Unmasking the chameleons: A benchmark for out-of-distribution detection in medical tabular data.

Background: Machine Learning (ML) models often struggle to generalize effectively to data that deviates from the training distribution. This raises significant concerns about the reliability of real-world healthcare systems encountering such inputs known as out-of-distribution (OOD) data. These concerns can be addressed by real-time detection of OOD inputs.

Development of alginate film filled with halloysite-carbon dots for active food packaging.

The development of functional bionanocomposites for active food packaging is of current interest to replace non-biodegradable plastic coatings. In the present work, we report the synthesis of an alginate-based nanocomposite filled with modified halloysite nanotubes (HNTs) to develop coatings with improved barrier properties for food packaging. Firstly, HNTs were chemically modified by the introduction of carbon dots units (CDs) onto their external surface (HNTs-CDs) obtaining a nanomaterial where CDs are uniformly present onto the tubes as verified by morphological investigations, with good UV absorption and antioxidant properties.

ICURE: Intensive care unit (ICU) risk evaluation for 30-day mortality. Developing and evaluating a multivariable machine learning prediction model for patients admitted to the general ICU in Sweden.

Background: A prediction model that estimates mortality at admission to the intensive care unit (ICU) is of potential benefit to both patients and society. Logistic regression models like Simplified Acute Physiology Score 3 (SAPS 3) and APACHE are the traditional ICU mortality prediction models. With the emergence of machine learning (machine learning) and artificial intelligence, new possibilities arise to create prediction models that have the potential to sharpen predictive accuracy and reduce the likelihood of misclassification in the prediction of 30-day mortality.

Comparison of Synthetic Pathways for Obtaining Fluorescent Nanomaterials Based on Halloysite and Carbon Dots for Potential Biological Sensing.

Recently, fluorescent sensors have gained considerable attention due to their high sensitivity, low cost and noninvasiveness. Among the different materials that can be used for this purpose, carbon dots (CDs) represent valuable candidates for applications in sensing. These, indeed, are easily synthesized, show high quantum yield and are highly biocompatible.

Hectorite/Phenanthroline-Based Nanomaterial as Fluorescent Sensor for Zn Ion Detection: A Theoretical and Experimental Study.

The development of fluorescent materials that can act as sensors for the determination of metal ions in biological fluids is important since they show, among others, high sensitivity and specificity. However, most of the molecules that are used for these purposes possess a very low solubility in aqueous media, and, thus, it is necessary to adopt some derivation strategies. Clay minerals, for example, hectorite, as natural materials, are biocompatible and available in large amounts at a very low cost that have been extensively used as carrier systems for the delivery of different hydrophobic species.

Thixotropic Hydrogels Based on Laponite® and Cucurbituril for Delivery of Lipophilic Drug Molecules.

Invited for this month's cover are the collaborating groups of Prof. Serena Riela at University of Catania, Prof. César Viseras at University of Granada and Dr.

Antioxidant Efficacy and "In Vivo" Safety of a Bentonite/Vitamin C Hybrid.

L-ascorbic acid (LAA), commonly known as vitamin C, is an excellent and recognized antioxidant molecule used in pharmaceutical and cosmetic formulations. Several strategies have been developed in order to preserve its chemical stability, connected with its antioxidant power, but there is little research regarding the employment of natural clays as LAA host. A safe bentonite (Bent)-which was verified by in vivo ophthalmic irritability and acute dermal toxicity assays-was used as carrier of LAA.

What Is the Role of Psychological Factors in Long COVID Syndrome? Latent Class Analysis in a Sample of Patients Recovered from COVID-19.

: This study aimed to identify clusters of long COVID-19 symptoms using latent class analysis and investigate the psychological factors involved in the onset of this syndrome. Five hundred and six subjects recovering from COVID-19 completed a series of standardized questionnaires to evaluate the personality traits, alexithymia, and post-traumatic stress. : Five classes were identified: (31.

Intensive Care Unit Physicians' Perspectives on Artificial Intelligence-Based Clinical Decision Support Tools: Preimplementation Survey Study.

Background: Artificial intelligence-based clinical decision support (AI-CDS) tools have great potential to benefit intensive care unit (ICU) patients and physicians. There is a gap between the development and implementation of these tools.

Objective: We aimed to investigate physicians' perspectives and their current decision-making behavior before implementing a discharge AI-CDS tool for predicting readmission and mortality risk after ICU discharge.

Antimicrobial Nanomaterials Based on Halloysite Clay Mineral: Research Advances and Outlook.

Bacterial infections represent one of the major causes of mortality worldwide. Therefore, over the years, several nanomaterials with antibacterial properties have been developed. In this context, clay minerals, because of their intrinsic properties, have been efficiently used as antimicrobial agents since ancient times.

Predicting Readmission or Death After Discharge From the ICU: External Validation and Retraining of a Machine Learning Model.

Objectives: Many machine learning (ML) models have been developed for application in the ICU, but few models have been subjected to external validation. The performance of these models in new settings therefore remains unknown. The objective of this study was to assess the performance of an existing decision support tool based on a ML model predicting readmission or death within 7 days after ICU discharge before, during, and after retraining and recalibration.

Impact of a Machine Learning-Based Decision Support System for Urinary Tract Infections: Prospective Observational Study in 36 Primary Care Practices.

Background: There is increasing attention on machine learning (ML)-based clinical decision support systems (CDSS), but their added value and pitfalls are very rarely evaluated in clinical practice. We implemented a CDSS to aid general practitioners (GPs) in treating patients with urinary tract infections (UTIs), which are a significant health burden worldwide.

Objective: This study aims to prospectively assess the impact of this CDSS on treatment success and change in antibiotic prescription behavior of the physician.

