editorial computational intelligence techniques in...

3
Editorial Computational Intelligence Techniques in Medicine Ezequiel López-Rubio, 1 David A. Elizondo, 2 Martin Grootveld, 3 José M. Jerez, 1 and Rafael M. Luque-Baena 4 1 Department of Computer Languages and Computer Science, University of M´ alaga, 29071 M´ alaga, Spain 2 DIGITS, Faculty of Technology, De Montfort University, e Gateway, Leicester LE1 9BH, UK 3 Leicester School of Pharmacy, Faculty of Health and Life Sciences, De Montfort University, e Gateway, Leicester LE1 9BH, UK 4 Department of Computer and Network Systems Engineering, University of Extremadura, 06800 M´ erida, Spain Correspondence should be addressed to Ezequiel L´ opez-Rubio; [email protected] Received 9 December 2014; Accepted 9 December 2014 Copyright © 2015 Ezequiel L´ opez-Rubio et al. is is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 1. Introduction e advent of the information age, also commonly known as the digital age, has made a profound impact on health sciences. Vast amounts of datasets now flow through the different stages of healthcare organizations, and there is a major requirement to extract knowledge and employ it to improve these centres in all respects. Intelligent computer systems provide support to health professionals involved both in the medical and managerial contexts. Amongst these systems, computational intelligence approaches have gained increasing popularity given their ability to cope with large amounts of clinical data and uncertain information. e goal of this special issue is to offer a broad view of this exciting field, the ever-growing importance of which is driven by the increasing availability of data and computational power. 2. Computational Intelligence Computational intelligence is based on biologically inspired computational algorithms. e key pillars that compose this field are neural networks, genetic algorithms, and fuzzy systems. Neural networks are algorithms that can be used for function approximation or classification problems [1, 2]. ey include supervised, unsupervised, and reinforcement learning [3]. Genetic algorithms, however, [4] are search algorithms inspired by biological genetics. ey rely on two main operators, cross-over and mutation. Populations of individuals representing solutions to the problem are created over several generations. e algorithm uses a random- guided approach to optimize problems based on a fitness function. Fuzzy logic [5] is based on fuzzy set theory [6] in order to encompass reasoning that is fluid or approximate rather than fixed and exact. Fuzzy logic variables have “truth” values ranging in degree between 0 and 1 which can also handle “partial truth”. Computational intelligence techniques have been suc- cessfully used in many “real-world” applications in a variety of engineering problems. ey can also be used in the medical research domain. 3. Organisation and Plan of the Special Issue is special issue presents a compilation of research papers describing novel recent strategies and developments on the use of computational intelligence techniques in medicine. It will be of interest to researchers interested in industry, academics, and also to postgraduate students interested in the latest advances and developments in the field of computa- tional intelligence in medicine. Its contents are summarized next. One of the best-known application fields of these tech- niques is computer-aided diagnosis (CAD). At this point, two types of methods must be distinguished: those which aim Hindawi Publishing Corporation Computational and Mathematical Methods in Medicine Volume 2015, Article ID 196976, 2 pages http://dx.doi.org/10.1155/2015/196976

Upload: others

Post on 21-May-2020

16 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Editorial Computational Intelligence Techniques in Medicinedownloads.hindawi.com/journals/cmmm/2015/196976.pdf · 2019-07-31 · Editorial Computational Intelligence Techniques in

EditorialComputational Intelligence Techniques in Medicine

Ezequiel López-Rubio,1 David A. Elizondo,2 Martin Grootveld,3

José M. Jerez,1 and Rafael M. Luque-Baena4

1Department of Computer Languages and Computer Science, University of Malaga, 29071 Malaga, Spain2DIGITS, Faculty of Technology, De Montfort University, The Gateway, Leicester LE1 9BH, UK3Leicester School of Pharmacy, Faculty of Health and Life Sciences, De Montfort University, The Gateway, Leicester LE1 9BH, UK4Department of Computer and Network Systems Engineering, University of Extremadura, 06800 Merida, Spain

Correspondence should be addressed to Ezequiel Lopez-Rubio; [email protected]

Received 9 December 2014; Accepted 9 December 2014

Copyright © 2015 Ezequiel Lopez-Rubio et al. This is an open access article distributed under the Creative Commons AttributionLicense, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properlycited.

