Les réseaux de neurones un outil de sélection de variables : Le cas des facteurs de risque de la maladie du cancer du sein

Ce papier utilise les réseaux de neurones avec un algorithme incrémental comme outil de sélection des facteurs de risques les plus pertinents dans la maladie du cancer du sein. Les résultats témoignent de la pertinence de l’approche neuronale avec un algorithme incrémentale dans ce domaine de recherche. A partir d’un échantillon de 248 patientes atteintes par cette maladie, il nous a été possible de déterminer la combinaison optimale des facteurs permettant d’atteindre une bonne performance prédictive du type de tumeur maligne et bénigne.

Conception d'un outil informatique basé sur un réseau de neurones artificiels pour la classification automatique des stades du sommeil

L’objectif de notre travail est de développer un outil d’analyse automatique des stades du sommeil basé sur les réseaux de neurones artificiels (RNA). Dans ce papier nous présentons notre démarche pour la conception de cet outil. La première difficulté consiste dans le choix de la représentation des signaux physiologiques et en particulier de l’électroencéphalogramme (EEG). Une fois la représentation adoptée, l’étape suivante est la conception du réseau de neurones optimal déterminé par un processus d’apprentissage et de validation sur les données issues d’un ensemble d'enregistrements de nuits de sommeil. Le résultat obtenu avec un taux de 63% de bonne classification pour six stades, nous incite à approfondir l’étude de cette problématique aux niveaux représentation et conception pour améliorer les performances de notre outil.

Entrevue avec Sylvain Barthélémy et Laurent Bougrain

Les questions de cette interview sont posées à Sylvain Barthélémy et Laurent Bougrain par les organisateurs du colloque international « Les applications des réseaux de neurones en économie, finance, management et environnement », Chtourou Nouri, Feki Rochdi et Bazin Damien. Ce colloque, organisé par l’Ecole Supérieure de Commerce de Sfax, s’est déroulé en juin 2011 aux Iles Kerkennah, en Tunisie.

Genetic testing with primary prevention and moral hazard

We develop a model where a free genetic test reveals whether the individual tested has a low or high probability of developing a disease. A costly prevention effort allows high-risk agents to decrease the probability of developing the disease. Agents are not obliged to take the test, but must disclose its results to insurers. Insurers offer separating contracts which take into account the individual risk, so that taking the test is associated to a discrimination risk. We study the individual decisions to take the test and to undertake the prevention effort as a function of the effort cost and of its e¢ ciency. We obtain that, if effort is observable by insurers, agents undertake the test only if the effort cost is neither too large nor too low. If the effort cost is not observable by insurers, they face a moral hazard problem which induces them to under-provide insurance. We obtain the counterintuitive result that moral hazard increases the value of the test if the effort cost is low enough. Also, agents may perform the test for lower levels of prevention e¢ ciency when effort is not observable

Attitudes towards and beliefs about genetic testing in the haemophilia community: a qualitative study

Widespread genetic testing for haemophilia has recently been introduced in Victoria, Australia. While attitudes towards predictive testing have been studied in other conditions, such as cancer, there is limited knowledge about the attitudes of members of the haemophilia community towards predictive testing. This study aimed at exploring attitudes towards, and beliefs about, genetic testing amongst members of the haemophilia community in Victoria prior to the widespread introduction of testing. The study was qualitative and descriptive. In-depth face to face interviews were held with a sample of 39 individuals, including men with haemophilia, female carriers and family members. Data were analysed thematically using cross-case analysis techniques. There was considerable knowledge about the proposed introduction of widespread genetic testing. However, not everyone thought that testing was accessible or user friendly, and there was confusion about who needed to be tested. Most thought that testing was necessary for adolescent girls to determine carrier status to help prepare families for a child with haemophilia, rather than leading them to choose to terminate a pregnancy or not to have children. A minority of women stated that if there was a history of inhibitors in a family then a termination might be considered. The study revealed strong religious beliefs among those studied, which may have influenced attitudes and approaches towards testing. Further investigation is needed into how people with a possible haemophilia genotype negotiate decisions about their further identification, and how this knowledge is placed within cultural, religious and family contexts.

