Prevalence of the use of antidepressants in patients with venous thromboembolism / Prevalencia del uso de antidepresivos en pacientes con enfermedad tromboembólica venosa.

OBJECTIVE: To estimate the prevalence of Antidepressant use in patients with a history of venous thromboembolism (VTE). Describe the patient's characteristics and which drugs are the most prescribed. METHODS: A cross-sectional study involving a consecutive sample of patients included in the Registro de Enfermedad Tromboembólica (RIET) from the Hospital Italiano de Buenos Aires in a period between 01/01/2014 to 01/09/2018. All patients presented symptomatic VTE and confirmed diagnosis. Drugs considered included in this study were: Selective Serotonin Reuptake Inhibitors (SSRI), Dopamine and Norepinephrine Reuptake Inhibitors (NDRI), Serotonin and Norepinephrine Reuptake Inhibitors (SNRI) and Tricyclic antidepressants (TCA). RESULTS: From a total of 2373 patients with VTE, 472 were active users of antidepressants, showing a prevalence of antidepressant use of 19.9% (CI 95%). The most frequently prescribed drugs by drug classification were: SSRI 83.9%, TCA 20.5%, ISRN 14.6%, and NDRI 2.5%. Patients presented a median age of 76 years, predominantly women (71.4%), with several comorbidities: 52.24% arterial hypertension, 37.29% overweight, and 34.75% history of smoking. Concerning relevant history, we observed: 29.03% active oncologic disease, 26.27% major surgery before the VTE, and 21.61% previous VTE. CONCLUSION: The prevalence of antidepressant use in patients with VTE is 19.9%, superior by far to that of the general population. Depression is a major cause of morbidity worldwide, and its prevalence is increasing over the years.

OBJETIVOS: Estimar la prevalencia de consumo de fármacos antidepresivos en pacientes que hayan sufrido un evento tromboembólico venoso (TEV), describir esta población y las drogas más utilizadas. MATERIAL Y MÉTODOS: Corte transversal que incluyó una muestra consecutiva de adultos incluidos en el Registro de Enfermedad Tromboembólica (RIET) del Hospital Italiano de Buenos Aires entre el 01/01/2014 y el 1/09/2018. Se consideraron los siguientes fármacos: Inhibidores Selectivos de la Recaptación de Serotonina (IRSS), Inhibidores de la Recaptación de Dopamina y Noradrenalina (IRDN), Inhibidores de la Recaptación de Serotonina y Noradrenalina (IRSN), y Antidepresivos Tricíclicos (ATC). RESULTADOS: De un total de 2373 pacientes, 472 se identificaron como usuarios activos de antidepresivos, arrojando una prevalencia de 19,9% (IC95% de 18,3-21,6). Según familia farmacológica, en orden de mayor a menor frecuencia, se indicaron: IRSS 83,9%, ATC 20,5%, IRS 14,6% e IRDN y IRDN 2,5%. Los pacientes bajo tratamiento con antidepresivos presentaron una mediana de edad de 76 años, mayoritariamente mujeres (71,4%), con alta carga de comorbilidad: 52,24% hipertensión arterial, 37,29% sobrepeso, 34,75% ex tabaquismo. Los antecedentes de mayor frecuencia resultaron enfermedad oncológica activa (29,03%), cirugía mayor en último mes (26,27%), y el 21,61% presentaba ETV previa. CONCLUSIONES: La prevalencia de uso de antidepresivos en pacientes con ETV resultó 19,9%, superior a la población general. La depresión es una causa principal de enfermedad y discapacidad en todo el mundo, cuya prevalencia aumentó durante los últimos años.

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System.

The game of Jenga is a benchmark used for developing innovative manipulation solutions for complex tasks. Indeed, it encourages the study of novel robotics methods to successfully extract blocks from a tower. A Jenga game involves many traits of complex industrial and surgical manipulation tasks, requiring a multi-step strategy, the combination of visual and tactile data, and the highly precise motion of a robotic arm to perform a single block extraction. In this work, we propose a novel, cost-effective architecture for playing Jenga with e.Do, a 6DOF anthropomorphic manipulator manufactured by Comau, a standard depth camera, and an inexpensive monodirectional force sensor. Our solution focuses on a visual-based control strategy to accurately align the end-effector with the desired block, enabling block extraction by pushing. To this aim, we trained an instance segmentation deep learning model on a synthetic custom dataset to segment each piece of the Jenga tower, allowing for visual tracking of the desired block's pose during the motion of the manipulator. We integrated the visual-based strategy with a 1D force sensor to detect whether the block could be safely removed by identifying a force threshold value. Our experimentation shows that our low-cost solution allows e.DO to precisely reach removable blocks and perform up to 14 consecutive extractions in a row.

Marvin: An Innovative Omni-Directional Robotic Assistant for Domestic Environments.

Population aging and pandemics have been shown to cause the isolation of elderly people in their houses, generating the need for a reliable assistive figure. Robotic assistants are the new frontier of innovation for domestic welfare, and elderly monitoring is one of the services a robot can handle for collective well-being. Despite these emerging needs, in the actual landscape of robotic assistants, there are no platforms that successfully combine reliable mobility in cluttered domestic spaces with lightweight and offline Artificial Intelligence (AI) solutions for perception and interaction. In this work, we present Marvin, a novel assistive robotic platform we developed with a modular layer-based architecture, merging a flexible mechanical design with cutting-edge AI for perception and vocal control. We focus the design of Marvin on three target service functions: monitoring of elderly and reduced-mobility subjects, remote presence and connectivity, and night assistance. Compared to previous works, we propose a tiny omnidirectional platform, which enables agile mobility and effective obstacle avoidance. Moreover, we design a controllable positioning device, which easily allows the user to access the interface for connectivity and extends the visual range of the camera sensor. Nonetheless, we delicately consider the privacy issues arising from private data collection on cloud services, a critical aspect of commercial AI-based assistants. To this end, we demonstrate how lightweight deep learning solutions for visual perception and vocal command can be adopted, completely running offline on the embedded hardware of the robot.