Dissertations / Theses on the topic 'Diagnostic/pronostic'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Diagnostic/pronostic.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Soualhi, Abdenour. "Du diagnostic au pronostic de pannes des entraînements électriques." Thesis, Lyon 1, 2013. http://www.theses.fr/2013LYO10146/document.
Full textFaults diagnosis and prognosis of electrical drives play a key role in the reliability and safety of production tools especially in key sectors (military, aviation, aerospace and nuclear, etc.). The research presented in this thesis aims to introduce new methods for faults diagnosis and prognosis of an induction motors and roller bearings. These methods use measured data collected from sensors placed on the system (induction motor, roller) in order to construct a feature vector which indicates the state of the system. Supervised and unsupervised classification methods are developed to classify measurements (observations) described by the feature vector compared to known or unknown operating modes, with or without failures. Defects were created in the rotor and the bearing of the induction motor, fed by a voltage inverter. The unsupervised classification technique, based on artificial ant-clustering, allows analyzing the unknown and unexplored observations to highlight classes with similar observations. This allows improving the classification and the detection of new operating modes. The supervised classification, based on hidden Markov models, allows associating a degree of similarity when we affect an observation to one or more classes. This defines a reliability index which allows the detection of new operating modes. These methods are not limited to diagnose faults; they can also contribute to the prognosis of faults. Indeed, the prognosis can be defined as an extension of the problem of diagnosis. The prognosis of faults is carried out by three methods based on hidden Markov models for the detection of an impending failure and by two methods based on the neuro-fuzzy system (ANFIS for Adaptive Neuro fuzzy Inference System and the neo-fuzzy neuron) to estimate the remaining time before its appearance. A set of historical data collected on roller bearings is used to validate the proposed methods. The obtained results show the effectiveness of the proposed methods for faults diagnosis and prognosis of electrical drives
Ribot, Pauline. "Vers l'intégration diagnostic/pronostic pour la maintenance des systèmes complexes." Phd thesis, Université Paul Sabatier - Toulouse III, 2009. http://tel.archives-ouvertes.fr/tel-00450835.
Full textHassan, Ali Mohamed. "Couplage diagnostic pronostic pour la maintenance prévisionnelle des systèmes photovoltaïques." Thesis, Amiens, 2018. http://www.theses.fr/2018AMIE0016.
Full textIn this work, we have developed a method of coupling a model-based diagnostic process with a prognostic process derived from the experience using an OSA-CBM (Open System Architecture for Condition Based Maintenance) architecture. For that, the 2M7P model of the photovoltaic cell is optimized by the implementation of a metaheuristic method of extraction of seven parameters, FodPSO. This optimization makes it possible to better reproduce cell's performance, especially under actual operating conditions. The diagnostic approach is treated by quantifying the differential residual using Euclidean distance in order to characterize electrical signatures of five targeted faults. The knowledge of faults signatures allows detection and discrimination. The prognostic part evolves since a first approach resulting from models of degradation of Pan and Monroe on the one hand and Vazquez et al. on the other hand towards a reliability analysis approach based on experience. The coupling proposed in this work consists of an exchange of information between the two diagnostic and prognostic processes for decision support according to an architecture where decisions are made by means of a threshold test on the selected indicator, the Corrected performance Ratio. Information is returned to the user on last layer of the OSA-CBM architecture. All approaches have been validated with experimental data from different plants (UPJV Platform, Catania University…)
Hassan, Ali Mohamed. "Couplage diagnostic pronostic pour la maintenance prévisionnelle des systèmes photovoltaïques." Electronic Thesis or Diss., Amiens, 2018. http://www.theses.fr/2018AMIE0016.
Full textIn this work, we have developed a method of coupling a model-based diagnostic process with a prognostic process derived from the experience using an OSA-CBM (Open System Architecture for Condition Based Maintenance) architecture. For that, the 2M7P model of the photovoltaic cell is optimized by the implementation of a metaheuristic method of extraction of seven parameters, FodPSO. This optimization makes it possible to better reproduce cell's performance, especially under actual operating conditions. The diagnostic approach is treated by quantifying the differential residual using Euclidean distance in order to characterize electrical signatures of five targeted faults. The knowledge of faults signatures allows detection and discrimination. The prognostic part evolves since a first approach resulting from models of degradation of Pan and Monroe on the one hand and Vazquez et al. on the other hand towards a reliability analysis approach based on experience. The coupling proposed in this work consists of an exchange of information between the two diagnostic and prognostic processes for decision support according to an architecture where decisions are made by means of a threshold test on the selected indicator, the Corrected performance Ratio. Information is returned to the user on last layer of the OSA-CBM architecture. All approaches have been validated with experimental data from different plants (UPJV Platform, Catania University…)
Ghaye, Benoît. "La Maladie thromboembolique pulmonaire aigue: diagnostic et pronostic par tomodensitométrie hélicoïdale." Doctoral thesis, Universite Libre de Bruxelles, 2015. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209051.
Full textDoctorat en Sciences médicales
info:eu-repo/semantics/nonPublished
Diez, Lledo Edouard. "Diagnostic et Pronostic de défaillances dans des composants d'un moteur d'avion." Phd thesis, Université Paul Sabatier - Toulouse III, 2008. http://tel.archives-ouvertes.fr/tel-00319675.
Full textMailles, Alexandra. "Epidémiologie, optimisation du diagnostic et pronostic des encéphalites infectieuses en France." Thesis, Grenoble, 2012. http://www.theses.fr/2012GRENV001.
Full textAbstract Background Despite a better knowledge about pathophysiological mechanisms and the generalisation of molecular biological Tools, the aetiology of encephalitis is still undetermined in most cases. Their incidence, the short-term and long-term prognosis of the disease and the persistence of sequelae are unknown. The objectives of this work were to improve the knowledge about the aetiology of encephalitis in France and to describe the patients hospitalized in France with encephalitis according to clinical, biological, demographic, epidemiological and outcome data. Methods Patients aged 28 days or more, who fitted the case definition, were enrolled in 2007. The investigation of aetiological diagnosis was carried out according to a previously defined diagnosis strategy. Epidemiological, clinical and biological data were collected using standardised questionnaires on admission, on day 5 of hospitalisation and on discharge. The study was carried out in accordance with French regulations. The long-term outcome of patients was assessed in 2010. Data collected encompassed persisting symptoms, resuming leisure activities, return to wok or resuming education and quality of life. Cognitive decline was assessed with patients' relatives using IQCODE. The main outcome measure was the Glasgow outcome scale (GOS). Results 253 patients presenting with acute encephalitis were included. A causative agent was identified for 131 (52%) of them. Most frequent causative agents were Herpes simplex virus (HSV, n=55), Varicella Zoster virus (VZV, n=20), Mycobacterium tuberculosis (n=20) and Listeria monocytogenes (n=13). Twenty-six patients (10%), died during hospitalisation. In 2010, 176 patients could be included and assessed. The outcome of encephalitis was favourable for 61% of patients and 39% had a poor outcome. Among patient employed before onset of encephalitis, 24% had not returned to work at the time of evaluation. Patients who presented with herpes encephalitis in 2007 had a lower score on GOS than other patients. Discussion Our study resulted in a important improvement of the proportion of encephalitis with a causative agent identified. We demonstrated that bacteria play a significant role as causes of encephalitis, and are responsible for most death occurring during the acute stage of encephalitis. An important proportion of patients presented long-term sequelae, illustrating the evolution of encephalitis from an acute infectious disease toward a chronic neurological disease. The high frequency of sequelae following herpes encephalitis is a shadow on the success of aciclovir. Conclusion Considering our results, we can propose recommendation for the everyday management of encephalitis patients, both to achieve aetiological diagnosis and a long-term follow-up that should be extended to all encephalitis patients. Herpes encephalitis should be more studied on pathophysiological aspects to explicate the severity of the disease despite the existence of a specific treatment, and to propose better prevention and management of sequelae
Diez, Lledo Eduard. "Diagnostic et pronostic de défaillances dans des composants d'un moteur d'avion." Toulouse 3, 2008. http://thesesups.ups-tlse.fr/305/.
