Search

On recense un nombre croissant d'applications médicales qui utilisent de l'intelligence artificielle (IA) et du machine learning. Actuellement en urologie, il y a peu d'outils concrets bien qu'il existe des projets en cours rapidement applicables à notre exercice, notamment en oncologie prostatique. D'ailleurs, de récentes autorisations réglementaires pour des usages dans d'autres domaines médicaux témoignent du fait qu'une vague d'IA pourrait investir nos pratiques. L'analyse de ces innovations et l'étude de leurs caractéristiques à l'origine de leur validation réglementaire renseignent sur les perspectives de recherche et de développements de l'IA dans notre spécialité. L'apport de l'IA pourrait être réparti en 3 catégories : l'assistance (IA-A), la substitution (IA-S) ou l'extension (IA-X) de l'expertise médicale humaine. Les freins à son émancipation seraient réduits d'autant que l'intégralité de ses 3 champs d'usage serait considérée sans se réduire à la seule IA-S, source du fantasme d'une intelligence concurrente de celle de l'homme. Dès lors, des évolutions du contexte réglementaire d'évaluation et de validation en matière d'innovation en IA seraient alors nécessaires pour en permettre l'essor dans nos pratiques et en autoriser la commercialisation sur notre marché, voire le remboursement selon certains usages. There are a growing number of medical applications that use artificial intelligence (AI) and machine learning. Currently in urology, there are few concrete tools but there are ongoing projects quickly applicable to our activities, especially in prostatic oncology. Moreover, recent regulatory authorizations for uses in other medical fields testify to the fact that a wave of AI could take over our practices. The analysis of these innovations and the study of their characteristics at the origin of their regulatory validation provide information on the perspectives of research and developments of AI in our specialty. The contribution of AI could be divided into 3 categories: assistance (A-AI), substitution (S-AI) or extension (X-AI) of human medical expertise. The brakes on its emancipation would be reduced as much as the entirety of its 3 fields of use would be considered without being reduced only to S-AI, source of the fantasy of an intelligence competing with that of the man. Therefore, changes to the regulatory context for evaluation and validation in terms of AI innovation would then be necessary to allow it to flourish in our practices and authorize its marketing, or even reimbursement according to certain uses. [ABSTRACT FROM AUTHOR]

Copyright of Italian Oral Surgery is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The lack of power anomaly is an intriguing feature at the largest angular scales of the CMB anisotropy temperature pattern, whose statistical significance is not strong enough to claim any new physics beyond the standard cosmological model. We revisit the former statement by also considering polarisation data. We propose a new one-dimensional estimator which takes jointly into account the information contained in the TT, TE and EE CMB spectra. By employing this estimator on Planck 2015 low- ℓ data, we find that a random Λ CDM realisation is statistically accepted at the level of 3.68%. Even though Planck polarisation contributes a mere 4% to the total information budget, its use pushes the lower-tail-probability down from the 7.22% obtained with only temperature data. Forecasts of future CMB polarised measurements, as e.g. the LiteBIRD satellite, can increase the polarisation contribution up to 6 times with respect to Planck at low- ℓ. We argue that the large-scale E-mode polarisation may play an important role in analysing CMB temperature anomalies with future mission. [ABSTRACT FROM AUTHOR]