• Complain

Lakshmi P. V. - Computational Intelligence Techniques in Health Care

Here you can read online Lakshmi P. V. - Computational Intelligence Techniques in Health Care full text of the book (entire story) in english for free. Download pdf and epub, get meaning, cover and reviews about this ebook. City: Singapore, year: 2016, publisher: Springer Singapore, genre: Home and family. Description of the work, (preface) as well as reviews are available. Best literature library LitArk.com created for fans of good reading and offers a wide selection of genres:

Romance novel Science fiction Adventure Detective Science History Home and family Prose Art Politics Computer Non-fiction Religion Business Children Humor

Choose a favorite category and find really read worthwhile books. Enjoy immersion in the world of imagination, feel the emotions of the characters or learn something new for yourself, make an fascinating discovery.

Lakshmi P. V. Computational Intelligence Techniques in Health Care

Computational Intelligence Techniques in Health Care: summary, description and annotation

We offer to read an annotation, description, summary or preface (depends on what the author of the book "Computational Intelligence Techniques in Health Care" wrote himself). If you haven't found the necessary information about the book — write in the comments, we will try to find it.

This book presents research on emerging computational intelligence techniques and tools, with a particular focus on new trends and applications in health care. Healthcare is a multi-faceted domain, which incorporates advanced decision-making, remote monitoring, healthcare logistics, operational excellence and modern information systems. In recent years, the use of computational intelligence methods to address the scale and the complexity of the problems in healthcare has been investigated. This book discusses various computational intelligence methods that are implemented in applications in different areas of healthcare. It includes contributions by practitioners, technology developers and solution providers.;Bioinformatics, genomics and diabetes -- Coralyne targets proteases involved cancer progression: An InSilico study -- Computational Intelligence Approach for Prediction Of Breast Cancer Using Particle Swarm Optimization: A Comparative Study Of The Results With Reduced Set Of Attributes -- QSAR and validation analysis on MMP-13 Inhibitors -- Detection of Lesion in Mammogram Images using Differential Evolution based Automatic Fuzzy Clustering -- Sequence Alignment By Advanced Differential Evolutionary Algorithm (ADE) -- Swarm Intelligence and Variable Precision Rough Set Model: A Hybrid Approach for Classification -- Ayush To Kidney (Atok) Data Science Model for Diagnosis and to Advice Through an Expert System.

Lakshmi P. V.: author's other books


Who wrote Computational Intelligence Techniques in Health Care? Find out the surname, the name of the author of the book and a list of all author's works by series.

Computational Intelligence Techniques in Health Care — read online for free the complete book (whole text) full work

Below is the text of the book, divided by pages. System saving the place of the last page read, allows you to conveniently read the book "Computational Intelligence Techniques in Health Care" online for free, without having to search again every time where you left off. Put a bookmark, and you can go to the page where you finished reading at any time.

Light

Font size:

Reset

Interval:

Bookmark:

