[The year 2023 placed in perspective by hospital internists]. / Année 2023 mise en perspective par les internistes hospitaliers.

This article features a selection of ten topics chosen, reviewed, and commented for you by chief residents at the Department of Internal Medicine at Centre hospitalier universitaire vaudois (CHUV). This selection synthesizes the novelties and essential reminders of 2023 in internal medicine. By analyzing the standout publications of the year, it offers an overview of progress in diagnosis and patient management within the hospital and their transition to outpatient care. From oral anticoagulation to community-acquired pneumonias, encompassing the management of heart and kidney failure, each key aspect is explored. This compilation provides practitioners with an essential resource to remain at the forefront of current developments, thereby stimulating more informed and effective care for patients.

Cet article propose une sélection de dix sujets choisis, revus et commentés pour vous par les cheffes et chefs de clinique du Service de médecine interne du Centre hospitalier universitaire vaudois (CHUV). Cette sélection synthétise les nouveautés et rappels essentiels de 2023 en médecine interne. En analysant les publications phares de l'année, elle offre une vue d'ensemble des progrès dans le diagnostic et la prise en charge des patients intrahospitaliers et leur transition ambulatoire. De l'anticoagulation orale aux pneumonies communautaires en passant par la prise en charge des insuffisances cardiaque et rénale, chaque aspect clé est exploré. Cette compilation fournit aux praticiens une ressource essentielle pour rester à la pointe des développements actuels, stimulant ainsi des soins plus éclairés et efficaces pour les patients.

BERT for Activity Recognition Using Sequences of Skeleton Features and Data Augmentation with GAN.

Recently, the scientific community has placed great emphasis on the recognition of human activity, especially in the area of health and care for the elderly. There are already practical applications of activity recognition and unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple devices may be prone to errors, might be uncomfortable to wear, might be forgotten or not worn, and are unable to detect more subtle conditions such as incorrect postures. Therefore, other proposed methods are based on the use of images and videos to carry out human activity recognition, even in open spaces and with multiple people. However, the resulting increase in the size and complexity involved when using image data requires the use of the most recent advanced machine learning and deep learning techniques. This paper presents an approach based on deep learning with attention to the recognition of activities from multiple frames. Feature extraction is performed by estimating the pose of the human skeleton, and classification is performed using a neural network based on Bidirectional Encoder Representation of Transformers (BERT). This algorithm was trained with the UP-Fall public dataset, generating more balanced artificial data with a Generative Adversarial Neural network (GAN), and evaluated with real data, outperforming the results of other activity recognition methods using the same dataset.

[Highlights of Swiss congress of internal general medicine : part 1]. / Highlights du congrès 2022 de la Société suisse de médecine interne générale: partie 1.

From June 1 to 3, 2022, Lausanne held the spring congress of the Swiss Society of General Internal Medicine: "Changes and Opportunities". In this article, chief residents in internal medicine from the CHUV summarize presentations they attended. In this overview, we choose to focus on cardiovascular health, as it a central topic in general and internal medicine. Cardiovascular prevention becomes more personalized by using a step-by-step approach. The benefits of statin treatment in persons over 70 years old is still controversial. Ortho-static hypotension in hypertensive patients should not hold back antihypertensive therapy, but it should favor a combined pharmacological and non-pharmacological approach. Finally, screening for fibrosis in non-alcoholic fatty liver disease in high-risk cardiovascular patients should now part be part of a systematic ambulatory process.

Du 1er au 3 juin 2022 se tenait à Lausanne le congrès de printemps de la Société suisse de médecine interne : « Changes & Opportunities ¼. Les chefs de clinique du Service de médecine interne du CHUV vous résument les présentations auxquelles ils ont assisté. Sujet central en médecine interne générale, nous privilégions la santé cardiovasculaire dans cette synthèse. La prévention cardiovasculaire s'individualise avec une approche dépendante du risque cardiovasculaire. Les statines en prévention primaire sont controversées chez les patients de plus de 70 ans. L'hypotension orthostatique du patient hypertendu ne doit pas entraver le traitement de l'hypertension mais se contrôler par des mesures spécifiques. Finalement, dépister la fibrose de la stéatose hépatique non alcoolique chez les patients à risque fait partie d'une démarche ambulatoire systématique.

Deep learning exoplanets detection by combining real and synthetic data.

Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope light curves. The approach is based on related work from the literature and enhanced to validation with real light curves. A CNN classification model is trained from a mixture of real and synthetic data. The model is then validated only with unknown real data. The best ratio of synthetic data is determined by the performance of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.

[The Internal medicine articles that struck us the most in 2021]. / Année 2021 mise en perspective par les internistes hospitaliers.

The year 2021 has seen many breakthroughs in general internal medicine, despite the ongoing COVID-19 pandemic, with multiple implications in our daily clinical practice. From shorter antibiotic treatment duration in community-acquired pneumonia, to new indications for colchicine treatment, without forgetting better targets of hemoglobin for transfusion, questioning of the interest of high dose vitamin D substitution when preventing falls in older patients and finally disappointing hopes for new indications of albumin substitution in cirrhosis, the literature is full of new evidence. Each year, the chief residents of the internal medicine ward in Lausanne university hospital (CHUV) in Switzerland meet up to share their readings: here is a selection of ten articles, chosen, summarized, and commented for you.

L'année 2021, malgré la pandémie de Covid-19, a vu de nombreux progrès en médecine interne générale, avec de multiples implications pour notre pratique quotidienne. D'une durée diminuée d'antibiothérapie pour le traitement de la pneumonie communautaire à de nouvelles indications au traitement de colchicine, en passant par des précisions sur les cibles de transfusion érythrocytaire, ainsi qu'une remise en question de l'intérêt de la vitamine D à haute dose dans la prévention des chutes chez la personne âgée, et pour finir des espoirs déçus de nouvelle indication à la substitution d'albumine dans la cirrhose, les nouveautés abondent dans la littérature. Chaque année, les cheffes et chefs de clinique du Service de médecine interne du CHUV se réunissent pour partager leurs lectures : voici une sélection de dix articles choisis, revus et commentés pour vous.

Enfermedad de Parkinson senil benigna / Benign late onset Parkinsons disease

No disponible