Full textIn Aeronautics engines and complementary equipments as regulators, actuators, sensors,. . . Are the most important. A preliminary study has shown that hydraulic actuators and lubrication system are among the most critical components. In the hydraulic system (turbines CFM56-7 Hispano-Suiza, Groupe Safran), the VSV actuator (Variable Stator Valve) and its regulation loop adapts the geometry of the engine to the particular situation with respect to the power demand during each flight phase. Another point of interest is the oil circuit for lubrication, this subsystem is critical. Diagnosis of the system is the main objective of our work, nevertheless prognostic is also proposed whenever periodic maintenance takes an important place for the full life of the system. The second objective of our study is to coordinate fault detection with prognostic, in order to propose an adaptive maintenance schedule for aircraft engines. The application of the tools developed, are applied on real size, in the framework of TATEM project
Jha, Mayank Shekhar. "Diagnostic et Pronostic de Systèmes Dynamiques Incertains dans un contexte Bond Graph." Thesis, Ecole centrale de Lille, 2015. http://www.theses.fr/2015ECLI0027/document.
Full textThis thesis develops the approaches for diagnostics and prognostics of uncertain dynamic systems in Bond Graph (BG) modeling framework. Firstly, properties of Interval Arithmetic (IA) and BG in Linear Fractional Transformation, are integrated for representation of parametric and measurement uncertainties on an uncertain BG model. Robust fault detection methodology is developed by utilizing the rules of IA for the generation of adaptive interval valued thresholds over the nominal residuals. The method is validated in real time on an uncertain and highly complex steam generator system.Secondly, a novel hybrid prognostic methodology is developed using BG derived Analytical Redundancy Relationships and Particle Filtering algorithms. Estimations of the current state of health of a system parameter and the associated hidden parameters are achieved in probabilistic terms. Prediction of the Remaining Useful Life (RUL) of the system parameter is also achieved in probabilistic terms. The associated uncertainties arising out of noisy measurements, environmental conditions etc. are effectively managed to produce a reliable prediction of RUL with suitable confidence bounds. The method is validated in real time on an uncertain mechatronic system.Thirdly, the prognostic methodology is validated and implemented on the electrical electro-chemical subsystem of an industrial Proton Exchange Membrane Fuel Cell. A BG of the latter is utilized which is suited for diagnostics and prognostics. The hybrid prognostic methodology is validated, involving real degradation data sets
Occelli, Céline. "Approche métabolomique pour l'identification de marqueurs diagnostiques et pronostiques dans la COVID-19." Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ6009.
Full textSevere acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been the source of a global pandemic with high morbidity and mortality, and has had a major socio-economic impact, as well as on the healthcare system. Coronavirus 2019 disease (COVID-19) has a very broad clinical spectrum, from the asymptomatic form to Acute Respiratory Distress Syndrome and multivisceral failure, both of which can lead to death, reflecting a complex pathophysiology, the understanding of which is still improving. In this context, the challenge for clinicians is to be able to quickly identify patients with COVID-19 and stratify the risk of poor clinical outcome. Metabolomics is a omic approach that enables dynamic analysis of molecular changes in response to disease at the individual level. Through metabolic profiling and phenotyping, it enables the identification of biomarkers and the metabolic pathways impacted. The aim of this work was to identify diagnostic and prognostic plasma and urine metabolomic signatures of COVID-19 and to analyze the metabolic pathways affected.In our first study, based on a non-targeted metabolomics analysis approach on plasma samples from COVID-19-infected subjects and healthy volunteers, we identified robust diagnostic and prognostic plasma metabolomic signatures, mainly involving changes in plasma lipid and amino acid levels. Especially, we found high levels of unsaturated lipids and low levels of saturated lipids in the plasma of infected subjects. We also identified novel plasma biomarkers for SARSCoV-2 infection and disease severity as deoxy-fructosyl-amino acids, and confirmed the impact of the kynurenine pathway in these signatures.In our second study, based on non-targeted metabolomic analysis of urinary samples, we also found robust diagnostic and prognostic urinary metabolomic signatures, highlighting the impact of urinary amino acid metabolism, purine metabolism, energy metabolism and the kynurenine pathway.Our results confirm the contribution of metabolomics to understanding the pathophysiology of COVID-19, and its interest in finding new diagnostic and prognostic biomarkers for the condition. The identification and, above all, validation of different “metabotypes” specific to the disease, its course and severity could enable us, in addition to developing robust and less invasive diagnostic tests, to predict the risk of poor clinical outcome of an infection such as COVID-19
Feng, Gang. "Etude de nouveaux marqueurs moléculaires pour le diagnostic précoce et le pronostic des cancers." Phd thesis, Université Jean Monnet - Saint-Etienne, 2010. http://tel.archives-ouvertes.fr/tel-00672376.
Full textMoarii, Matahi. "Apprentissage de données génomiques multiples pour le diagnostic et le pronostic du cancer." Thesis, Paris, ENMP, 2015. http://www.theses.fr/2015ENMP0086/document.
Full textSeveral initiatives have been launched recently to investigate the molecular characterisation of large cohorts of human cancers with various high-throughput technologies in order to understanding the major biological alterations related to tumorogenesis. The information measured include gene expression, mutations, copy-number variations, as well as epigenetic signals such as DNA methylation. Large consortiums such as “The Cancer Genome Atlas” (TCGA) have already gathered publicly thousands of cancerous and non-cancerous samples. We contribute in this thesis in the statistical analysis of the relationship between the different biological sources, the validation and/or large scale generalisation of biological phenomenon using an integrative analysis of genetic and epigenetic data.Firstly, we show the role of DNA methylation as a surrogate biomarker of clonality between cells which would allow for a powerful clinical tool for to elaborate appropriate treatments for specific patients with breast cancer relapses.In addition, we developed systematic statistical analyses to assess the significance of DNA methylation variations on gene expression regulation. We highlight the importance of adding prior knowledge to tackle the small number of samples in comparison with the number of variables. In return, we show the potential of bioinformatics to infer new interesting biological hypotheses.Finally, we tackle the existence of the universal biological phenomenon related to the hypermethylator phenotype. Here, we adapt regression techniques using the similarity between the different prediction tasks to obtain robust genetic predictive signatures common to all cancers and that allow for a better prediction accuracy.In conclusion, we highlight the importance of a biological and computational collaboration in order to establish appropriate methods to the current issues in bioinformatics that will in turn provide new biological insights
Barake, Samih Hicham. "Intérêt de la biopsie endomyocardique dans le diagnostic et le pronostic des myocardites." Clermont-Ferrand 1, 1987. http://www.theses.fr/1987CLF13021.