Make
The Author(s) 2016
P.V. Lakshmi , Wengang Zhou and P Satheesh (eds.) Computational Intelligence Techniques in Health Care SpringerBriefs in Applied Sciences and Technology 10.1007/978-981-10-0308-0_1
1. Bioinformatics, Genomics and Diabetes
Gumpeny Ramachandra Sridhar 1 and Gumpeny Lakshmi 1
(1)
Endocrine and Diabetes Centre, 15-12-15 Krishnanagar, Visakhapatnam, 530 002, India
Gumpeny Ramachandra Sridhar
Email:
Abstract
Bioinformatic analysis has been a key in unraveling the genetic basis of diabetes mellitus, which figured predominantly among target diseases for research after the human genome project. Despite extensive research the genetic contribution using current methods explains less than 10 % of predisposition. Data from next generation sequencing is bound to alter diagnosis, pathogenesis and treatment targets. Insight into the fine genetic architecture allows a fine grained classification of the diabetes spectrum, allowing primary preventive methods in at-risk individuals. In this quest the role of computational, statistical and pattern recognition would play increasingly major roles.
1.1 Introduction
Diabetes mellitus is a metabolic disorder with increasing prevalence the world over. It accounts for substantial disability death, economic and socioeconomic loss. It results from an imbalance between the need and availability in the body for insulin, a protein hormone secreted by cells of pancreas. There is a complex interaction of genetic factors, environment and lifestyle in the expression of the disease. Extensive work on the genetic basis has generated enormous data, which in the current state explains for only a minor part of its cause. Next generation technologies applied to diabetes is providing insights to the elaborate checks and balances in normal physiology, whose disturbances result in susceptibility to and expression of diabetes. A number of hitherto unexplored regulatory factors such as regulatory RNA, epigenetic influences and microbiota found in the gut have come to the forefront in the cause and course of this disease.
1.2 Background
Diabetes, with a worldwide prevalence of 382 million people in 2013 is projected to nearly double that figure by 2035 [].
Diabetes mellitus is broadly classified into Type 1 diabetes , which often presents in the young as a result of pancreatic cell loss. It is characterized by insulin deficiency and circulating autoimmune markers such as antibodies to glutamic acid dehydrogenase. The proportion of people with type 1 diabetes is less, ranging from 2 to 20 %. Heritability was explained up to 80 % by genetic factors, principally HLA class II alleles, other loci encompassing insulin gene, CTLA4, PTPN22, and interleukin 2 receptor [].
Type 2 diabetes mellitus , which is more common, presents in adulthood, although obesity and sedentary lifestyle have seen children presenting with type 2 diabetes mellitus. The largest number of type 2 diabetes subjects are reported from China and from India [].
Latent autoimmune diabetes in adults is also referred to as LADA. It has features of both type 1 and type 2 diabetes: GAD antibodies are found circulating in adults first diagnosed after the age of 35. They do not require insulin for glycemic control during the first six months of diagnosis. Since GAD antibodies are not routinely measured, a number of these cases are undiagnosed and clubbed under type 2 diabetes mellitus.
Maturity - onset - diabetes in the young or MODY is a monogenic form of diabetes. A number of genetic causes were identified, and the number is increasing. Individuals with MODY are diagnosed usually below 25 years. More than 200 mutations are described involving GCK (MODY2), HNF1A (MODY3) and PDX1 genes [].
Maternally inherited diabetes and deafness (MIDD) results from a mutation in the mitochondrial DNA (A3242G mutation). Derived from the mother, it is transmitted maternally. Other neurological abnormalities may accompany diabetes and deafness.
Neonatal diabetes mellitus has been limited to diabetes with first onset at birth or before the first six months of birth. It may be transient or permanent. A number of genetic mutations were reported (KCJN11, SUR1, GCKm INS), which can be diagnosed only by genetic sequencing. A proper diagnosis is crucial, because they may respond to sulfonylurea drugs given orally, and may not require insulin injections [].
Gestational diabetes mellitus is defined when diabetes is first identified during pregnancy. Secondary forms of diabetes result from other endocrine or pancreatic diseases.
1.3 Genetics and Heritability of Type 2 Diabetes
There has for long been evidence for genetic basis in subjects with type 2 diabetes: monozygotic twins have a nearly 70 % concordance of diabetes compared to dizygotic twins. Studies on the genetic basis for type 2 diabetes ranged from linkage studies to candidate gene studies, culminating in the genome wide association studies (GWAS); the last has to date provided the most extensive data, which, however is not yet translatable to clinical care [].
Linkage analysis is used in the search for putative genes responsible for diabetes. A rough location of the gene is looked for, in relation to a DNA sequence called a genetic marker, which is another known sequence of DNA. Using this method, gene coding for the protein calpain 10 (CAPN10) was identified on chromosome 10. As a prelude to other loci to be identified, the calpain 10 was a protease which had no well known functions in the metabolism of glucose. However replications studies of the gene were largely unsuccessful. Variants in the TCF7L2 intronic variant (rs7903146) has been the most consistently replicated genetic association with type 2 diabetes [].
Candidate gene studies . Greater success was obtained with PPARG gene, which was associated with type 2 diabetes mellitus. A number of studies have replicated the association. A variant, expressed in the adipose tissue showed increased transcription, improved insulin sensitivity and was protective against type 2 diabetes [].
Genome wide association studies ( GWAS ) scale up markers for genetic susceptibility with improved power and resolution. They are not yet employed in routine clinical care, and even if they would be, one must consider whether necessary time, financial and computational resources and expertise are available. In an ideal scenario, the genome sequencing consists of the complete base sequence for all chromosomes in an individual.
In the shotgun sequencing method, DNA of interest is cut into small fragments randomly; next computer algorithms are employed to put back the sequence reads back into longer stretches, which needs adequate overlap obtained by deeper sequencing. The scaffolds, obtained after joining together of contigs from the initial assembly are in turn joined into linkage groups or are placed on chromosomes. Intensive computational methods are applied in analysis.
GWAS for diabetes are used to evaluate variability of genomes with susceptibility to diabetes using either data that is either population-based or family-based []. But these studies were limited by the difficulty in interpreting the results and by the low proportion of heritability that could be accounted for by these markers.
In GWAS of diabetes mellitus, unbiased interrogation of millions of common variants associated with the disease, without restricting to known or suspected genes was carried out [].
Further, a meta-analysis comprising more than 50,000 subjects including both European and non-European cohorts was performed [].
A meta-analysis of GWAS (24,488 cases, 83,964 controls) was done among subjects with ancestry from Europe, East Asia, South Asia, Mexico and Mexico-America []. In this large cohort, there was an excess in directional consistency of T2D risk alleles. Seven novel T2D susceptibility loci were identified, which improved with fine-mapping resolution.
Next page
Light

Font size:

Reset

Interval:

Bookmark:

Make

Similar books «Computational Intelligence Techniques in Health Care»

Look at similar books to Computational Intelligence Techniques in Health Care. We have selected literature similar in name and meaning in the hope of providing readers with more options to find new, interesting, not yet read works.


Reviews about «Computational Intelligence Techniques in Health Care»

Discussion, reviews of the book Computational Intelligence Techniques in Health Care and just readers' own opinions. Leave your comments, write what you think about the work, its meaning or the main characters. Specify what exactly you liked and what you didn't like, and why you think so.