scholarly journals Modern Clinical Text Mining: A Guide and Review

2020 ◽  
Author(s):  
Bethany Percha
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Health Records ◽  
Clinical Text ◽  
Quality Improvement Research ◽  
The Past ◽  
New Methods ◽  
Comprehensive Survey ◽  
Technical Advances ◽  
First Time

Electronic health records (EHRs) are becoming a vital source of data for healthcare quality improvement, research, and operations. However, much of the most valuable information contained in EHRs remains buried in unstructured text. The field of clinical text mining has advanced rapidly in recent years, transitioning from rule-based approaches to machine learning and, more recently, deep learning. With new methods come new challenges, however, especially for those new to the field. This review provides an overview of clinical text mining for those who are encountering it for the first time (e.g. physician researchers, operational analytics teams, machine learning scientists from other domains). While not a comprehensive survey, it describes the state of the art, with a particular focus on new tasks and methods developed over the past few years. It also identifies key barriers between these remarkable technical advances and the practical realities of implementation at health systems and in industry.

scholarly journals Modern Clinical Text Mining: A Guide and Review

2021 ◽  
Author(s):  
Bethany Percha
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Health Records ◽  
Clinical Text ◽  
Quality Improvement Research ◽  
The Past ◽  
New Methods ◽  
Comprehensive Survey ◽  
Technical Advances ◽  
First Time

Electronic health records (EHRs) are becoming a vital source of data for healthcare quality improvement, research, and operations. However, much of the most valuable information contained in EHRs remains buried in unstructured text. The field of clinical text mining has advanced rapidly in recent years, transitioning from rule-based approaches to machine learning and, more recently, deep learning. With new methods come new challenges, however, especially for those new to the field. This review provides an overview of clinical text mining for those who are encountering it for the first time (e.g. physician researchers, operational analytics teams, machine learning scientists from other domains). While not a comprehensive survey, it describes the state of the art, with a particular focus on new tasks and methods developed over the past few years. It also identifies key barriers between these remarkable technical advances and the practical realities of implementation at health systems and in industry.

scholarly journals Modern Clinical Text Mining: A Guide and Review

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Bethany Percha
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Data Science ◽  
Annual Review ◽  
Publication Date ◽  
Biomedical Data ◽  
Clinical Text ◽  
Quality Improvement Research ◽  
Comprehensive Survey ◽  
Technical Advances

Electronic health records (EHRs) are becoming a vital source of data for healthcare quality improvement, research, and operations. However, much of the most valuable information contained in EHRs remains buried in unstructured text. The field of clinical text mining has advanced rapidly in recent years, transitioning from rule-based approaches to machine learning and, more recently, deep learning. With new methods come new challenges, however, especially for those new to the field. This review provides an overview of clinical text mining for those who are encountering it for the first time (e.g., physician researchers, operational analytics teams, machine learning scientists from other domains). While not a comprehensive survey, this review describes the state of the art, with a particular focus on new tasks and methods developed over the past few years. It also identifies key barriers between these remarkable technical advances and the practical realities of implementation in health systems and in industry. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 4 is July 2021. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Can an Algorithm Be Disturbed?

2019 ◽  
pp. 32-65
Author(s):  
James E. Dobson
Keyword(s):  
Machine Learning ◽  
Text Mining ◽  
Literary Criticism ◽  
Digital Humanities ◽  
Cultural Criticism ◽  
Literary Analysis ◽  
The Past ◽  
Digital Methods ◽  
Learning Analysis

This chapter positions the use of machine learning within the digital humanities as part of a wider movement that nostalgically seeks to return literary criticism to the structuralist era, to a moment characterized by belief in systems, structure, and the transparency of language. While digital methods enable one to examine radically larger archives than those assembled in the past, a transformation that Matthew Jockers characterizes as a shift from micro to macroanalysis, the fundamental assumptions about texts and meaning implicit in these tools and in the criticism resulting from the use of these tools belong to a much earlier period of literary analysis. The author argues that the use of imported tools and procedures within literary and cultural criticism on the part of some digital humanists in the present is an attempt to separate methodology from interpretation. In the process, these critics have deemphasized the degree to which methodology participates in interpretation. The chapter closes by way of a return to the deconstructive critique of structuralism in order to highlight the ways in which numerous interpretive decisions are suppressed in the selection, encoding, and preprocessing of digitized textual sources for text mining and machine learning analysis.

