La Revue de médecine interne
-
Following the emergence of open public databases and connected objects, big data and artificial intelligence are developing rapidly, especially in medicine, with many opportunities ranging from complex diagnostic assistance to real-time statistical analysis. In order to promote their development and guide their use in the field of internal medicine, guidelines and recommendations are needed. First of all, this article seeks to clarify the concepts of big data and artificial intelligence and the correlations between each other, and then to give an overview of the progress made at European level in this rapidly expanding field.
-
Review Case Reports
[A new case of rare erythrocytosis due to EGLN1 mutation with review of the literature].
The origin of polycythemia is often simple to detect. Sometimes it is necessary to look for hereditary forms, the decisive parameters being the dosage of erythropoietin and the measurement of the oxygen dissociation curve (P50). These rare diseases are related to high oxygen-affinity haemoglobins, abnormalities of the erythropoietin receptor or dysfunction of the HIF (hypoxia-inducible factor) pathway. ⋯ In the face of an unexplained polycythemia a good cooperation between clinicians and biologists is necessary to be able to characterize rare hereditary pathologies.
-
Mucopolysaccharidosis are lysosomal storage diseases, secondary to the accumulation of mucopolysaccharides. Type 1 mucopolysaccharidosis is the most common form and affects between 0.69 and 1.66 newborns per 100,000. The severity of mucopolysaccharidosis is variable with lethal forms in utero and attenuated forms diagnosed in adults. ⋯ Mucopolysaccharidosis recognition is important for patient management and family screening. In addition, specific enzyme replacement therapy exists for certain types of mucopolysaccharidosis. Role of clinician is important to evoke and diagnose mucopolysaccharidosis.
-
Review
[Do artificial intelligence systems reason in the same way as clinicians when making diagnoses?]
Clinical reasoning is at the heart of physicians' competence, as it allows them to make diagnoses. However, diagnostic errors are common, due to the existence of reasoning biases. ⋯ It is increasingly seen as a solution to improve the diagnostic performance of physicians, or even to perform this task for them, in a totally autonomous and more efficient way. In order to understand the challenges associated with the development of artificial intelligence, it is important to understand how the machine works to make diagnoses, what are the similarities and differences with the physician's diagnostic reasoning, and what are the consequences for medical training and practice.
-
Belimumab is currently approved for the treatment of active systemic lupus erythematosus (SLE). The aim of our study was to evaluate the efficacy of belimumab in the treatment of cutaneous lupus erythematosus (CLE), resistant to conventional therapy. ⋯ Our study suggests the clinical efficiency of belimumab in a series of 7 patients presenting a resistant and progressive CLE.