Search

BackgroundSepsis is a challenging condition increasingly managed in medical wards, however literature and clinical evidence in this hospital setting are lacking.MethodsUsing the computational i2b2 framework, we retrospectively analyzed data from patients admitted to internal medicine units of four hospitals in Lombardy (Italy) between January 2012 and December 2023, with a discharge diagnosis of sepsis, septic shock, or septicemia.ResultsA total of 4,375 patients were recruited. Median length of stay (LOS) was 14 days, and mean ward-to-intensive care unit (ICU) transfer and in-hospital mortality rates were 11 and 26%, respectively; significant differences were observed over the years, with LOS peaks preceding mortality peaks by 1 year. Blood culture-negative sepses showed shorter stays and higher mortality (acute kidney injury and fast deterioration) compared to culture-positive ones; polymicrobial sepses showed higher ICU transfer rates (acute respiratory distress); while multidrug-resistant (MDR+) and/or polymicrobial sepses showed longer stays and higher mortality (complicated course) compared to drug-sensitive or monomicrobial ones. C-reactive protein elevation predicted rapidly evolving culture-negative sepsis, whereas lower leukocyte counts predicted prolonged hospitalization; higher fractions of inspired oxygen predicted polymicrobial sepsis, while lactate elevation predicted ICU transfer; ferritin elevation and increased leukocyte counts predicted MDR+ sepsis, while further ferritin elevation and decreased platelet counts predicted death. From 2016 to 2023, MDR+ sepsis frequency declined, due to decreased resistance to several antibiotic classes, such as cephalosporins, fluoroquinolones, and aminoglycosides; however, carbapenemase- and extended-spectrum beta-lactamase-producing Gram-negative bacteria, as well as vancomycin-resistant enterococci, increased, as did the frequency of polymicrobial sepsis following the COVID-19 outbreak.ConclusionThis work provides novel insights into sepsis management in internal medicine units, highlighting the need for validated biomarkers and implemented therapies in this scenario.

Detecting lung diseases in medical images can be quite challenging for radiologists. In some cases, even experienced experts may struggle with accurately diagnosing chest diseases, leading to potential inaccuracies due to complex or unseen biomarkers. This review paper delves into various datasets and machine learning techniques employed in recent research for lung disease classification, focusing on pneumonia analysis using chest X-ray images. We explore conventional machine learning methods, pretrained deep learning models, customized convolutional neural networks (CNNs), and ensemble methods. A comprehensive comparison of different classification approaches is presented, encompassing data acquisition, preprocessing, feature extraction, and classification using machine vision, machine and deep learning, and explainable-AI (XAI). Our analysis highlights the superior performance of transfer learning-based methods using CNNs and ensemble models/features for lung disease classification. In addition, our comprehensive review offers insights for researchers in other medical domains too who utilize radiological images. By providing a thorough overview of various techniques, our work enables the establishment of effective strategies and identification of suitable methods for a wide range of challenges. Currently, beyond traditional evaluation metrics, researchers emphasize the importance of XAI techniques in machine and deep learning models and their applications in classification tasks. This incorporation helps in gaining a deeper understanding of their decision-making processes, leading to improved trust, transparency, and overall clinical decision-making. Our comprehensive review serves as a valuable resource for researchers and practitioners seeking not only to advance the field of lung disease detection using machine learning and XAI but also from other diverse domains.

Skin cancer is among the most prevalent cancers globally, emphasizing the need for early detection and accurate diagnosis to improve outcomes. Traditional diagnostic methods, based on visual examination, are subjective, time-intensive, and require specialized expertise. Current artificial intelligence (AI) approaches for skin cancer detection face challenges such as computational inefficiency, lack of interpretability, and reliance on standalone CNN architectures. To address these limitations, this study proposes a comprehensive pipeline combining transfer learning, feature selection, and machine-learning algorithms to improve detection accuracy. Multiple pretrained CNN models were evaluated, with Xception emerging as the optimal choice for its balance of computational efficiency and performance. An ablation study further validated the effectiveness of freezing task-specific layers within the Xception architecture. Feature dimensionality was optimized using Particle Swarm Optimization, reducing dimensions from 1024 to 508, significantly enhancing computational efficiency. Machine-learning classifiers, including Subspace KNN and Medium Gaussian SVM, further improved classification accuracy. Evaluated on the ISIC 2018 and HAM10000 datasets, the proposed pipeline achieved impressive accuracies of 98.5% and 86.1%, respectively. Moreover, Explainable-AI (XAI) techniques, such as Grad-CAM, LIME, and Occlusion Sensitivity, enhanced interpretability. This approach provides a robust, efficient, and interpretable solution for automated skin cancer diagnosis in clinical applications.

