Diagnostic pitfalls: posterior ischemic optic neuropathy mimicking optic neuritis.

In young people, the most frequent cause of isolated monocular visual loss due to an optic neuropathy is optic neuritis. We present the case of a 27 year old woman who presented monocular visual loss, excruciating orbital pain and unusual temporal headache. The initial diagnosis of optic neuritis revealed later to be a posterior ischemic optic neuropathy (PION). In this case, PION was the first unique presentation of a non-traumatic carotid dissection, and it was followed 24h later by an ischemic stroke. Sudden monocular visual loss associated with a new-onset headache are clinical symptoms that should immediately prompt to a carotid dissection.

Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

Impact of the Advisa MRI pacing system on the diagnostic quality of cardiac MR images and contraction patterns of cardiac muscle during scans: Advisa MRI randomized clinical multicenter study results.

BACKGROUND: The Advisa MRI system is designed to safely undergo magnetic resonance imaging (MRI). Its influence on image quality is not well known. OBJECTIVE: To evaluate cardiac magnetic resonance (CMR) image quality and to characterize myocardial contraction patterns by using the Advisa MRI system. METHODS: In this international trial with 35 participating centers, an Advisa MRI system was implanted in 263 patients. Of those, 177 were randomized to the MRI group and 150 underwent MRI scans at the 9-12-week visit. Left ventricular (LV) and right ventricular (RV) cine long-axis steady-state free precession MR images were graded for quality. Signal loss along the implantable pulse generator and leads was measured. The tagging CMR data quality was assessed as the percentage of trackable tagging points on complementary spatial modulation of magnetization acquisitions (n=16) and segmental circumferential fiber shortening was quantified. RESULTS: Of all cine long-axis steady-state free precession acquisitions, 95% of LV and 98% of RV acquisitions were of diagnostic quality, with 84% and 93%, respectively, being of good or excellent quality. Tagging points were trackable from systole into early diastole (360-648 ms after the R-wave) in all segments. During RV pacing, tagging demonstrated a dyssynchronous contraction pattern, which was not observed in nonpaced (n = 4) and right atrial-paced (n = 8) patients. CONCLUSIONS: In the Advisa MRI study, high-quality CMR images for the assessment of cardiac anatomy and function were obtained in most patients with an implantable pacing system. In addition, this study demonstrated the feasibility of acquiring tagging data to study the LV function during pacing.

Un diagnostic de maladie coeliaque peut en cacher un autre [A diagnosis of coeliac disease can hide an alternative diagnosis]

The Common variable Immunodeficiency (CVID) is next to the selective IgA-deficiency the most frequent primary immunodeficiency syndrome. Because of its variable clinical manifestations and age of declaration, CVID can mimic different other pathologies and is therefore frequently diagnosed in a later stage of the disease. However, as a consequence of late diagnosis, irreversible organ damage can have occurred which could have been prevented by early treatment. Therefore, early diagnosis of CVID by the general practitioner in patients with recurrent infections or other typical clinical manifestations is of great importance.

Bilan préopératoire en chirurgie viscérale [Preoperative assessment in visceral surgery]

The purpose of preoperative assessment is to evaluate the patient's health status, to address known or unidentified co-morbidities and to perform adequate complementary exams if necessary. On the other hand, it allows to prepare and protect the patient in order to reduce perioperative risk. The assessment consists of patient's history and physical examination, both focusing on cardiovascular and respiratory assessment. Complementary exams have to be chosen selectively depending on the patient's risk factors and the type of surgery. They are indicated if their result leads to a potential patient's benefit only, either by a modification in anesthetic and/or surgical management or by introduction of a pharmacological strategy, adequate and maximal if necessary, especially for cardioprotection.

Reduction in the use of diagnostic tests in infants with risk factors for early-onset neonatal sepsis does not delay antibiotic treatment.