scholarly journals LITERATURE SURVEY ON MACHINE LEARNING BASED TECHNIQUES IN MEDICAL DATAANALYSIS

2019 ◽  
pp. 1-4
Author(s):  
Lavanya Vemulapalli
Keyword(s):  
Machine Learning ◽  
Disease Diagnosis ◽  
Research Area ◽  
Machine Learning Techniques ◽  
Intelligent Algorithms ◽  
The Past ◽  
Disease Prognosis ◽  
Learning Techniques ◽  
Machine Learning Applications ◽  
Comprehensive Survey

Machine Learning plays a significant role among the areas of Artificial Intelligence (AI). During recent years, Machine Learning (ML) has been attracting many researchers, and it has been successfully applied in many fields such as medical, education, forecasting etc., Right now, the diagnosis of diseases is mostly from expert's decision. Diagnosis is a major task in clinical science as it is crucial in determining if a patient is having the disease or not. This in turn decides the suitable path of treatment for disease diagnosis. Applying machine learning techniques for disease diagnosis using intelligent algorithms has been a hot research area of computer science. This paper throws a light on the comprehensive survey on the machine learning applications in the medical disease prognosis during the past decades

scholarly journals A State-of-the-Art Review on Machine Learning-based Methods for Prostate Cancer Diagnosis

2021 ◽  
Vol 5 (1) ◽  
pp. 41
Author(s):  
Ari Mohammed ali Ahmed ◽  
Aree Ali Mohammed
Keyword(s):  
Prostate Cancer ◽  
Machine Learning ◽  
State Of The Art ◽  
Characteristic Curve ◽  
Machine Learning Techniques ◽  
Learning Methods ◽  
The Past ◽  
Learning Techniques ◽  
Comprehensive Survey ◽  
Auc Value

Prostate cancer can be viewed as the second most dangerous and diagnosed cancer of men all over the world. In the past decade, machine and deep learning methods play a significant role in improving the accuracy of classification for both binary and multi classifications. This review is aimed at providing a comprehensive survey of the state of the art in the past 5 years from 2015 to 2020, focusing on different datasets and machine learning techniques. Moreover, a comparison between studies and a discussion about the potential future researches is described. First, an investigation about the datasets used by the researchers and the number of samples associated with each patient is performed. Then, the accurate detection of each research study based on various machine learning methods is given. Finally, an evaluation of five techniques based on the receiver operating characteristic curve has been presented to show the accuracy of the best technique according to the area under curve (AUC) value. Conducted results indicate that the inception-v3 classifier has the highest score for AUC, which is 0.91.

scholarly journals Produção científica sobre hospitais no contexto da ciência de dados: um estudo a partir da web of science

2021 ◽  
Vol 26 (Especial) ◽  
pp. 1-16
Author(s):  
Natanael Vitor Sobral ◽  
Gillian Leandro de Queiroga Lima ◽  
Ana Sara Pereira de Melo Sobral
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Big Data ◽  
Text Mining ◽  
Data Warehouse ◽  
Data Analytics ◽  
Data Science ◽  
Web Of Science ◽  
Health Technology ◽  
Health Records

Objetivo: realizar análise bibliométrica sobre as aplicações da ciência de dados no âmbito das organizações hospitalares. Método: por meio de pesquisa na base de dados Web of Science, verificou-se a existência de termos relacionados à ciência de dados, tais como “big data”, “data analytics”, “businesss intelligence”, “data mining”, “data warehouse”, “text mining” e “data science", relacionando-os a hospitais. A análise de dados pautou-se na técnica de análise de redes sociais. O período considerado foi de 2015 a 2019. Resultado: “machine learning” e “electronic health records” despontam como assuntos relevantes. As interações mais expressivas refletem a inclinação da informática médica em assuntos relacionados à tomada de decisão, sistemas de informação para hospitais e unidade de cuidados intensivos. Sobre os campos científicos, nota-se a predominância esperada da área de saúde e dos domínios pertencentes ou fronteiriços à tecnologia. No mais, vê-se que a grande variedade de áreas encontradas acusa a natureza multidisciplinar do assunto, inclusive com importante participação da Ciência da Informação (CI). Em relação à geografia do conhecimento, observa-se um razoável grau de descentralização, havendo produções representativas na América do Norte, Europa e Ásia. Quanto aos veículos de publicação, destaque para os Studies in Health Technology and Informatics, que compreendem uma série de publicações. Os dois periódicos mais representativos da lista, integram, respectivamente, os grupos Springer Nature e Elsevier, grandes players do mercado editorial científico. Conclusões: por fim, evidencia-se a multidisciplinaridade existente em torno do assunto estudado e a relevância da tecnologia para o progresso das organizações hospitalares.