IntroductionDiverticular disease (DD), commonly associated with the elderly, is becoming more prevalent among younger individuals. This retrospective study aimed to evaluate the differences in the natural history and outcomes between young and old patients with DD.MethodsAdult patients with DD diagnosed between 2010 and 2022 at an Italian tertiary referral center were enrolled, and their demographic and clinical data were retrieved. The patients were categorized as young or old based on the 25th percentile of the population's age at diagnosis. Univariate and multivariate analyses were performed to assess the association between the collected variables and the age of disease presentation. Additionally, survival analyses were conducted to evaluate the association between the age of diagnosis and clinical outcomes at follow-up, including disease recurrence, hospital access, surgery, and death.ResultsA total of 220 DD patients (with a median age of 66 years, IQR 55–74, and a female-to-male ratio of 1.4:1) were included in the study, comprising 54 patients receiving a diagnosis before the age of 49 years (young DD patients) and 166 patients diagnosed after the age of 49 years (old DD patients). Male sex (57 vs. 36%, p < 0.01), smoking (38 vs. 14%, p < 0.01), and alcohol consumption (54 vs. 38%) were highly prevalent in young patients. The complications at the time of diagnosis, particularly abscesses and free perforations, occurred more frequently in younger patients (p = 0.04). Moreover, young DD patients experienced a higher rate of hospitalization and surgical intervention (p = 0.01 and p = 0.04, respectively) over a median follow-up period of 5 years.ConclusionPreventive strategies and prompt diagnosis are crucial in young patients with DD for achieving better disease outcomes and preventing complications.

IntroductionDeveloping efficient methods to infer relations among different faces consisting of numerous expressions or on the same face at different times (e.g., disease progression) is an open issue in imaging related research. In this study, we present a novel method for facial feature extraction, characterization, and identification based on classical computer vision coupled with deep learning and, more specifically, convolutional neural networks.MethodsWe describe the hybrid face characterization system named FRetrAIval (FRAI), which is a hybrid of the GoogleNet and the AlexNet Neural Network (NN) models. Images analyzed by the FRAI network are preprocessed by computer vision techniques such as the oriented gradient-based algorithm that can extract only the face region from any kind of picture. The Aligned Face dataset (AFD) was used to train and test the FRAI solution for extracting image features. The Labeled Faces in the Wild (LFW) holdout dataset has been used for external validation.Results and discussionOverall, in comparison to previous techniques, our methodology has shown much better results on k-Nearest Neighbors (KNN) by yielding the maximum precision, recall, F1, and F2 score values (92.00, 92.66, 92.33, and 92.52%, respectively) for AFD and (95.00% for each variable) for LFW dataset, which were used as training and testing datasets. The FRAI model may be potentially used in healthcare and criminology as well as many other applications where it is important to quickly identify face features such as fingerprint for a specific identification target.

For a long time, the study of heart failure focused on single heart chamber disease. There is, instead, growing attention on the interplay between the atria and the ventricles during the cardiac cycle and on the consequences of an altered chamber coupling on global heart performance and heart failure. This review aimed to explore the principles of atrioventricular (AV) function and coupling of the left heart and the consequences that their disruption could have in several diseases. Furthermore, we will examine echocardiographic tips for analyzing the chamber function and the AV coupling. Finally, we will explore the most recent pharmacological acquisitions and the device therapies we have for use.

In recent decades, there has been considerable effort in investigating the clinical utility of renal Doppler measurements in both cardiovascular and renal disorders. In particular, a measure of renal arterial resistance, the renal resistive index (RRI), has been demonstrated to predict chronic kidney disease progression and acute kidney injury in different clinical settings. Furthermore, it is linked to a poorer prognosis in individuals suffering from chronic heart failure. Examining the renal venous flow through pulsed Doppler can offer additional insights into renal congestion and cardiovascular outcomes for these patients. This review seeks to summarize the existing data concerning the clinical significance of arterial and venous renal Doppler measurements across various cardiovascular and renal disease contexts.

Skin cancer is among the most prevalent cancers globally, emphasizing the need for early detection and accurate diagnosis to improve outcomes. Traditional diagnostic methods, based on visual examination, are subjective, time-intensive, and require specialized expertise. Current artificial intelligence (AI) approaches for skin cancer detection face challenges such as computational inefficiency, lack of interpretability, and reliance on standalone CNN architectures. To address these limitations, this study proposes a comprehensive pipeline combining transfer learning, feature selection, and machine-learning algorithms to improve detection accuracy. Multiple pretrained CNN models were evaluated, with Xception emerging as the optimal choice for its balance of computational efficiency and performance. An ablation study further validated the effectiveness of freezing task-specific layers within the Xception architecture. Feature dimensionality was optimized using Particle Swarm Optimization, reducing dimensions from 1024 to 508, significantly enhancing computational efficiency. Machine-learning classifiers, including Subspace KNN and Medium Gaussian SVM, further improved classification accuracy. Evaluated on the ISIC 2018 and HAM10000 datasets, the proposed pipeline achieved impressive accuracies of 98.5% and 86.1%, respectively. Moreover, Explainable-AI (XAI) techniques, such as Grad-CAM, LIME, and Occlusion Sensitivity, enhanced interpretability. This approach provides a robust, efficient, and interpretable solution for automated skin cancer diagnosis in clinical applications. [ABSTRACT FROM AUTHOR]