Molecular analysis of the Von Hippel-Lindau (VHL) gene in a family with non-syndromic pheochromocytoma: the importance of genetic testing

Dois pacientes índices da família analisada neste estudo foram submetidos a adrenalectomia bilateral devido a feocromocitoma. Foi, então, realizado o estudo genético dos pacientes e de sete parentes de primeiro grau. Os dois pacientes com feocromocitoma e dois outros membros assintomáticos da família apresentaram a mutação c496G>T no exon 3 do gene VHL. A família perdeu seguimento médico. Três anos após a realização da avaliação genética, a irmã dos pacientes, portadora da mutação, foi encaminhada para o nosso serviço após uma gestação complicada por pré-eclampsia. Ela referia paroxismos sugestivos de feocromocitoma, mas as metanefrinas urinárias eram negativas. Entretanto, a tomografia computadorizada de abdômen evidenciou uma massa adrenal que também se contrastou na cintilografia com metaiodobenzilguanidina (MIBG). Esse estudo mostra que a análise molecular do paciente índice pode levar à identificação de parentes assintomáticos portadores da mutação. Além disso, mesmo com as metanefrinas urinárias negativas, a identificação de uma mutação específica levou a um aumento da suspeita e detecção de feocromocitoma na irmã dos afetados pela doença.

A rigorous approach to facilitate and guarantee the correctness of the genetic testing management in human genome information systems

Abstract Background Recent medical and biological technology advances have stimulated the development of new testing systems that have been providing huge, varied amounts of molecular and clinical data. Growing data volumes pose significant challenges for information processing systems in research centers. Additionally, the routines of genomics laboratory are typically characterized by high parallelism in testing and constant procedure changes. Results This paper describes a formal approach to address this challenge through the implementation of a genetic testing management system applied to human genome laboratory. We introduced the Human Genome Research Center Information System (CEGH) in Brazil, a system that is able to support constant changes in human genome testing and can provide patients updated results based on the most recent and validated genetic knowledge. Our approach uses a common repository for process planning to ensure reusability, specification, instantiation, monitoring, and execution of processes, which are defined using a relational database and rigorous control flow specifications based on process algebra (ACP). The main difference between our approach and related works is that we were able to join two important aspects: 1) process scalability achieved through relational database implementation, and 2) correctness of processes using process algebra. Furthermore, the software allows end users to define genetic testing without requiring any knowledge about business process notation or process algebra. Conclusions This paper presents the CEGH information system that is a Laboratory Information Management System (LIMS) based on a formal framework to support genetic testing management for Mendelian disorder studies. We have proved the feasibility and showed usability benefits of a rigorous approach that is able to specify, validate, and perform genetic testing using easy end user interfaces.

[Early genetic testing in nephrology - a diagnostic aid in ambiguous clinical situations]

Despite a growing number of identified genetic causes of monogenetic disorders, early molecular testing is rarely applied in daily nephrologic practice. In selected cases and to answer specific questions, molecular testing however can be helpful for the specialist. The future significance of genetic testing most likely lies in the area of individual risk profiling for polygenetic disorders. The basis for this testing however has yet to be established.

Analysis of mRNA transcripts improves the success rate of molecular genetic testing in OTC deficiency

BACKGROUND: Ornithine transcarbamylase (OTC) deficiency is the most common inborn error of urea metabolism that can lead to hyperammonemic crises and orotic aciduria. To date, a total of 341 causative mutations within the OTC gene have been described. However, in about 20% of the patients with enzymatically confirmed OTC deficiency no mutation can be detected when sequencing of genomic DNA analyzing exons and adjacent intronic segments of the OTC gene is performed. METHODS: Standard genomic DNA analysis of the OTC gene in five consecutive patients from five families revealed no mutation. Hence, liver tissue was obtained by needle sampling or open biopsy and RNA extracted from liver was analyzed. RESULTS: Complex rearrangements of the OTC transcript (three insertions and two deletions) were found in all five patients. CONCLUSION: In patients with a strong suspicion of OTC deficiency despite normal results of sequencing exonic regions of the OTC gene, characterization of liver OTC mRNA is highly effective in resolving the genotype. Liver tissue sampling by needle aspiration allows for both enzymatic analysis and RNA based diagnostics of OTC deficiency.