Despite a low positive predictive value, diagnostic tests such as complete blood count (CBC) and C-reactive protein (CRP) are commonly used to evaluate whether infants with risk factors for early-onset neonatal sepsis (EOS) should be treated with antibiotics. We investigated the impact of implementing a protocol aiming at reducing the number of diagnostic tests in infants with risk factors for EOS in order to compare the diagnostic performance of repeated clinical examination with CBC and CRP measurement. The primary outcome was the time between birth and the first dose of antibiotics in infants treated for suspected EOS. Among the 11,503 infants born at ≥35 weeks during the study period, 222 were treated with antibiotics for suspected EOS. The proportion of infants receiving antibiotics for suspected EOS was 2.1% and 1.7% before and after the change of protocol (p = 0.09). Reduction of diagnostic tests was associated with earlier antibiotic treatment in infants treated for suspected EOS (hazard ratio 1.58; 95% confidence interval [CI] 1.20-2.07; p <0.001), and in infants with neonatal infection (hazard ratio 2.20; 95% CI 1.19-4.06; p = 0.01). There was no difference in the duration of hospital stay nor in the proportion of infants requiring respiratory or cardiovascular support before and after the change of protocol. Reduction of diagnostic tests such as CBC and CRP does not delay initiation of antibiotic treatment in infants with suspected EOS. The importance of clinical examination in infants with risk factors for EOS should be emphasised.

Evaluation de la prise en charge des femmes de plus de 30 ans avec un diagnostic de L-SIL du col de l'utérus en vigueur depuis 2009 au CHUV

Introduction : Les lésions malpighiennes intraépithéliales de bas grade (LSIL) sont un diagnostic rencontré fréquemment lors des frottis de dépistage du cancer du col utérin. Leur prise en charge reste controversée. Au CHUV, avant 2009, un test HPV était effectué chez toutes les femmes avec un diagnostic de L-SIL et seules les patientes avec un test HPV positif pour les hauts risques (HR) étaient adressées en colposcopie. Actuellement, suivant les guidelines européennes de 2006, l'attitude est de faire une colposcopie à toutes les patientes avec un diagnostic initial de L-SIL, sans faire préalablement un test HPV. Cette démarche semble efficiente chez les jeunes patientes, mais pas chez les plus de 30 ans chez qui la prévalence de tests HPV HR positifs est inférieure. Plus de 40% des femmes de plus de 30 ans seraient référées inutilement en colposcopie car elles ne seraient pas infectées par un HPV HR et n'auraient pas de risque d'évolution de leur L-SIL vers une lésion de haut grade. Buts : Comparer les deux différentes prises en charge des femmes de plus de 30 ans présentant un diagnostic de L-SIL, soit celle qui était en vigueur au CHUV avant 2009 et la prise en charge actuelle. Etudier le rôle et l'utilité du test HPV et de la colposcopie dans le suivi de ces femmes. Méthode : Il s'agit d'une étude rétrospective, monocentrique. Nous avons étudié le dossier de toutes les femmes de plus de 30 ans ayant eu une cytologie avec un diagnostic initial de L-SIL du col de l'utérus au CHUV entre le 01.01.09 et le 31.12.10, soit 61 patientes. Résultats : Parmi les 61 femmes inclues dans notre étude 60 ont eu un test HPV effectué lors du diagnostic de L-SIL, dont seuls 29 (48,33%) étaient positifs pour les hauts risques. Comparé aux femmes avec test HPV négatif pour HR, les femmes positives pour HPV HR ont eu un taux inférieur d'évolution spontanément résolutive de leur lésion et un taux supérieur de conisation ou vaporisation du col. Cinq des femmes inclues dans l'étude ont eu une évolution de leurs lésions vers une pathologie plus avancée, dont 4 vers un CIN2 et 1 vers un CIN3. Ces cinq cas étaient positifs pour HPV HR. Conclusion : Les nouvelles guidelines en vigueur au CHUV concernant la prise en charge des femmes avec diagnostic de L-SIL n'étaient pas encore appliquées en 2010, en effet le test HPV a été effectué chez presque la totalité de ces patientes. Ces nouvelles guidelines ne semblent pas être applicables aux femmes de plus de 30 ans, chez qui la prévalence du HPV HR est inférieure, et qui risquent alors de subir des examens complémentaires invasifs, sans qu'il y ait de réel bénéfice sur le pronostic de leur pathologie.