1. Introduction

The advent of the information age, also commonly knownas the digital age, has made a profound impact on healthsciences. Vast amounts of datasets now flow through thedifferent stages of healthcare organizations, and there is amajor requirement to extract knowledge and employ it toimprove these centres in all respects.

Intelligent computer systems provide support to healthprofessionals involved both in the medical and managerialcontexts. Amongst these systems, computational intelligenceapproaches have gained increasing popularity given theirability to cope with large amounts of clinical data anduncertain information.

The goal of this special issue is to offer a broad view of thisexciting field, the ever-growing importance of which is drivenby the increasing availability of data and computationalpower.

2. Computational Intelligence

Computational intelligence is based on biologically inspiredcomputational algorithms. The key pillars that compose thisfield are neural networks, genetic algorithms, and fuzzysystems. Neural networks are algorithms that can be usedfor function approximation or classification problems [1, 2].They include supervised, unsupervised, and reinforcementlearning [3]. Genetic algorithms, however, [4] are search

algorithms inspired by biological genetics. They rely on twomain operators, cross-over and mutation. Populations ofindividuals representing solutions to the problem are createdover several generations. The algorithm uses a random-guided approach to optimize problems based on a fitnessfunction. Fuzzy logic [5] is based on fuzzy set theory [6] inorder to encompass reasoning that is fluid or approximaterather than fixed and exact. Fuzzy logic variables have “truth”values ranging in degree between 0 and 1 which can alsohandle “partial truth”.

Computational intelligence techniques have been suc-cessfully used in many “real-world” applications in a varietyof engineering problems.They can also be used in themedicalresearch domain.

3. Organisation and Plan of the Special Issue

This special issue presents a compilation of research papersdescribing novel recent strategies and developments on theuse of computational intelligence techniques in medicine.It will be of interest to researchers interested in industry,academics, and also to postgraduate students interested inthe latest advances and developments in the field of computa-tional intelligence in medicine. Its contents are summarizednext.

One of the best-known application fields of these tech-niques is computer-aided diagnosis (CAD). At this point, twotypes of methods must be distinguished: those which aim

Hindawi Publishing CorporationComputational and Mathematical Methods in MedicineVolume 2015, Article ID 196976, 2 pageshttp://dx.doi.org/10.1155/2015/196976

Page 2: Editorial Computational Intelligence Techniques in Medicinedownloads.hindawi.com/journals/cmmm/2015/196976.pdf · 2019-07-31 · Editorial Computational Intelligence Techniques in

2 Computational and Mathematical Methods in Medicine

at providing clinicians with enhanced diagnostic proceduresthat can lead to improved human decisions, and those thatintend to provide a second opinion; that is, given a set of signs,they can indicate or confirm one or more possible diseaseprocesses.

Many methods belonging to the first type correspondto image processing algorithms. Indeed, the automatedsegmentation of magnetic resonance images (MRI) of thebrain is employed to determine pathological regions andto plan image-guided surgery. On the other hand, high-resolution computed tomography has become a standard toolto diagnose diffuse lung diseases, and sparse representationscan help to identify abnormal patterns. Segmentation is alsouseful at the microscopic scale, where intracellular calciumvariation can be measured by a marked controlled watershedtransform. Additionally, the emergence of a number ofdiffering medical imaging techniques brings our attentionto the problem of fusing these images. An approach basedon the Nonsubsampled Contourlet Transform, which is adirectional multiresolution image representation method, isalso proposed.