Full textLOCHET, GOARANT SYLVIE. "Diagnostic et pronostic de la toxoplasmose congenitale : etude de 107 seroconversions pendant la grossesse." Rennes 1, 1992. http://www.theses.fr/1992REN1M059.
Full textDievart, Mickaël. "Architectures de diagnostic et de pronostic distribuées de systèmes techniques complexes de grande dimension." Thesis, Toulouse, INPT, 2010. http://www.theses.fr/2010INPT0063/document.
Full textIn this dissertation, various architectures for the control and the monitoring of Large Scale Complex Technical Systems (LSCTS) are discussed. The problematic of condition-based maintenance and health status assessment is defined. A diagnostic and prognostic typology is presented leading to the assessment of the health status of LSCTSs. Decentralized diagnosis studies are discussed then the contributions of the ICT and of the distributed technologies for the diagnosis are presented. Thereafter, the distributed diagnosis and works relative to this kind of deployments are introduced. The limits of the centralized and decentralized diagnosis approaches are presented. Then the centralized approaches are compared to the distributed ones. Information and/or knowledge that support the diagnosis and the prognosis as well as their modeling in order to exploit them are described and formalized. A characterization is proposed for the different status of a component can be in. Requirements are described for the monitoring layer of the LSCTSs are described in order to implement the proposed diagnosis and prognosis principles that are then specified by the means of algorithms. Eventually, a health assessment method of the LSCTSs is also proposed. Several deployments can be considered to implement the health assessment of the LSCTSs. A simulation platform, which was developed to evaluate the performances of the centralized and the distributed deployments, is presented. Among the purposes of the platform, one is to behave as the monitoring layer of a LSCTS. A use case is proposed for two deployments and their performances are compared
Ruet, Aurélie. "Prédiction du diagnostic et du pronostic aux stades précoces de la Sclérose en Plaques." Thesis, Bordeaux 2, 2012. http://www.theses.fr/2012BOR21952/document.
Full textMultiple sclerosis (MS) is the most frequent chronic, disabling, non-traumatic neurologic disease of young adults in France. Relapsing-remitting MS (RRMS) is the most frequent phenotype of this disease. The diagnosis of RRMS is based on the demonstration of the dissemination of lesions in space and time after a first typical clinical event, which is called a clinically isolated syndrome (CIS). The 2 main objectives of this thesis were, first, to investigate predictors of an early diagnosis of MS after a typical CIS and, second, to provide support for cognitive impairment as a potentially useful prognostic marker in the early stages of MS. The first article reported the results obtained in a retrospective study that included a homogeneous sample of 114 patients with a spinal cord CIS. The diagnosis of MS was predicted by 3 independent factors: ≤40 years of age, positive for oligoclonal bands in the cerebrospinal fluid or a raised IgG index, and ≥3 periventricular lesions at the time of the CIS. In the second article, a confirmation of the validity of these 3 predictive factors was provided through a large prospective study that included 652 patients with a CIS, regardless of the anatomical location of the lesions. Notably, these predictive factors achieved the same accuracy as the dissemination in space criteria which were proposed in the McDonald criteria for the prediction of the diagnosis of MS. Once an MS diagnosis is established, the main challenge is to assess the severity of the disease, and early clinical predictors of long-term disability are still lacking. The anatomical substrate of the disabilities that are accumulated in MS appears primarily to be cumulative axonal loss. Cognitive impairment is frequent in MS, even at the early stages of the disease, and has been associated with MRI markers of diffuse brain damage. Therefore, cognitive impairment appears to be an interesting candidate as a prognostic factor in the early stages of MS. In the third article, the relationship between cognitive impairment and MRI parameters reflecting early diffuse brain damage was confirmed in a 7-year longitudinal study of 44 newly diagnosed RRMS patients. In the fourth article, the ability of the cognitive impairment detected after RRMS diagnosis in this sample of patients to predict the progression of disability over time supported the prognostic value of cognitive deficits in early MS. In the fifth article, cognitive assessments were performed on patients with 2 clinical phenotypes of MS with different prognoses: RRMS and primary progressive MS (PPMS). The extent and the severity of cognitive deficits were greater in the 41 PPMS patients compared to the 60 RRMS patients; this finding supports the relationship between cognitive impairment and widespread brain damage. In the sixth article, the prognostic value of cognitive dysfunction in MS was illustrated through the negative impacts of cognitive deficits on the qualities of life and vocational statuses of 48 patients living with MS who were followed for 7 years. Finally, as cognitive deficits were shown to have the potential to predict early disability in patients with MS, and early disability is known to be relevant to predict long-term disability in MS, the detection of cognitive deficits appears to be a priority in managing patients with MS and adapting early-stage therapeutic strategies. Information processing speed (IPS) is the main cognitive domain impaired in MS that has clinical implications. In the seventh article, the ability of a new, in-house cognitive tool called the computerised speed cognitive test to detect lowered processing speed was assessed in a validation study using samples obtained from 101 patients with MS and 415 healthy subjects. This test was clinically relevant, and had excellent reliability, ecological validity, and predictive value for detecting IPS impairment in patients with MS
Ingels, Alexandre. "Développement de techniques d’imageries pour le diagnostic et le pronostic des tumeurs du rein." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS451/document.
Full textThe aim of this project is the development of new imaging techniques for renal cancer diagnostic and treatment.We have assessed several techniques including optical coherence tomography and molecular imaging. We assessed a series of potential markers for molecular imaging by measuring some pre-defined markers expressions by immunohistochemistry in renal cell carcinoma and their association with disease’s prognostic. Finally, we assessed two molecular imaging techniques in pre-clinical models: Molecular Magnetic Resonance Imaging and Molecular Ultrasound Imaging
Nguile, Makao Molière. "Pneumonies nosocomiales acquises sous ventilation mécanique : prédiction du diagnostic et influence sur le pronostic." Phd thesis, Grenoble, 2010. http://www.theses.fr/2010GRENM073.
Full textNosocomial Pneumonia is the most frequent and severe infection encountered in intensive care unit, notably in patients under mechanical ventilation. The objective of this thesis is to develop tools to optimize the prevention of Ventilation Associated nosocomial Pneumonias (VAP) using the information of OUTCOMEREA database. Thus, a VAP score was built from a hierarchical logistic regression mixed model to compare the care structures. As the logistic regression model presenting a few shortcomings, we oriented our work towards multi-state models. In particular, we studied the Progressive Disability model from which the attributable mortality due to VAP was evaluated efficiently and patients groups with bad prognosis were identified. This model has been simplified to a Disability model. Thereafter, the covariates were included via the Breslow estimator and the mortality was re-estimated. From the Disability model, a global and individualized prediction of VAP in the three days following observation time was built. The prediction performance is evaluated by a loss function weighted by events frequency over time
Nguile, Makao Molière. "Pneumonies nosocomiales acquises sous ventilation mécanique : prédiction du diagnostic et influence sur le pronostic." Phd thesis, Grenoble, 2010. http://tel.archives-ouvertes.fr/tel-00538779.