The dynamics of a probe particle is highly influenced by the nature of the bath in which it is immersed. In particular, baths composed by active (e.g., self-propelled) particles induce intriguing out-of-equilibrium effects on tracer's motion that are customarily described by integrating out the dynamics of the bath's degrees of freedom (DOFs). However, thermodynamic quantities, such as the entropy production rate, are generally severely affected by coarse-graining procedures. Here, by employing an exact integration of a subset of DOFs, we show that two classes of DOFs emerge, entropic and nonentropic. By inspecting the resulting generalized Langevin equation (GLE) for the observed variables, it turns out that active baths are associated with the presence of entropic DOFs exhibiting nonreciprocal interactions with a probe particle. Surprisingly, integrating out these DOFs inevitably results into a system-dependent increase or reduction of the entropy production rate, at variance with other coarse-graining schemes. In this case, the resulting GLE is not thermodynamically consistent. On the contrary, the entropy production rate stays invariant after integrating out nonentropic DOFs and the resulting GLE preserves the thermodynamics of the full system. Additionally, the number of nonentropic DOFs determines the dimensionality of isoentropic hypersurfaces in the parameter space. Our results shed light on the nature of active baths, revealing that the presence of a typical correlation timescale is not a sufficient condition to have nonequilibrium effects on a probe particle, and draws a path towards the understanding of thermodynamically consistent procedures to derive effective dynamics of observed DOFs.

The Michael‐type addition of indoles represents one of the most important C−C bonds forming reactions at their C‐3 position. Herein, we present a mild, versatile and sustainable protocol for the efficient preparation of β‐indolylketones via a Michael addition between indoles and chalcones or α,β‐unsaturated ketones in the presence of substituted arylazo sulfones as photoacid generators (PAGs). [ABSTRACT FROM AUTHOR]

Arylazo sulfones were used as Photoacid Generators (PAGs) for the visible-light photorelease of strong sulfonic acids to promote the ring opening of epoxides in benign media (DMC/water mixtures) or under neat conditions. Water, alcohols, azide and thiocyanate anions, as well as electron-rich aromatics were used in the role of the nucleophile. The resulting 1,2-disubstituted adducts were formed mostly in >99% yield in a high regioselective fashion. [ABSTRACT FROM AUTHOR]

Background: Chest Computed Tomography (CT) imaging has played a central role in the diagnosis of interstitial pneumonia in patients affected by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and can be used to obtain the extent of lung involvement in COVID-19 pneumonia patients either qualitatively, via visual inspection, or quantitatively, via AI-based software. This study aims to compare the qualitative/quantitative pathological lung extension data on COVID-19 patients. Secondly, the quantitative data obtained were compared to verify their concordance since they were derived from three different lung segmentation software. Methods: This double-center study includes a total of 120 COVID-19 patients (60 from each center) with positive reverse-transcription polymerase chain reaction (RT-PCR) who underwent a chest CT scan from November 2020 to February 2021. CT scans were analyzed retrospectively and independently in each center. Specifically, CT images were examined manually by two different and experienced radiologists for each center, providing the qualitative extent score of lung involvement, whereas the quantitative analysis was performed by one trained radiographer for each center using three different software: 3DSlicer, CT Lung Density Analysis, and CT Pulmo 3D. Results: The agreement between radiologists for visual estimation of pneumonia at CT can be defined as good (ICC 0.79, 95% CI 0.73–0.84). The statistical tests show that 3DSlicer overestimates the measures assessed; however, ICC index returns a value of 0.92 (CI 0.90–0.94), indicating excellent reliability within the three software employed. ICC was also performed between each single software and the median of the visual score provided by the radiologists. This statistical analysis underlines that the best agreement is between 3D Slicer “LungCTAnalyzer” and the median of the visual score (0.75 with a CI 0.67–82 and with a median value of 22% of disease extension for the software and 25% for the visual values). Conclusions: This study provides for the first time a direct comparison between the actual gold standard, which is represented by the qualitative information described by radiologists, and novel quantitative AI-based techniques, here represented by three different commonly used lung segmentation software, underlying the importance of these specific values that in the future could be implemented as consistent prognostic and clinical course parameters.

For a long time, the study of heart failure focused on single heart chamber disease. There is, instead, growing attention on the interplay between the atria and the ventricles during the cardiac cycle and on the consequences of an altered chamber coupling on global heart performance and heart failure. This review aimed to explore the principles of atrioventricular (AV) function and coupling of the left heart and the consequences that their disruption could have in several diseases. Furthermore, we will examine echocardiographic tips for analyzing the chamber function and the AV coupling. Finally, we will explore the most recent pharmacological acquisitions and the device therapies we have for use. [ABSTRACT FROM AUTHOR]