Other diagnostic enhancement procedures are not relatedto image processing. In this issue, the most relevant criteriato diagnose Guillain-Barre syndrome are studied by thePartitions around Medoids clustering algorithm, which isable to manage both categorical and numerical data sinceit only requires the distance matrix amongst the samples.The reactivity of blood pressure (BP) to talking episodes ispredicted by a hybrid system composed of several soft com-puting approaches, specifically neural networks, an adaptiveneurofuzzy inference system, and support vector machines(SVMs). This increases the precision of BP measures forclinical and research purposes. Screening for prediabetes iscarried out by means of a combination of neural networksand SVMs, which is aimed at early intervention to avoid theserious complications associated with the disease. Validationprocedures for electroencephalographic (EEG) signal pro-cessing by principal component analysis (PCA) are also pro-posed, which is a valuable tool for many neurological studies.EEG signals are also analyzed by mixed-norm regularizationfor sensor selection in brain computer interfaces. Finally,the problem of privacy preservation in self-helped medicaldiagnosis is addressed, where secure two-party computationin wireless sensor networks is ensured in order to developa system where the patient inserts a health card into anautomated teller machine and obtains a diagnostic report.

The second class of methods includes classification sys-tems which are most useful for the early diagnosis of diseasesfor which there is currently no definitive diagnostic test.Computer-aided screening for Alzheimer’s disease based onneuropsychological rating scales is carried out by a hybridapproachwhich combines rough sets, genetic algorithms, andBayesian networks, and an expert system for multicriteriadecision support in psychotic disorders is proposed. Clinicaldecision support systems are not limited to diagnosis, asnoted in the osteoporosis case, where the system can alsorecommend treatments and assess the fracture risk.

Management and planning represent the other sec-tions of healthcare organizations that can also benefit from

the applications of computational intelligence. Particle swarmoptimization can be employed to enhance blood assignmentin blood banks, whilst social network simulation can helpto develop effective preventative and interventional strategiesfor AIDS epidemics.

Last but not least, computational intelligence techniquesare also useful tools for probing the improvement of drugmanufacturing processes, as demonstrated in another pro-posal where neural networks are applied to drug tablet visualtracking for high speed mass production.

Ezequiel Lopez-RubioDavid A. ElizondoMartin Grootveld

Jose M. JerezRafael M. Luque-Baena

References

[1] K. Gurney,An Introduction to Neural Networks, Routledge, NewYork, NY, USA, 1997.

[2] S. Haykin, Neural Networks: A Comprehensive Foundation,Prentice Hall, Upper Saddle River, NJ, USA, 1999.

[3] T. Masters, Practical Neural Network Recipes in C++, AcademicPress, New York, NY, USA, 1993.

[4] D. Goldberg, Genetic Algorithms in Search, Optimization, andMachine Learning, Addison-Wesley, New York, NY, USA, 1989.

[5] L. A. Zadeh, “Fuzzy sets,” Information and Computation, vol. 8,pp. 338–353, 1965.

[6] L. A. Zadeh, “Fuzzy algorithms,” Information and Computation,vol. 12, no. 2, pp. 94–102, 1968.

Page 3: Editorial Computational Intelligence Techniques in Medicinedownloads.hindawi.com/journals/cmmm/2015/196976.pdf · 2019-07-31 · Editorial Computational Intelligence Techniques in

Submit your manuscripts athttp://www.hindawi.com

Stem CellsInternational

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

MEDIATORSINFLAMMATION

of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Behavioural Neurology

EndocrinologyInternational Journal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Disease Markers

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

BioMed Research International

OncologyJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Oxidative Medicine and Cellular Longevity

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

PPAR Research

The Scientific World JournalHindawi Publishing Corporation http://www.hindawi.com Volume 2014

Immunology ResearchHindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Journal of

ObesityJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Computational and Mathematical Methods in Medicine

OphthalmologyJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Diabetes ResearchJournal of

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Research and TreatmentAIDS

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Gastroenterology Research and Practice

Hindawi Publishing Corporationhttp://www.hindawi.com Volume 2014

Parkinson’s Disease

Evidence-Based Complementary and Alternative Medicine

Volume 2014Hindawi Publishing Corporationhttp://www.hindawi.com