as technology and development of machine learning methods have matured. The learning curve for using machine learning methods is rapidly declining, enabling new possibilities for all researchers. A framework is presented on how to use topic modelling on a large collection of papers for an exploratory literature review and how that can be used for a full literature review. The aim of the paper is to enable the use of topic modelling for researchers by presenting a step-by-step framework on a case and sharing a code template. The framework consists of three steps; pre-processing, topic modelling, and post-processing, where the topic model Latent Dirichlet Allocation is used. The framework enables huge amounts of papers to be reviewed in a transparent, reliable, faster, and reproducible way.

MACHINE LEARNING APPLICATION: IMAGE PROCESSING

2021 ◽  
Vol 6 (3) ◽  
Author(s):  
Ayush Gupta
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Computer Vision ◽  
Early Stage ◽  
Human Beings ◽  
Significant Information ◽  
Helpful Tool ◽  
Early Stages ◽  
Literature Reviews ◽  
Current Scenario

-In the current scenario of the data world, the data holds significant information if processed correctly. The data can be in the form of images which can prove to be a boon in deriving the useful insights from it in order to get the knowledge of things at an early stage itself. But the matter of concern is deriving the information from the images will be a tedious task for human beings and would incur a heavy cost and time. So, an easy and cheaper technique is to teach a machine efficiently to do the task for us. The concept of using Machines to do human tasks is known as Machine Learning. In this paper, I present various literature reviews regarding image processing in Machine learning and how image processing has helped in identifying the issues at early stages so that they can be resolved easily without causing much harm. Also, image processing has been a helpful tool in computer vision.

Sign in / Sign up

Export Citation Format

Share Document