Validation procedures in radiological diagnostic models. Neural network and logistic regression

The objective of this paper is to compare the performance of twopredictive radiological models, logistic regression (LR) and neural network (NN), with five different resampling methods. One hundred and sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross validation, leave-one-out and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). The neural network obtained statistically higher Az than LR with cross validation. The remaining resampling validation methods did not reveal statistically significant differences between LR and NN rules. The neural network classifier performs better than the one based on logistic regression. This advantage is well detected by three-fold cross-validation, but remains unnoticed when leave-one-out or bootstrap algorithms are used.

Rôle de l'imagerie dans le diagnostic et le suivi de la polyarthrite rhumatoïde [Role of imaging in the diagnosis and follow-up of rheumatoid arthritis].

Cross-sectional imaging techniques such as magnetic resonance imaging and ultrasound are becoming essential tools not only for making an early diagnosis of rheumatoid arthritis, but also to help clarify the prognosis of the disease and better assess the response to various therapies. This article summarises the recommendations established in 2013 by the European League Against Rheumatism on the role of imaging in the diagnosis and follow-up of rheumatoid arthritis, while adding comments and emphasising on our Swiss experience with the use of ultrasound.

L'apathie, un symptôme transnosographique: diagnostic différentiel et prise en charge [Apathy, a transnosographic symptom: diagnosis and treatment]

Apathy defined as a loss of motivation and interest for novelty is a frequent symptom encountered in a number of psychiatric and somatic disorders. The purpose of this article is to provide an overview of the many different medical contexts where apathy may occur and help clinicians to differentiate it from a depressive syndrome. The treatment of apathy requires a diagnostic clarification in order to treat the underlying condition. Then, pharmacological or non-pharmacological interventions may help to specifically improve apathy.

Non-invasive diagnostic biomarkers for estimating the onset time of permanent cerebral ischemia.

The treatments for ischemic stroke can only be administered in a narrow time-window. However, the ischemia onset time is unknown in ~30% of stroke patients (wake-up strokes). The objective of this study was to determine whether MR spectra of ischemic brains might allow the precise estimation of cerebral ischemia onset time. We modeled ischemic stroke in male ICR-CD1 mice using a permanent middle cerebral artery filament occlusion model with laser Doppler control of the regional cerebral blood flow. Mice were then subjected to repeated MRS measurements of ipsilateral striatum at 14.1 T. A striking initial increase in γ-aminobutyric acid (GABA) and no increase in glutamine were observed. A steady decline was observed for taurine (Tau), N-acetyl-aspartate (NAA) and similarly for the sum of NAA+Tau+glutamate that mimicked an exponential function. The estimation of the time of onset of permanent ischemia within 6 hours in a blinded experiment with mice showed an accuracy of 33±10 minutes. A plot of GABA, Tau, and neuronal marker concentrations against the ratio of acetate/NAA allowed precise separation of mice whose ischemia onset lay within arbitrarily chosen time-windows. We conclude that (1)H-MRS has the potential to detect the clinically relevant time of onset of ischemic stroke.

Maladies auto-immunes neuromusculaires: diagnostic et prise en charge [Dysimmune neuromuscular disorders: diagnostic challenges and new ways of management].

This review describes some dysimmune neuromuscular disorders and their recent management: syndrome of peripheral nerve hyperexcitability (treatment of cramps, immunosuppressors); Guillain-Barré syndrome (new mechanisms and consensus treatment); chronic inflammatory demyelinating polyradiculoneuropathy (new indication for the use of pulse dexamethasone, new scores of activity); importance of subcutaneous immunoglobulin in multifocal motor neuropathy and of infusions of rituximab in myasthenia gravis; new entities in myositis and their treatment.

Dosimetric aspects of a national survey of diagnostic and interventional radiology in Switzerland.

The effective dose delivered to the patient was determined, by modeling, for 257 types of examinations covering the different modalities of diagnostic and interventional radiology. The basic operational dosimetric quantities considered were obtained from the parameters of the examinations on the basis of dosimetric models. These models required a precise characterization of each examination. The operational dosimetric quantities were converted into doses to organs and effective doses using appropriate conversion factors. The determination of the collective effective dose to the Swiss population requires a number of corrections to account for the variability of several parameters: sensitivity of the detection system, age, gender, and build of the patient. The use of various dosimetric models is illustrated in this paper for a limited number of examination types covering the different radiological modalities, for which the established typical effective doses are given. With regard to individual doses, the study indicated that the average effective doses per type of examination can be classified into three levels: (a) the weakly irradiating examinations (less than 0.1 mSv), which represent 78% of the examinations and 4% of the collective dose, (b) the moderately irradiating examinations (between 0.1 mSv and 10 mSv), which represent 21% of the examinations and 72% of the collective dose, (c) the strongly irradiating examinations (more than 10 mSv), which represent 1% of the examinations and 24% of the collective dose.