Full textRIHET, STEPHANE. "Diagnostic et pronostic des lesions de bas grade du col uterin liees aux papillomavirus humains." Amiens, 1997. http://www.theses.fr/1997AMIE0102.
Full textNze, Ossima Arnaud Davin. "Evaluation statistique des outils diagnostiques et pronostiques à l'aide des surfaces ROC." Thesis, Montpellier 1, 2014. http://www.theses.fr/2014MON1T005/document.
Full textIn diagnostic medical, the receiver operating characteristic (ROC) surface is the statistical tool used to assess the accuracy of a diagnostic test in discriminating three disease states, and the volume under the ROC surface is the used index for the quantification of the performance of the test. In some situations, various factors can affect the test results and subsequently the accuracy measures. In the case of longitudinal studies, the patient's status may change over time. In this manuscript, we developed statistical methods to assess the discriminatory capabilities of diagnostic and pronostic tools. We first proposed a semiparametric method for estimating ROC surface under density ratio models. The construction of the proposed method is based on the adjacent-category logit model and the empirical likelihood approach. We described the bootstrap method for inference of the obtained estimators. Next, we presented a method for estimating ROC surfaces called Lehmann family ROC surfaces. This method is based on the family of Lehmann alternatives or proportional hazards model. It has the advantage of taking into account covariates that may affect the accuracy of a diagnostic test. Moreover, we have developed a covariate-specific ROC surface based on the Bayes rule. For that, we proposed semiparametric estimator for covariate-specific ROC surfaces via polytomous logistic regression procedures and a semiparametric location model. Finally, in the case where patient's status may evolve through different stages of disease a method of time-dependent ROC surfaces was developed. The proposed estimator uses the "Inverse Probability of Censoring Weighting" (IPCW) approach. Simulations and examples are provided to illustrate the performance of the proposed estimators
Seronde, Marie-France. "Facteurs diagnostiques et pronostiques dans l'insuffisance cardiaque aiguë." Thesis, Besançon, 2013. http://www.theses.fr/2013BESA3009/document.
Full textHeart failure (HF) is highly prevalent disease, and prevalence increases with age. HF is generally discovered on presentation of an acute episode of decompensation (or insufficiency). Acute decompensated heart failure (ADHF) is very frequent in elderly subjects and is difficult to diagnose when the patient is admitted with acute dyspnoea. The advent of plasma biomarkers, such as BNP or NT-proBNP represents a major advancement in the diagnostic of ADHF. ADHF leads to high rates of re-admission and mortality. The objectives of this doctoral thesis were: (1) to describe the epidemiology of ADHF in France in a one-day observational study of admissions for ADHF in 170 French hospitals; (2) to evaluate the prognostic and diagnostic value of natriuretic peptides (NPs) in ADHF; (3) to describe the extent of post-transcriptional modifications in these NPs in ADHF; and (4) to search for new biomarkers.The comparison of the prognostic and diagnostic properties of NPs showed that the 4 commercially available NPs (namely BNP, NT-proBNP, proBNP and MR-proANP) overall have very similar prognostic and diagnostic abilities. However, proBNP and BNP seem to be more useful for diagnosis, while MR-proANP appears to be better for the association with 5-year mortality.Amongthe post-transcriptional modifications of BNP, we studied the impact of glycosylation of pro¬BNP. Threonin 71 0-glycosylation prevents cleavage of proBNP into BNP and NT-proBNP, resulting in the release of proBNP from the cell without being cleaved. Conversely, non-glycosylated proBNP is cleaved into BNP and NT-proBNP by corin or furin. We showed that non-glycosylation of proBNP and activation of furin are two important mechanisms in the acceleration of production of NPs during ADHF. We also showed that production of NT-proBNP was more closely linked to the rate of glycosylation of proBNP than to the production of BNP. Thus, our results strongly suggest that NT-proBNP should be used in future studies exploring the concept of "biomarker-guided therapy" in ADHF.To investigate new biomarkers, we explored plasma concentrations of 5 microRNAs (miR-l/-21/-23/-126/-423-5p), in patients with acute dyspnoea. None of these microRNAs were shown to have any diagnostic value. Conversely, miR-423-5p appears to be a prognostic marker for re-admission at 1 year. Secondly, we investigated the consequences of cardiac congestion on the liver. The hepatic markers studied were alkaline phosphatise and transaminases. Markers of cholestasis were associated with hepatic congestive while markers of cellular necrosis (transaminases) were related to arterial hypertension and low cardiac output. An increase in transaminases was associated with various criteria of excess mortality in the short term
Ammour, Rabah. "Contribution au diagnostic et pronostic des systèmes à évènements discrets temporisés par réseaux de Petri stochastiques." Thesis, Normandie, 2017. http://www.theses.fr/2017NORMLH21/document.
Full textDue to the increasing complexity of systems and to the limitation of sensors number, developing monitoring methods is a main issue. This PhD thesis deals with the fault diagnosis and prognosis of timed Discrete Event Systems (DES). For that purpose, partially observed stochastic Petri nets are used to model the system. The model represents both the nominal and faulty behaviors of the system and characterizes the uncertainty on the occurrence of events as random variables with exponential distributions. It also considers partial measurements of both markings and events to represent the sensors of the system. Our main contribution is to exploit the timed information, namely the dates of the measurements for the fault diagnosis and prognosis of DES. From the proposed model and collected measurements, the behaviors of the system that are consistent with those measurements are obtained. Based on the event dates, our approach consists in evaluating the probabilities of the consistent behaviors. The probability of faults occurrences is obtained as a consequence. When a fault is detected, a method to estimate its occurrence date is proposed. From the probability of the consistent trajectories, a state estimation is deduced. The future possible behaviors of the system, from the current state, are considered in order to achieve fault prediction. This prognosis result is extended to estimate the remaining useful life as a time interval. Finally, a case study representing a sorting system is proposed to show the applicability of the developed methods
Raposo, Nicolas. "Apport des nouveaux biomarqueurs sur la physiopathologie, le diagnostic et le pronostic de l'angiopathie amyloïde cérébrale." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30340.