The Potential Cost-Effectiveness of a Machine Learning Tool That Can Prevent Untimely Intensive Care Unit Discharge.

Objectives: The machine learning prediction model Pacmed Critical (PC), currently under development, may guide intensivists in their decision-making process on the most appropriate time to discharge a patient from the intensive care unit (ICU). Given the financial pressure on healthcare budgets, this study assessed whether PC has the potential to be cost-effective compared with standard care, without the use of PC, for Dutch patients in the ICU from a societal perspective.

Methods: A 1-year, 7-state Markov model reflecting the ICU care pathway and incorporating the PC decision tool was developed.

Risk of post-traumatic stress symptoms in hospitalized and non-hospitalized COVID-19 recovered patients. A cross-sectional study.

High rates of post-traumatic stress disorder (PTSD) symptoms have been found among patients with more severe COVID-19-related symptoms, and hospitalization is generally recognized as a risk factor for developing PTSD. Furthermore, other personality characteristics may increase the risk of developing post-traumatic stress symptoms following a COVID-19 infection. This study aimed to assess personality traits, alexithymia, dissociation, anxiety, and depression in patients who have recovered from COVID-19 and the impact of these variables on the presence of post-traumatic stress symptoms.

Predictors for extubation failure in COVID-19 patients using a machine learning approach.

Introduction: Determining the optimal timing for extubation can be challenging in the intensive care. In this study, we aim to identify predictors for extubation failure in critically ill patients with COVID-19.

Methods: We used highly granular data from 3464 adult critically ill COVID patients in the multicenter Dutch Data Warehouse, including demographics, clinical observations, medications, fluid balance, laboratory values, vital signs, and data from life support devices.

The Dutch Data Warehouse, a multicenter and full-admission electronic health records database for critically ill COVID-19 patients.

Background: The Coronavirus disease 2019 (COVID-19) pandemic has underlined the urgent need for reliable, multicenter, and full-admission intensive care data to advance our understanding of the course of the disease and investigate potential treatment strategies. In this study, we present the Dutch Data Warehouse (DDW), the first multicenter electronic health record (EHR) database with full-admission data from critically ill COVID-19 patients.

Methods: A nation-wide data sharing collaboration was launched at the beginning of the pandemic in March 2020.

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse.

Background: The identification of risk factors for adverse outcomes and prolonged intensive care unit (ICU) stay in COVID-19 patients is essential for prognostication, determining treatment intensity, and resource allocation. Previous studies have determined risk factors on admission only, and included a limited number of predictors. Therefore, using data from the highly granular and multicenter Dutch Data Warehouse, we developed machine learning models to identify risk factors for ICU mortality, ventilator-free days and ICU-free days during the course of invasive mechanical ventilation (IMV) in COVID-19 patients.

Recurrent varicose veins of the legs: a single centre experience.

Aim: The aim of our study is to report our experience on the surgery for recurrent varicose veins of the legs over the period 2007-2012.

Materials And Methods: A series of 480 consecutive surgical procedures for varicose veins of the legs was reviewed; among a total of 480 cases, 65 procedures were for recurrent varicose veins. Data collected included clinical characteristics, surgical techniques, cause of recurrence and surgical outcomes.

Percutaneous intravascular retrieval of embolised fragments of long-term central venous catheters.

Embolisation of a catheter fragment is a rare mechanical complication of long-term central venous access devices. From 1995 to 1999 we observed 10 cases: the cause of embolisation was the 'pinch-off syndrome' in half of the cases, and in 8 cases out of 10 the fragment had embolised in the pulmonary arterial vessels. Percutaneous transvenous retrieval was successful in all cases; it was performed mainly (8 cases out of ten) through the left transfemoral route, using a single-snare-loop device sometimes associated with a pig-tail catheter.

Computed tomography imaging of vena cava filter complications: a pictorial review.

Caval filters are widely used in the prevention of pulmonary embolism. Filters have proved to be effective, but the complication rate is not negligible. Computed tomography (CT) provides a complete evaluation of the filter, including both caval and extracaval complications.

Color-Doppler sonography in chronic venous insufficiency: what the radiologist should know.

Chronic venous insufficiency (CVI) is a pathologic condition caused by valvular incompetence, with or without associated venous outflow obstruction, which may affect both the superficial and the deep venous system, causing venous hypertension and stasis. The most common form of CVI is primary varicose veins due to the insufficiency of the saphenous system. Color-Doppler sonography (CDS) is actually the main diagnostic technique of imaging for CVI.

Teaching subfascial perforator veins surgery: survey on a 2-day hands-on course.

Background: The present paper describes a training method with objective evaluation to enhance video-assisted surgical skills in subfascial endoscopic perforator veins surgery (SEPS). Training was scheduled during a 2-day intensive course.

Methods: Hands-on exercises were performed (i) on a simulator to assess whether specific training exercises were helpful in attainment of skills; (ii) on a known animal model that uses the swine abdominal wall and which allows practice in endoscopic dissection and perforator veins (PV) using appropriate instrumentation in an environment that is a reasonable surrogate for the human calf; and (iii) assisting a senior surgeon performing SEPS.

Mesenteric vein thrombosis after surgery and radiotherapy for pancreatic carcinoma. A case report.

A case is reported of a 54-year-old female patient undergoing the resection of a pancreatic carcinoma with intraoperative radiation therapy (10 Gy) on the tumor bed and subsequent external beam radiotherapy (50 Gy). After surgery the patient presented chronic diarrhea resistant to oral pancreatic enzymes. Twenty-five months postoperatively, mesenteric vein thrombosis was diagnosed after an episode of melena and was treated with conservative therapy.