Diagnostic INSMED: Cuentagotas S.L.

Modèle de diagnostic C4.1.1 (UPC)

Diagnostic INSMED: COPERSA, S.A.

Modèle de disgnostic C4.1.2 (UPC)

Pyoderma gangrenosum: défi diagnostique et thérapeutique [Pyoderma gangrenosum: diagnostic and therapeutic challenge]

Pyoderma gangrenosum is a rare ulcerative disease associated with inflammatory bowel disease, arthritis or haematological malignancies. The diagnosis of Pyoderma gangrenosum is often delayed while consideration is given to the more likely diagnoses of wound breakdown or bacterial infection. The outcome depends on early diagnosis and on excellent collaboration between the surgical team and the infectious disease specialist. We present two puzzling cases of Pyoderma gangrenosum and discuss the physiopathology, the diagnosis strategy and the management. Le Pyoderma gangrenosum constitue une entité clinique méconnue, se présentant classiquement par des ulcérations cutanées inflammatoires et douloureuses. Le contexte clinique retrouve fréquemment une pathologie inflammatoire digestive, une néoplasie ou une atteinte rhumatologique concomitante. Le diagnostic est trop souvent tardif, après de multiples traitements antibiotiques et chirurgicaux, et nécessite une excellente coordination entre le médecin traitant, les équipes chirurgicales et les spécialistes des maladies infectieuses. Au travers de deux cas spectaculaires, nous rappelons quelques notions de base sur la physiopathologie, la présentation clinique et la prise en charge du Pyoderma gangrenosum.

Développement, implémentation et utilisation pratique d'un score diagnostique [Development, implementation and practical use of a diagnostic score].

In recent years many clinical prediction rules (CPR) have been developed. Before a CPR can be used in clinical practice, different methodical steps are necessary, from the development of the score, the internal and external validation to the impact study. Before using a CPR in daily practice family doctors have to verify how the rules have been developed and whether this has been done in a population similar to the population in which they would use them. The aim of this paper is to describe the development of a CPR, and to discuss advantages and risks related to the use of CPR in order to help family doctors in their choice of scores for use in their daily practice.

Diagnostic Performances of 18F-FDG Positron Emission Tomography in Large Vessels Vasculitis: Meta-analysis

Toperform a meta-analysis of FDG-PET performances in the diagnosis of largevessels vasculitis (Giant Cell Arteritis (GCA) associated or not withPolymyalgia Rheumatica(PMR), Takayasu). Materials and methods : The MEDLINE,Cochrane Library, Embase were searched for relevant original articlesdescribing FDG-PET for vasculitis assessment, using MesH terms ("GiantCell Arteritis or Vasculitis" AND "PET"). Criteria for inclusionwere:(1)FDG-PET for diagnosis of vasculitis(2)American College of Rheumatologycriteria as reference standard(3)control group. After data extraction, analyseswere performed using a random-effects model. Results : Of 184 citations(database search and references screening),70 articles were reviewed of which12 eligible studies were extracted (sensitivity range from 32% to 97%). 7studies fulfilled all inclusion criteria. Owing to overlapping population, 1study was excluded. Statistical heterogeneity justified the random-effectsmodel. Pooled 6 studies analysis(116 vasculitis,224 controls) showed a 81%sensitivity (95%CI:70-89%);a 89% specificity (95%CI:77-95%);a 85%PPV(95%CI:63-95%); a 90% NPV(95%CI:79-95%);a 7.1 positive LR(95%CI:3.4-14.9); a0.2 negative LR(95%CI:0.14-0.35) and 90.1 DOR(95%CI: 18.6-437). Conclusion :FDG-PET has good diagnostic performances in the detection of large vesselsvasculitis. Its promising role could be extended to follow up patients undertreatment, but further studies are needed to confirm this possibility.

European Association of Veterinary Diagnostic Imaging : 4th European conferece : matkakertomus

Mirja Ruohoniemi