Machine Learning into Metaheuristics

2021 ◽  
Vol 54 (6) ◽  
pp. 1-32
Author(s):  
El-Ghazali Talbi
Keyword(s):  
Machine Learning ◽  
Optimization Problem ◽  
State Of The Art ◽  
Research Topic ◽  
High Quality ◽  
Research Issues ◽  
The Past ◽  
Open Research ◽  
Comprehensive Survey ◽  
High Level

During the past few years, research in applying machine learning (ML) to design efficient, effective, and robust metaheuristics has become increasingly popular. Many of those machine learning-supported metaheuristics have generated high-quality results and represent state-of-the-art optimization algorithms. Although various appproaches have been proposed, there is a lack of a comprehensive survey and taxonomy on this research topic. In this article, we will investigate different opportunities for using ML into metaheuristics. We define uniformly the various ways synergies that might be achieved. A detailed taxonomy is proposed according to the concerned search component: target optimization problem and low-level and high-level components of metaheuristics. Our goal is also to motivate researchers in optimization to include ideas from ML into metaheuristics. We identify some open research issues in this topic that need further in-depth investigations.

The Evolution of Lead Extraction

2009 ◽  
Vol 5 (1) ◽  
pp. 32
Author(s):  
Melanie Maytin ◽  
Laurence M Epstein ◽  
◽  
Keyword(s):  
Natural Selection ◽  
Lead Extraction ◽  
Significant Morbidity ◽  
Extraction Techniques ◽  
Extraction Technology ◽  
Device Management ◽  
Future Developments ◽  
The Past ◽  
New Methods ◽  
Life Threatening

Prior to the introduction of successful intravascular countertraction techniques, options for lead extraction were limited and dedicated tools were non-existent. The significant morbidity and mortality associated with these early extraction techniques limited their application to life-threatening situations such as infection and sepsis. The past 30 years have witnessed significant advances in lead extraction technology, resulting in safer and more efficacious techniques and tools. This evolution occurred out of necessity, similar to the pressure of natural selection weeding out the ineffective and highly morbid techniques while fostering the development of safe, successful and more simple methods. Future developments in lead extraction are likely to focus on new tools that will allow us to provide comprehensive device management and the design of new leads conceived to facilitate future extraction. With the development of these new methods and novel tools, the technique of lead extraction will continue to require operators that are well versed in several methods of extraction. Garnering new skills while remembering the lessons of the past will enable extraction technologies to advance without repeating previous mistakes.

Spider diversity in the Bukit Timah Nature Reserve, Singapore

2019 ◽  
Vol 71 ((suppl.1)) ◽  
pp. 209-243
Author(s):  
J.K.H. Koh ◽  
D.J. Court
Keyword(s):  
Nature Reserve ◽  
New Records ◽  
Secondary Forest ◽  
Distinct Species ◽  
Primary Forest ◽  
Preliminary Results ◽  
Vegetation Zones ◽  
Comprehensive Survey ◽  
Quantitative Analyses ◽  
First Time

This paper discusses the preliminary results of the first comprehensive survey of the spiders of the Bukit Timah Nature Reserve (BTNR) in Singapore. Two plots were established in each of the three zones of vegetation, viz., primary forest, old secondary forest, and maturing secondary forest. They were repeatedly sampled over an 18-month period. Sorting of the collection so far suggests that the three vegetation zones harbour rather different spider assemblages. Only ~9% of the total spider fauna recovered was shared by all three zones. The results have also yielded a preliminary picture of dominance, abundance and rarity. Although first intended to obtain a baseline for future quantitative analyses, the survey became a testing ground to modify and refine methodology so as to conduct future quantitative surveys with greater scientific rigour. Taxonomic work on the samples so far shows that the spiders in the BTNR span over 43 families, of which six families are listed for the first time in Singapore. The tally is summarised in an interim checklist of BTNR spiders. The checklist, with a total of 317 entries, shows that there are 158 described species of spiders in BTNR, of which 25 species are new records for Singapore. Another 159 morphospecies are provisionally recognised as distinct species, some of which may be new to science. Our observations during the survey have allowed us to provide a narrative of BTNR spider diversity against a backdrop of their microhabitat specialisation.

Sign in / Sign up

Export Citation Format

Share Document