Full textSporadic cerebral amyloid angiopathy (CAA) is a common cerebral small vessel disease with growing interest among clinicians and researchers. CAA occurs frequently in elderly subjects and is a major and increasing cause of intracerebral hemorrhage and dementia. Over the last several years, important advances have been made in this research field, with the development of new biomarkers for the disease, thanks to advances in structural, functional and molecular neuroimaging. Anti-amyloid therapies are currently in development and clinical trial assessing anticoagulant strategy in these patients are ongoing, raising the perspective of future treatments. Hence, evaluating these new biomarkers of CAA seems particularly important. The main objective of this PhD thesis was to get insights into novel neuroimaging biomarkers and their potential clinical applications in patients with CAA. We conducted 6 clinical research studies exploring new hemorrhagic (cortical superficial siderosis, convexity subarachnoid hemorrhage) and non-hemorrhagic (enlarged perivascular spaces, amyloid PET, brain network connectivity) markers of the disease. Biomarkers are evaluated as diagnostic tools and their clinical relevance, as prognostic markers are investigated
Justino, Joana. "Autoanticorps dans la glomérulonéphrite extra-membraneuse associée à PLA2R1 : épitopes, immunodominance et implication clinique." Electronic Thesis or Diss., Université Côte d'Azur (ComUE), 2019. http://theses.univ-cotedazur.fr/2019AZUR6028.
Full textMembranous Nephropathy (MN) is a rare (1.2/100,000 new cases per year) but severe autoimmune kidney disease. It is also a common cause of nephrotic syndrome in adults. The clinical outcome of patients is complex and variable, going from spontaneous remission to end-stage renal disease (ESRD), with persistent high levels of proteinuria. Despite international KDIGO recommendations, MN treatment remains highly controversial and challenging. Better biomarkers are needed to identify patients at risk of severe disease, orient treatment decision and predict response to therapy.From the pathophysiological point of view, MN is characterized by the formation of immune complex deposits at the glomerular basement membrane leading to podocyte injury and proteinuria. A major breakthrough was the identification of the phospholipase A2 receptor 1 (PLA2R1) as the main autoantigen of MN for about 70% of the patients, followed by the identification of thrombospondin–type 1 domain containing 7A (THSD7A) as a second autoantigen in another group of 2-5% of patients. These discoveries not only gave a new molecular basis to better understand MN pathogenesis but also rapidly provided clinical assays to diagnose MN and monitor disease activity. Anti–PLA2R1 titers correlate with disease activity and have a prognostic value. Another major discovery was the identification of three distinct epitope-containing domains in PLA2R1-associated MN: CysR, CTLD1 and CTLD7. The severity of the disease and poor clinical outcome were found to be associated with multiple autoantibodies targeting these domains. These antibodies are likely produced by a mechanism of epitope spreading.PLA2R1 is a 180 kDa glycosylated transmembrane receptor with a large extracellular region comprising 10 distinct domains: a cysteine-rich domain (CysR), a fibronectin type II domain (FnII) and eight different C-type lectin-like domains (CTLDs). PLA2R1 binds sPLA2 and inhibits their enzymatic activity, thereby playing a role in immune and inflammatory conditions. PLA2R1 may also act as a tumor suppressor in cancer. However, its biological function in podocytes is largely unknown.The major aim of my thesis was to characterize the full set of PLA2R1 epitopes, and analyze their clinical relevance, in particular as predictors of clinical outcome and response to treatment. Using different molecular and cellular biology techniques, we have demonstrated that patients’ autoantibodies can recognize multiple epitopes in up to 5 of the 10 PLA2R1 domains. Further screening of a cohort of 142 PLA2R1-associated MN patients by ELISA, with each of the 10 individual domains of PLA2R1 indicated different prevalence towards each domain. In this cohort, anti-PLA2R1 titer and epitope positivity appear as relevant biomarkers to predict clinical outcome and response to treatment. We also identified the CysR and CTLD1 domains as two alternative immunodominant epitope-domains, suggesting that the driving force of the autoimmune response may progress towards two different pathways. Of potential clinical interest, patients with a CysR versus CTLD1 immunodominance had different response to treatment and clinical outcome. Together, this work provides a better understanding of the trajectory of the PLA2R1 autoimmune response within the pathogenesis of PLA2R1–associated MN, and might contribute to the development of specific diagnosis tests towards more personalized medicine
Gaudel, Quentin. "Approche intégrée de diagnostic et de pronostic pour la gestion de santé des systèmes hybrides sous incertitude." Thesis, Toulouse, INSA, 2016. http://www.theses.fr/2016ISAT0019/document.
Full textThis study takes place in the field of system health management, which aims at developing maintenance aid tools, but also at improving the systems autonomous decision-making in case of failures. In this context, diagnostic techniques determine whether and why the system is down, while prognostic techniques determine when failures will occur and their consequences. If they seem to be correlated, they are usually studied separately because the time scales manipulated by the two processes are very different. This work aims at developing a tool that integrates both diagnosis and prognosis methods for the monitoring of hybrid systems, whose dynamics are both continuous and discrete. The proposed methodology, based on hybrid particle Petri nets, is applied to a planetary rover to demonstrate its usability in real cases through the management of knowledge-based and data-based uncertainty
Daher, Alaa. "Diagnostic et pronostic des défauts pour la maintenance préventive et prédictive. Application à une colonne de distillation." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMR090/document.
Full textThe distillation process is largely used in many applications such a petrochemical production, natural gas processing, and petroleum refineries, etc. Usually, maintenance of the chemical reactors is very costly and it disrupts production for long periods of time. All these factors really demonstrate the fundamental need for effective fault diagnosis and prognostic strategies that they are able to reduce and avoid the greatest number of thes problems and disasters. The first part of our work aims to propose a reliable diagnostic method that can be used in the steady-state regime of a nonlinear procedure. Moreover, we propose a modified procedure of the fuzzy c-means clustering method (MFCM) where MFCM calculates the percentage variation between the two clustered classes. The purpose of using MFCM is to reduce the computing time and increase the performance of the classifier. The results of the proposed method confirm the ability to classify between normal mode and eight abnormal modes of faults. Our second goal aims to propose a prognosis reliable method used to estimate the degradation path of a distillation column and calculate the lifetime percentage of this system. The work presents an approach based on adaptive neuro-fuzzy inference system (ANFIS) combined with (FCM) to predict the future path and calculate the lifetime percentage of the system. The results obtained demonstrate the validity of the proposed technique to achieve the needed objectives with a high-level accuracy. To improve ANFIS performance we propose Parzen windows distribution as a new membership function for ANFIS algorithm. Results demonstrated the importance of the proposed technique since it proved to be highly successful in terms of reducing the time consumed. Additionally, Parzen windows had the smallest Root Mean Square Error (RMSE). The last part of this thesis was focusing on the proposing of new algorithm which can be applied to obtain real-time monitoring system which relies on the fault production module to reach the diagnosis module in contrast to the previous strategies ; this means this method predict the future state of the system then diagnosis what is the probable fault source. This proposed method has proven to be a reliable process that can evaluate the degradation of a distillation column and subsequently diagnose the possible faults or accidents that can emerge as a result of the estimated degradation. This new approach combines the benefits of ANFIS with the benefits of feedforward ANN. The results were demonstrated that the technique achieved with a high level of accuracy, the objective of prediction and diagnosis especially when applied to the data obtained from automated distillation process in the chemical industry
Piaton, Eric. "Place de la cytologie dans l'évaluation diagnostique et pronostique de la glande prostatique." Lyon 1, 1990. http://www.theses.fr/1990LYO1T234.