Mental health and quality of life after genetic testing for Huntington disease: a long-term effect study in Germany

Predictive genetic testing for Huntington disease (HD) might cause severe short-term psychological reactions in patients with poor mental health. Very few studies exist on the long-term effects of genetic HD testing. The aim of this study was to assess mental health and quality of life in persons who were tested for HD mutation, to compare mental health depending on the result of the genetic test (non-carriers, gene carriers, and patients with HD) and to identify predictors of mental health and quality of life via linear regression. The data were collected by self-report questionnaires. In total, 121 individuals participated in this study: 52 were non-carriers, 54 were gene carriers, and 15 were gene carriers suffering from HD. Non-carriers and gene carriers showed better mental health and quality of life than HD-patients but did not differ from each other. In non-carriers four variables predicted increased depression and low mental quality of life: low perceived social support, no intimate relationship, female sex and younger age. For gene carriers three predictors were found: low perceived social support, the expectation of an unfavorable genetic test result before the testing procedure and being childless. To prevent detrimental effects of HD testing on mental health and mental quality of life, specific attention should be paid to persons with limited social networks during genetic counseling. Assessment of expectations related to the test result and mental health prior to a genetic testing procedure may help to identify gene carriers at risk of poor coping after an unfavorable test result.

Refining abacavir hypersensitivity diagnoses using a structured clinical assessment and genetic testing in the Swiss HIV Cohort Study

BACKGROUND: We aimed to assess the value of a structured clinical assessment and genetic testing for refining the diagnosis of abacavir hypersensitivity reactions (ABC-HSRs) in a routine clinical setting. METHODS: We performed a diagnostic reassessment using a structured patient chart review in individuals who had stopped ABC because of suspected HSR. Two HIV physicians blinded to the human leukocyte antigen (HLA) typing results independently classified these individuals on a scale between 3 (ABC-HSR highly likely) and -3 (ABC-HSR highly unlikely). Scoring was based on symptoms, onset of symptoms and comedication use. Patients were classified as clinically likely (mean score > or =2), uncertain (mean score > or = -1 and < or = 1) and unlikely (mean score < or = -2). HLA typing was performed using sequence-based methods. RESULTS: From 131 reassessed individuals, 27 (21%) were classified as likely, 43 (33%) as unlikely and 61 (47%) as uncertain ABC-HSR. Of the 131 individuals with suspected ABC-HSR, 31% were HLA-B*5701-positive compared with 1% of 140 ABC-tolerant controls (P < 0.001). HLA-B*5701 carriage rate was higher in individuals with likely ABC-HSR compared with those with uncertain or unlikely ABC-HSR (78%, 30% and 5%, respectively, P < 0.001). Only six (7%) HLA-B*5701-negative individuals were classified as likely HSR after reassessment. CONCLUSIONS: HLA-B*5701 carriage is highly predictive of clinically diagnosed ABC-HSR. The high proportion of HLA-B*5701-negative individuals with minor symptoms among individuals with suspected HSR indicates overdiagnosis of ABC-HSR in the era preceding genetic screening. A structured clinical assessment and genetic testing could reduce the rate of inappropriate ABC discontinuation and identify individuals at high risk for ABC-HSR.

Spectrum and prevalence of mutations involving BrS1- through BrS12-susceptibility genes in a cohort of unrelated patients referred for Brugada syndrome genetic testing: implications for genetic testing

OBJECTIVES The aim of this study was to provide the spectrum and prevalence of mutations in the 12 Brugada syndrome (BrS)-susceptibility genes discovered to date in a single large cohort of unrelated BrS patients. BACKGROUND BrS is a potentially lethal heritable arrhythmia syndrome diagnosed electrocardiographically by coved-type ST-segment elevation in the right precordial leads (V1 to V3; type 1 Brugada electrocardiographic [ECG] pattern) and the presence of a personal/family history of cardiac events. METHODS Using polymerase chain reaction, denaturing high-performance liquid chromatography, and DNA sequencing, comprehensive mutational analysis of BrS1- through BrS12-susceptibility genes was performed in 129 unrelated patients with possible/probable BrS (46 with clinically diagnosed BrS [ECG pattern plus personal/family history of a cardiac event] and 83 with a type 1 BrS ECG pattern only). RESULTS Overall, 27 patients (21%) had a putative pathogenic mutation, absent in 1,400 Caucasian reference alleles, including 21 patients with an SCN5A mutation, 2 with a CACNB2B mutation, and 1 each with a KCNJ8 mutation, a KCND3 mutation, an SCN1Bb mutation, and an HCN4 mutation. The overall mutation yield was 23% in the type 1 BrS ECG pattern-only patients versus 17% in the clinically diagnosed BrS patients and was significantly greater among young men<20 years of age with clinically diagnosed BrS and among patients who had a prolonged PQ interval. CONCLUSIONS We identified putative pathogenic mutations in ∼20% of our BrS cohort, with BrS genes 2 through 12 accounting for <5%. Importantly, the yield was similar between patients with only a type 1 BrS ECG pattern and those with clinically established BrS. The yield approaches 40% for SCN5A-mediated BrS (BrS1) when the PQ interval exceeds 200 ms. Calcium channel-mediated BrS is extremely unlikely in the absence of a short QT interval.