Long diagnostic delay in Crohn's disease is associated with complicated disease course and increased operation rate

Background: We have recently shown that the median diagnostic delay to establish Crohn's disease (CD) diagnosis in the Swiss IBD Cohort (SIBDC) was 9 months. Seventy five percent of all CD patients were diagnosed within 24 months. The clinical impact of a long diagnostic delay on the natural history of CD is unknown. Aim: To compare the frequency and type of CD-related complications in the patient groups with long diagnostic delay (>24 months) vs. the ones diagnosed within 24 months. Methods: Retrospective analysis of data from the SIBDCS, comprising a large sample of CD patients followed in hospitals and private practices across Switzerland. Results: Two hundred CD patients (121 female, mean age 44.9 ± 15.0 years, 38% smokers, 71% ever treated with immunomodulators and 35% with anti-TNF) with long diagnostic delay were compared to 697 CD patients (358 female, mean age 39.1 ± 14.9 years, 33% smokers, 74% ever treated with immunomodulators and 33% with anti-TNF) diagnosed within 24 months. No differences in the outcomes were observed between the two patient groups within year one after CD diagnosis. Among those diagnosed 2-5 years ago, CD patients with long diagnostic delay (n = 45) presented more frequently with internal fistulas (11.1% vs. 3.1%, p = 0.03) and bowel stenoses (28.9% vs. 15.7%, p = 0.05), and they more frequently underwent CD-related operations (15.6% vs. 5.0%, p = 0.02) compared to the patients diagnosed within 24 months (n = 159). Among those diagnosed 6-10 years ago, CD patients with long diagnostic delay (n = 48) presented more frequently with extraintestinal manifestations (60.4% vs. 34.6%, p = 0.001) than those diagnosed within 24 months (n = 182). For the patients diagnosed 11-15 years ago, no differences in outcomes were found between the long diagnostic delay group (n = 106) and the one diagnosed within 24 months (n = 32). Among those diagnosed >= 16 years ago, the group with long diagnostic delay (n = 71) more frequently underwent CD-related operations (63.4% vs. 46.5%, p = 0.01) compared to the group diagnosed with CD within 24 months (n = 241). Conclusions: A long diagnostic delay in CD patients is associated with a more complicated disease course and higher number of CD-related operations in the years following the diagnosis. Our results indicate that efforts should be undertaken to shorten the diagnostic delay in CD patients in order to reduce the risk for progression towards a complicated disease phenotype.

On the convergence of EM-like algorithms for image segmentation using Markov random fields.

Inference of Markov random field images segmentation models is usually performed using iterative methods which adapt the well-known expectation-maximization (EM) algorithm for independent mixture models. However, some of these adaptations are ad hoc and may turn out numerically unstable. In this paper, we review three EM-like variants for Markov random field segmentation and compare their convergence properties both at the theoretical and practical levels. We specifically advocate a numerical scheme involving asynchronous voxel updating, for which general convergence results can be established. Our experiments on brain tissue classification in magnetic resonance images provide evidence that this algorithm may achieve significantly faster convergence than its competitors while yielding at least as good segmentation results.

Patient doses in CT examinations in Switzerland: implementation of national diagnostic reference levels.