Full textAlma, Marjorie. "Intérêt de l'échocardiographie aux urgences." Montpellier 1, 2001. http://www.theses.fr/2001MON11023.
Full textVERON, BERNARD ISABELLE. "Apport de l'echographie et de la biochimie dans le diagnostic et le pronostic des uropathies detectees in utero." Lyon 1, 1991. http://www.theses.fr/1991LYO1M309.
Full textSoyeur, Luc. "Les marqueurs urinaires des tumeurs urothéliales : place du CYFRA 21-1." Bordeaux 2, 2001. http://www.theses.fr/2001BOR23021.
Full textBarutaut, Manon Anne. "Découverte et validation de nouveaux biomarqueurs de l'insuffisance cardiaque." Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30127.
Full textCardiovascular diseases are a major concern for human health. According to the health word organization (HWO), they are the first cause of mortality. They can progress into heart failure, which is the inability of the heart to supply enough oxygen quantity for all the organs. There is no cure for heart failure, treatments more and more performing are developed to take care of symptoms, improve quality of life and stop the progression of the disease. Research is heading toward innovative therapies, like stimulating cardiomyocytes regeneration or gene therapy. A biomarker is defined as "a characteristic measured objectively and evaluated as a marker of biological, physiological, pathological processes or therapeutic response". Heart failure biomarkers are commonly used, mainly under circulating form. Several studies established their efficiency (diagnostic, prognostic, therapeutic adjustment) and their limitations (limited specificity, variability...). Discovery of new biomarkers aims to find performing molecules without those limitations. Our team has access to several cohorts of heart failure patients, our cohort (IBLOMAVED) recruited with our partnership with the cardiology unit of Toulouse University hospital and other cohorts furnished by partner teams. We use a screening approach (urinary proteome with CE-MS) to discover new biomarkers for heart failure. We identified a potential target, Insulin-like growth factor binding protein 2 (IGFBP2). I studied diagnostic and prognostic capacity of IGFBP2 in our cohorts. I participated to clinical trials with known heart failure biomarkers (Galectin-3 and sST2) in order to respond to new problematics. I also worked with transgenic mice over expressing IGFBP2 in the heart to obtain data on the possible role of IGFBP2 in the physiopathology of heart failure. The study of the apolipoprotein O (APOO) is a major research topic of the team. APOO is up-regulated in the heart during obesity or diabetes and participates to physio pathological mechanisms taking place in the heart in response to stress. The results showed a correlation between APOO function and the regulation of lipid metabolism, apoptosis and autophagy. These processes are involved in the development of heart failure, which suggests that APOO is as a potential biomarker. We intend to test/validate the diagnostic or prognostic capacity of APOO in our cohorts. We will continue our clinical trials with IGFBP2, by example investigating the prognostic capacity according to the etiology of heart failure or to the treatments received by the patients. With a prospective study, we could validate the usefulness of serial measurements of IGFBP2 for therapeutic adjustment. Novel models for fundamental research (mice, cell lines) will be used to get more information about the physio pathological role of IGFBP2
Razavi, Darius. "Contribution à l'étude des facteurs psychologiques et psychopathologiques associés au diagnostic, au traitement et au pronostic des affections cancéreuses." Doctoral thesis, Universite Libre de Bruxelles, 1994. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/212645.
Full textDecaestecker, Christine. "Développements méthodologiques pour la classification de données réelles. Application à l'aide au diagnostic et au pronostic de tumeurs gliales." Doctoral thesis, Universite Libre de Bruxelles, 1997. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/212173.
Full textBäumler, Antoine. "Gestion de l'énergie basée sur le diagnostic/pronostic de défaut d'un véhicule électrique hybride à pile à combustible/batterie." Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPAST113.
Full textThe concept of hybrid energy systems have considerably improved dynamic performance, energy efficiency and lifespan of energetic systems, which is very promising for the powertrain system in electrified vehicles. Especially the effectiveness of hybrid system based on polymer electrolyte membrane fuel cells (PEMFCs) and lithium-ion batteries (LIBs) has been highlighted by many research projects in recent years. In such system, energy management strategy (EMS) plays a critical role in the supervisory level. It manage the power flow among the different power sources, to meet the power demand and to improve the operation efficiency. A smart EMS should be supported by reliable diagnostic/prognostic results of the single power source. Namely, the topic of diagnostic/prognostic of PEMFCs and LIBs is indispensable when designing a health-conscious EMS. However, the current research work of designing EMS and executing diagnostic/prognostic of ESS is usually independent of each other. Therefore, in this PhD project, integrating the diagnosis/prognosis module of each power source into EMS design is the primary aim. Especially, the proposed health-aware EMS and the module of diagnostic/prognostic will be based on artificial intelligence techniques through operation data self-learning process
Duranton, Flore. "Histoire naturelle de la maladie rénale : Analyse des facteurs physiopathologiques et évaluation pronostique de l’insuffisance rénale terminale et de ses complications." Thesis, Montpellier 1, 2013. http://www.theses.fr/2013MON1T022/document.
Full textChronic kidney disease (CKD) and end-stage renal disease (ESRD) are associated with various complications, many of which occur within the internal environment: uremia, anemia, hyperparathyroidism, uremic retention… Plasma urea concentrations have long been used as a diagnostic criterion of CKD, despite the absence of some key characteristics. We discussed these features with regards to the historical uses of urea determinations. It is essential to characterize the plasma changes which occur in CKD to understand the disease and the relationship with comorbidities. We expanded our focus to all of uremic retention solutes, and identified 56 new solutes from recently published clinical studies. The study of plasma and urinary concentrations of amino acids and their association with CKD stage and complications further extended the study of CKD diagnosis, and allowed to generate hypotheses on the metabolic origin of these alterations. On the other hand, by meta-analysis, we showed a reduced risk of death in patients treated with vitamin D derivatives. Correcting comorbidities (hypovitaminosis, disturbances of bone and mineral metabolism) and other renoprotective effects may explain these benefits. Finally, the determination of the urinary proteome and the resulting CKD273 score was proved to be very useful for identifying patients at risk of progression, which is a public health issue. This work based on clinical research and literature analyses is part of an effort to improve the characterization of CKD and the evaluation of progression in order to avoid complications. It is the basis for a wider observational project: analyzing the characteristics of CKD patients and their changes over time
Benoist, Guillaume. "Infection congénitale par le CMV : apport des modèles expérimentaux et étude des facteurs pronostiques anténataux." Caen, 2012. http://www.theses.fr/2012CAEN3133.