Cardiac channel molecular autopsy: insights from 173 consecutive cases of autopsy-negative sudden unexplained death referred for postmortem genetic testing

OBJECTIVE To perform long QT syndrome and catecholaminergic polymorphic ventricular tachycardia cardiac channel postmortem genetic testing (molecular autopsy) for a large cohort of cases of autopsy-negative sudden unexplained death (SUD). METHODS From September 1, 1998, through October 31, 2010, 173 cases of SUD (106 males; mean ± SD age, 18.4 ± 12.9 years; age range, 1-69 years; 89% white) were referred by medical examiners or coroners for a cardiac channel molecular autopsy. Using polymerase chain reaction, denaturing high-performance liquid chromatography, and DNA sequencing, a comprehensive mutational analysis of the long QT syndrome susceptibility genes (KCNQ1, KCNH2, SCN5A, KCNE1, and KCNE2) and a targeted analysis of the catecholaminergic polymorphic ventricular tachycardia type 1-associated gene (RYR2) were conducted. RESULTS Overall, 45 putative pathogenic mutations absent in 400 to 700 controls were identified in 45 autopsy-negative SUD cases (26.0%). Females had a higher yield (26/67 [38.8%]) than males (19/106 [17.9%]; P<.005). Among SUD cases with exercise-induced death, the yield trended higher among the 1- to 10-year-olds (8/12 [66.7%]) compared with the 11- to 20-year-olds (4/27 [14.8%]; P=.002). In contrast, for those who died during a period of sleep, the 11- to 20-year-olds had a higher yield (9/25 [36.0%]) than the 1- to 10-year-olds (1/24 [4.2%]; P=.01). CONCLUSION Cardiac channel molecular autopsy should be considered in the evaluation of autopsy-negative SUD. Several interesting genotype-phenotype observations may provide insight into the expected yields of postmortem genetic testing for SUD and assist in selecting cases with the greatest potential for mutation discovery and directing genetic testing efforts.

Genetic testing for glucokinase mutations in clinically selected patients with MODY: a worthwhile investment

The differential diagnosis for children with diabetes includes a group of monogenic diabetic disorders known as maturity-onset diabetes of the young (MODY). So far, six underlying gene defects have been identified. The most common subtypes are caused by mutations in the genes encoding the transcription factor HNF-1a (MODY 3) and the glycolytic enzyme glucokinase (GCK) (MODY 2). MODY 2 is the most benign form of diabetes as the threshold for glucose sensing is elevated resulting in mild, regulated hyperglycemia. MODY 2 may usually be treated with diet alone without risk of microvascular complications. Patients with MODY usually present as children or young adults. Genetic testing for MODY in diabetic subjects is often not performed because of the costs and its unavailability in Switzerland. We describe the impact of the genetic analysis for MODY 2 on diabetes management and treatment costs in a five-year-old girl. The patient and her diabetic mother were both found to have a heterozygous missense mutation (V203A) in the glucokinase gene. The five-year-old girl was started on insulin therapy for her diabetes but because her HbA1c remained between 5.8-6.4% (reference 4.1-5.7%) and her clinical presentation suggested MODY insulin was discontinued. She is now well controlled on a carbohydrate controlled diet regimen only. Omission of insulin treatment made regular blood glucose monitoring unnecessary and removed her risk of hypoglycemia. Costs for the genetic analysis were 500 Euro. At our centre costs for diabetes care of a patient with type 1 diabetes are approximately 2050 Euro/year compared to 410 Euro/year for the care of a patient with MODY 2. In addition, a diagnosis of MODY 2 may reassure patients and their families, as microvascular complications are uncommon. Thus there are both health and financial benefits in diagnosing MODY 2. We recommend genetic testing for MODY 2 in clinically selected patients even though this analysis is currently not available in Switzerland and costs are not necessarily covered by the health insurances.