Diagnostic reference levels (DRLs) were established for 21 indication-based CT examinations for adults in Switzerland. One hundred and seventy-nine of 225 computed tomography (CT) scanners operated in hospitals and private radiology institutes were audited on-site and patient doses were collected. For each CT scanner, a correction factor was calculated expressing the deviation of the measured weighted computed tomography dose index (CTDI) to the nominal weighted CTDI as displayed on the workstation. Patient doses were corrected by this factor providing a realistic basis for establishing national DRLs. Results showed large variations in doses between different radiology departments in Switzerland, especially for examinations of the petrous bone, pelvis, lower limbs and heart. This indicates that the concept of DRLs has not yet been correctly applied for CT examinations in clinical routine. A close collaboration of all stakeholders is mandatory to assure an effective radiation protection of patients. On-site audits will be intensified to further establish the concept of DRLs in Switzerland.

Diagnostic interview for genetic studies (DIGS): inter-rater and test-retest reliability of alcohol and drug diagnoses

The semi-structured diagnostic interview for genetic studies (DIGS) was developed to assess major mood and psychotic disorders and their spectrum manifestations in genetic studies. Our research group developed a French version of the DIGS and tested its inter-rater and test-retest reliability in psychiatric patients. In this article, we present estimates of the reliability of substance use and antisocial personality disorders. High kappa coefficients for inter-rater reliability were found for drug and alcohol as well as antisocial personality diagnoses and slightly lower kappas for test-retest reliability. Combined with evidence of the reliability of major mood and psychotic disorders, these findings support the suitability of the DIGS for studies of familial aggregation and comorbidity of psychiatric disorders including substance use and antisocial personality disorders.

Superior diagnostic performance of perfusion-cardiovascular magnetic resonance versus SPECT to detect coronary artery disease: The secondary endpoints of the multicenter multivendor MR-IMPACT II (Magnetic Resonance Imaging for Myocardial Perfusion Assessment in Coronary Artery Disease Trial).

ABSTRACT: BACKGROUND: Perfusion-cardiovascular magnetic resonance (CMR) is generally accepted as an alternative to SPECT to assess myocardial ischemia non-invasively. However its performance vs gated-SPECT and in sub-populations is not fully established. The goal was to compare in a multicenter setting the diagnostic performance of perfusion-CMR and gated-SPECT for the detection of CAD in various populations using conventional x-ray coronary angiography (CXA) as the standard of reference. METHODS: In 33 centers (in US and Europe) 533 patients, eligible for CXA or SPECT, were enrolled in this multivendor trial. SPECT and CXA were performed within 4 weeks before or after CMR in all patients. Prevalence of CAD in the sample was 49% and 515 patients received MR contrast medium. Drop-out rates for CMR and SPECT were 5.6% and 3.7%, respectively (ns). The study was powered for the primary endpoint of non-inferiority of CMR vs SPECT for both, sensitivity and specificity for the detection of CAD (using a single-threshold reading), the results for the primary endpoint were reported elsewhere. In this article secondary endpoints are presented, i.e. the diagnostic performance of CMR versus SPECT in subpopulations such as multi-vessel disease (MVD), in men, in women, and in patients without prior myocardial infarction (MI). For diagnostic performance assessment the area under the receiver-operator-characteristics-curve (AUC) was calculated. Readers were blinded versus clinical data, CXA, and imaging results. RESULTS: The diagnostic performance (= area under ROC = AUC) of CMR was superior to SPECT (p = 0.0004, n = 425) and to gated-SPECT (p = 0.018, n = 253). CMR performed better than SPECT in MVD (p = 0.003 vs all SPECT, p = 0.04 vs gated-SPECT), in men (p = 0.004, n = 313) and in women (p = 0.03, n = 112) as well as in the non-infarct patients (p = 0.005, n = 186 in 1-3 vessel disease and p = 0.015, n = 140 in MVD). CONCLUSION: In this large multicenter, multivendor study the diagnostic performance of perfusion-CMR to detect CAD was superior to perfusion SPECT in the entire population and in sub-groups. Perfusion-CMR can be recommended as an alternative for SPECT imaging. TRIAL REGISTRATION: ClinicalTrials.gov, Identifier: NCT00977093.