Full textHuman cytomegalovirus (CMV) is part of the herpesviridae family. The perinatal infection that can result from this virus is the leading infectious cause of congenital malformation, mental retardation and deafness. About half the pregnant women in France are not immune to CMV. Vertical transmission of CMV is about 30%. Current resources enable doctors to diagnose CMV infection in pregnant women as well as in the fetus and newborn. Prognostic factors for CMV fetal infection are poorly understood. We were able to demonstrate the prognostic value of fetal blood sampling by showing that fetal thrombocytopenia was an independent predictor of symptomatic CMV infection and have confirmed the strong prognostic value of the existence of fetal ultrasound abnormalities. Furthermore, we demonstrated the benefit of practicing magnetic resonance imaging of the fetal brain in addition to an ultrasound examination in order to determine fetal brain abnormalities. These data enable us to refine and determining the prognosis of infected fetuses. We also assessed the replicative capacity of CMV strain AD169 on transformed cells extravillous cytotrophoblast HIPEC65. We have shown that CMV has a complete replicative cycle in this line that appears at least as permissive as the MRC5 cell system used for comparison, during the first week of culture. These results are original and show that this system is certainly very interesting to study the characteristics of placental infection with CMV
Dallet, Emmanuelle. "Hernie diaphragmatique congénitale : intérêt de l'échographie anténatale dans l'évaluation du pronostic, apport nouveau de l'IRM." Bordeaux 2, 2000. http://www.theses.fr/2000BOR23014.
Full textBressel, Mathieu. "Modélisation raphique pour le pronostic robuste de pile à combustible à membrane échangeuse de proton." Thesis, Lille 1, 2016. http://www.theses.fr/2016LIL10119/document.
Full textThe fuel cell (FC) is at present the alternative solution to the fossil fuels the most promising. It is however advisable to improve its reliability. This requires the implementation of algorithms capable of estimating in real time the state of health and forecasting its remaining useful life (prognostics). The methods of prognostics based on a physical model offer precise results once they do not requiring either learning or expertise of the operator. However, the problem for a FC system lies in the coupling of several physical phenomena, the uncertainty of the parameters of the model and the low instrumentation of the FC stack.Thus, we use uncertain models based on the Bond Graph tool well adapted for the FC. Concretely, the parameters uncertainties are integrated in the model of evolution of the powers which is used for the detection of the beginning of the aging and the estimation of the degradation of the FC based on the causal and structural properties of the model. The generated model of degradation is used by an extended Kalman filter which allows the estimation of the state of health , the dynamics of the aging and the quantification of the uncertainty for any operating condition (of temperature, current and pressure). An Inverse First Order Reliability Method is then used for the prediction of the remaining useful life and the inherent uncertainty. The global method was validated on various sets of experimental data. Thanks to this set of tools, a control based on the inversion of an Energetic Macroscopic Representation (EMR) model with time varying parameters, robust to aging is developed based on the state of health estimation
Ramakers, Michel. "Intérêt du dosage du cyfra 21. 1 dans les cancers bronchiques : étude portant sur 80 dossiers." Caen, 1994. http://www.theses.fr/1994CAEN3082.
Full textDupuy, Renée-Pierre. "Les épanchements péricérébraux du nourrisson : diagnostic, étude clinique, échographique et tomodensitométrique, risques évolutifs et pronostic : à propos de 171 cas." Montpellier 1, 1990. http://www.theses.fr/1990MON11067.
Full textCONAN, CHEVILLOTTE GWENAELLE. "Les masses abdomino-pelviennes de l'enfant : epidemiologie, diagnostic et pronostic ; a propos de 112 cas observes en milieu chirurgical pediatrique." Angers, 1990. http://www.theses.fr/1990ANGE1002.
Full textVinson, Garance. "Développement d'une méthode commune de diagnostic et pronostic basée sur un cadre formel de modélisation génériqueApplication à un module électro-hydrostatique aéronautique." Toulouse 3, 2014. http://www.theses.fr/2014TOU30143.
Full textThe aviation industry is a changing market where demands on the equipment are high, and competition is fierce among manufacturers. Therefore cost reduction, quality, reliability, operational availability and dependability become the cornerstone of this industry. One of the levers that can support manufacturers to make their products more attractive for airlines is the optimization of maintenance. A way to achieve this is health-monitoring. In order to provide the integration of diagnosis and prognosis in one same method, this thesis proposes a formal approach of health-monitoring. One of the aims is to help in the optimization of maintenance operation. The method is based on a generic modeling framework. This framework represents the behavior of any complex system at a given time, and the evolution of its health over time depending on the stress it undergoes. The model summarizes the information needed for both diagnosis and prognosis. The diagnosis provides a good knowledge of all the damages and faults present in the components of the system, and any associated losses of performance and failures. From the result of diagnosis, the prognosis allows the prediction of the future health state of the system and the deduction of the nature and the times of occurrence of future possible failures. Performance metrics in the diagnosis and prognosis, as well as uncertainties related to prognosis, are discussed and integrated in the formal approach. The chosen application is the motor-pump of an electro-hydrostatic actuator, a technology pushed by Messier-Bugatti-Dowty to meet the needs of future all-electric aircrafts. The process of monitoring the health state focuses on two critical elements: a synchronous permanent magnet machine and a hydraulic pump. The application shows the feasibility of health-monitoring, and highlights the problems that should be treated in the future to obtain, in particular, realistic aging laws
Irinopoulou, Theano. "L'apport de l'analyse d'images bidimensionnelle et tridimensionnelle dans le diagnostic des pathologies de la prostate et le pronostic individuel des patients." Paris 7, 1995. http://www.theses.fr/1995PA077038.
Full textVincent, Sylvie. "Intérêts des gènes à homéodomaines PAX-6 et Engrailed-2 dans le diagnostic et le pronostic des tumeurs neuroectodermiques primitives humaines." Lille 1, 2003. https://ori-nuxeo.univ-lille1.fr/nuxeo/site/esupversions/cdf25b11-a440-48c3-866f-6005820f1805.
Full textGuigal, Pierre-Michel. "Modélisation de la propagation infectieuse dans un réseau organise d'individus : apport de la prétopologie et de la géometrie fractale." Lyon, INSA, 1995. http://www.theses.fr/1995ISAL0064.
Full textThis report deals with forecast and diagnosis modelling of a disease wich spread is intimately linked to the population organisation. According to some hypothesis, we bring to the fore that the characteristics of susceptibility (defined as local relations) give raise to a kind of global organisation in the population. This characteristic forms a main factor in forecasting. Scrapie in sheep give us a concrete support for this approach. The pretopological theory allows us to design a simplified model of the population organisation and suggests that a scale law may structure a network of local relations. This property leads to look for a self similar process in the clusters consitution. We implement pattern recognition methods based on syntax to design a model of cluster constitution on a network of local relations. This on reveals the self similarity property wich allows us to formulate the aim of analysis in the frame of fractal geometry. An adaptation of the Zifp-Mandelbrot law to hierarchic organisation of the local relations enable us to propose a parametric method of anlaysis. We use these results in a new kind of compartmental model that give an analytic representation of the complex phenomena of spreak in a network. In order to validate this synthetic approach of complex spreak in a network, we propose a cellular automaton for simulation of local events as relation and spread. We obtain similar results by the two ways. This result suggests that the synthetic approach is operative
CHRETIEN, OLIVIER. "La neurone-specifique enolase : un marqueur tumoral utile pour le diagnostic, la surveillance et le pronostic des carcinomes bronchiques a petites cellules." Angers, 1989. http://www.theses.fr/1989ANGE1015.
Full textJose, Sagar. "Stratégies d'apprentissage multimodal pour le diagnostic et le pronostic de la santé des machines industrielles dans un contexte de manque de données." Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSEP093.
Full textPrognostics and Health Management (PHM) with data-driven techniques is heavily dependent upon the availability of extensive and high-quality datasets, a requirement often challenging to fulfill in industrial condition monitoring environments. This discrepancy creates a significant gap between state-of-the-art PHM methodologies and their practical application in real-world scenarios. The prevailing focus in data-driven PHM research on unimodal datasets highlights the potential of multimodal data to bridge this gap.This thesis explores the integration of multimodal data to advance PHM models for industrial machines. It systematically addresses pivotal challenges such as data missingness and noise, sparse and irregular datasets, class imbalance, and the scarcity of run-to-failure data. The research develops innovative methodologies that incorporate multiple data modalities and harness domain-specific expertise to create robust predictive models.The primary contributions of this research include:1. Cross-modal attention-based learning: A new multimodal learning method is designed to mitigate the limitations posed by missing and noisy data. It allows integrating information across multiple modalities, thereby enhancing the accuracy and robustness of predictive models.2. Expert-knowledge-assisted multimodal diagnostics methodology: This methodology combines domain expertise with multimodal learning to enable comprehensive diagnostics, thereby improving fault detection and classification in industrial machinery.3. Graph-based prognostics approach: This innovative approach constructs run-to-failure trajectories from incomplete data using graph-based techniques, offering a significant advancement in failure prognostics.These methodologies were rigorously validated using both simulation and industrial dataset of hydrogenerators, demonstrating significant improvements in PHM and predictive maintenance capabilities. The results underscore the potential of multimodal data to significantly enhance the reliability and efficiency of PHM methods and algorithms.This thesis proposes a comprehensive framework for leveraging diverse data sources and domain expertise, promising to transform maintenance strategies and reducing operational costs across various industries. The findings pave the way for future research and practical implementations, positioning multimodal data integration as a pivotal advancement in the field of PHM
Shahin, Kamrul. "Modèle graphique probabiliste appliqué au diagnostic de l'état de santé des systèmes, au pronostic et à l'estimation de la durée de vie résiduelle." Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0129.
Full textThis thesis contributes to prognosis and health management for assessing health condition of complex systems. In the context of operational management and operational safety of systems, we propose to investigate how Dynamic Probabilistic Graphical Modelling (DPGM) can be used to diagnose the current health state of systems, prognostic the future health state, and the evolution of degradation, as well as estimate its remaining useful life based on its operating conditions. System degradation is generally unknown and requires shutting down the system to be observed. However, this is difficult or even impossible during system operation. Though, a set of observable quantities on a system or component can characterise the level of degradation and help to estimate the remaining useful life of components and systems. The DPGM provides an approach suitable for modelling the evolution of the health state of systems and components. The aim of this thesis is to transpose and capitalize on the experience of these previous works in a prognostic context on the basis of a more efficient DPGM taking into account the available knowledge on the system. We extend the classical HMM family models to the IOHMM to allow the time propagation of uncertainty to address prognostic problems. This research includes the extension of learning and inference algorithms. Variants of the HMM model are proposed to incorporate the operating environment into the prognosis. The aim of this thesis is to contribute to solving the following scientific locks: - Considering the state of health whatever the complexity of the system by a stochastic model and learning the model parameters from the available measurements on the system. - Establish a diagnosis of the state of health of the system and the prognosis of its evolution by integrating several operational conditions. - Estimate the remaining useful life of components and structured systems with series and parallel components. This is a major challenge because the prognosis of the degradation of system components makes it possible to define strategies for either control or maintenance in relation to the residual life of the system. This allows the reduction of the probability of occurrence of a shutdown due to a system malfunction either by adjusting the degradation speed to fit in with a preventive maintenance plan or by proactively planning maintenance interventions
Leroy, Mélanie. "Contribution des bases de données de soin courant à l’amélioration du diagnostic et du pronostic de la maladie d’Alzheimer et des dégénérescences lobaires frontotemporales." Electronic Thesis or Diss., Université de Lille (2018-2021), 2021. http://www.theses.fr/2021LILUS026.
Full textBiomarkers, whether cerebrospinal fluid (CSF), magnetic resonance imaging (MRI), or positional emission tomography (PET), have acquired a prominent place in the diagnostic process of a cognitive disorder. They are an integral part of the diagnostic criteria for Alzheimer's disease (AD) and its main differential diagnosis, frontotemporal dementia (FTD). In 2021, however, histological analysis, where pathological changes are observed directly on tissues, often remains the only method allowing a diagnosis of certainty.In 1992, the Lille Memory Resource and Research Center (CMRR) set up a network of memory consultations in the Nord Pas-de-Calais region. In addition to standardizing care, it has set up a database that now includes over 120,000 patients. Based on this large active file, our work consisted in studying the clinical and biochemical characteristics of AD and FTD patients on different scales (rare but perfectly characterized cases of clinicopathological correlations, monocentric cohorts of patients having undergone lumbar puncture, regional or international cohorts).Our first study focused on the correlations between the biochemical profile of cerebrospinal fluid (CSF) and post-mortem findings. We were able to show that amyloid and tau biomarkers are less sensitive to the corresponding pathologies when these are not yet fully developed in the cortex, leading to incomplete detection of patients with AD-related neuropathological changes.We subsequently focused on AD patients with pathological tau and pTau biomarkers in the CSF, pathological Aβ42/Aβ40 ratio, but normal Aβ42 levels. We showed that the cognitive, morphological, and functional profile of patients with AD and normal Aβ42 does not differ from those with pathological Aβ42.In the setting of FTD, CSF biomarkers are used to rule out a possible diagnosis of AD. Nevertheless, if this is the case, a whole spectrum of pathology remains possible as FTD is so heterogeneous. There are currently few established phenotype-pathology correlations, which, at the dawn of the development of a targeted treatment, may represent a loss of chance for these patients. We wished to constitute a multicentric cohort of patients with confirmed post-mortem FTD, in order to improve clinicopathological correlations. This preliminary work demonstrates the complexity of the FTD spectrum, with many phenotypic and histological overlaps.In addition to this study of gold standard FTD patients, we wished to consider the entire FTD active file of the Nord Pas-de-Calais memory consultation network. Although this disease is rare, the pooling of data within the network allowed us to reach a large number of patients. This work allowed us to demonstrate that FTD differs from AD, both in terms of initial characteristics, speed of progression and treatment. Despite the use of the latest clinical criteria, these pathologies remain under-diagnosed and should no longer be considered as limited to young subjects.Although each memory center, individually, is in a position to contribute to the advancement of science and to help better understand neurodegenerative diseases, it seems obvious at this time that the pooling of health data is indispensable. Within the framework of the European Human Brain Project, we have worked on the implementation of a federated data analysis tool. The Medical Informatics Platform allows complex analyses to be carried out from geographically distant databases, thus avoiding transfers and the risk of health data leaks between research centers.Data from routine care is abundant and contains a lot of information. It is up to us to make the most of it to advance our understanding of neurocognitive diseases, a challenge for the years to come