Search

Short QT syndrome (SQTS) is an inherited cardiac ion-channel disease related to an increased risk of sudden cardiac death (SCD) in young and otherwise healthy individuals. SCD is often the first clinical presentation in patients with SQTS. However, arrhythmia risk stratification is presently unsatisfactory in asymptomatic patients. In this context, artificial intelligence-based electrocardiogram (ECG) analysis has never been applied to refine risk stratification in patients with SQTS. The purpose of this study was to analyze ECGs from SQTS patients with the aid of different AI algorithms to evaluate their ability to discriminate between subjects with and without documented life-threatening arrhythmic events. The study group included 104 SQTS patients, 37 of whom had a documented major arrhythmic event at presentation and/or during follow-up. Thirteen ECG features were measured independently by three expert cardiologists; then, the dataset was randomly divided into three subsets (training, validation, and testing). Five shallow neural networks were trained, validated, and tested to predict subject-specific class (non-event/event) using different subsets of ECG features. Additionally, several deep learning and machine learning algorithms, such as Vision Transformer, Swin Transformer, MobileNetV3, EfficientNetV2, ConvNextTiny, Capsule Networks, and logistic regression were trained, validated, and tested directly on the scanned ECG images, without any manual feature extraction. Furthermore, a shallow neural network, a 1-D transformer classifier, and a 1-D CNN were trained, validated, and tested on ECG signals extracted from the aforementioned scanned images. Classification metrics were evaluated by means of sensitivity, specificity, positive and negative predictive values, accuracy, and area under the curve. Results prove that artificial intelligence can help clinicians in better stratifying risk of arrhythmia in patients with SQTS. In particular, shallow neural networks' processing features showed the best performance in identifying patients that will not suffer from a potentially lethal event. This could pave the way for refined ECG-based risk stratification in this group of patients, potentially helping in saving the lives of young and otherwise healthy individuals. [ABSTRACT FROM AUTHOR]

Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0.948. [ABSTRACT FROM AUTHOR]

Big high dimensional data is becoming a challenging field of research. There exist a lot of techniques which infer information. However, because of the curse of dimensionality, a necessary step is the dimensionality reduction (DR) of the information. DR can be performed by linear and nonlinear algorithms. In general, linear algorithms are faster because of less computational burden. A related problem is dealing with time-varying high dimensional data, where the time dependence is due to nonstationary data distribution. Data stream algorithms are not able to project in lower dimensional spaces. Indeed, only linear projections, like principal component analysis (PCA), are used in real time while nonlinear techniques need the whole database (offline). The Growing Curvilinear Component Analysis (GCCA) neural network addresses this problem; it has a self-organized incremental architecture adapting to the changing data distribution and performs simultaneously the data quantization and projection by using CCA, a nonlinear distance-preserving reduction technique. This is achieved by introducing the idea of “seed”, pair of neurons which colonize the input domain, and “bridge”, a novel kind of edge in the manifold graph, which signals the data non-stationarity. Some artificial examples and a real application are given, with a comparison with other existing techniques. [ABSTRACT FROM AUTHOR]

The electrocardiogram (ECG) signal describes the heart's electrical activity, allowing it to detect several health conditions, including cardiac system abnormalities and dysfunctions. Nowadays, most patient medical records are still paper-based, especially those made in past decades. The importance of collecting digitized ECGs is twofold: firstly, all medical applications can be easily implemented with an engineering approach if the ECGs are treated as signals; secondly, paper ECGs can deteriorate over time, therefore a correct evaluation of the patient's clinical evolution is not always guaranteed. The goal of this paper is the realization of an automatic conversion algorithm from paper-based ECGs (images) to digital ECG signals. The algorithm involves a digitization process tested on an image set of 16 subjects, also with pathologies. The quantitative analysis of the digitization method is carried out by evaluating the repeatability and reproducibility of the algorithm. The digitization accuracy is evaluated both on the entire signal and on six ECG time parameters (R-R peak distance, QRS complex duration, QT interval, PQ interval, P-wave duration, and heart rate). Results demonstrate the algorithm efficiency has an average Pearson correlation coefficient of 0.94 and measurement errors of the ECG time parameters are always less than 1 mm. Due to the promising experimental results, the algorithm could be embedded into a graphical interface, becoming a measurement and collection tool for cardiologists. [ABSTRACT FROM AUTHOR]

Every year cardiovascular diseases kill the highest number of people worldwide. Among these, pathologies characterized by sporadic symptoms, such as atrial fibrillation, are difficult to be detected as state-of-the-art solutions, e.g., 12-leads electrocardiogram (ECG) or Holter devices, often fail to tackle these kinds of pathologies. Many portable devices have already been proposed, both in literature and in the market. Unfortunately, they all miss relevant features: they are either not wearable or wireless and their usage over a long-term period is often unsuitable. In addition, the quality of recordings is another key factor to perform reliable diagnosis. The ECG WATCH is a device designed for targeting all these issues. It is inexpensive, wearable (size of a watch), and can be used without the need for any medical expertise about positioning or usage. It is non-invasive, it records single-lead ECG in just 10 s, anytime, anywhere, without the need to physically travel to hospitals or cardiologists. It can acquire any of the three peripheral leads; results can be shared with physicians by simply tapping a smartphone app. The ECG WATCH quality has been tested on 30 people and has successfully compared with an electrocardiograph and an ECG simulator, both certified. The app embeds an algorithm for automatically detecting atrial fibrillation, which has been successfully tested with an official ECG simulator on different severity of atrial fibrillation. In this sense, the ECG WATCH is a promising device for anytime cardiac health monitoring. [ABSTRACT FROM AUTHOR]

In this work we designed and developed a cluster of light expendable radiosondes that can float passively inside warm clouds to study their micro-physical processes. This involves the tracking of both saturated and unsaturated turbulent air parcels. The aim of this new kind of observation system is to obtain Lagrangian statistics of the intense turbulence inside warm clouds and of the lower intensity turbulence that is typical of the air surrounding such clouds. Each radiosonde in a cluster includes an electronic board, which is mounted onto a small, biodegradable balloon filled with a mixture of helium and air. The cluster is able to float inside clouds for a few hours and to measure air temperature, pressure, humidity and the associated position, velocity, acceleration and magnetic field readings of each radiosonde along their trajectory. • In-field measurement system based on a cluster of radiosondes for studying physical processes in warm clouds. • Each radiosonde is able to track turbulent air parcels inside clouds and their surroundings. • Radiosondes measure temperature, pressure, humidity, and provide trajectory data. • Field tests conducted to validate sensor readings against reference values. [ABSTRACT FROM AUTHOR]

Hierarchical clustering is an important tool for extracting information from data in a multi-resolution way. It is more meaningful if driven by data, as in the case of divisive algorithms, which split data until no more division is allowed. However, they have the drawback of the splitting threshold setting. The neural networks can address this problem, because they basically depend on data. The growing hierarchical GH-EXIN neural network builds a hierarchical tree in an incremental (data-driven architecture) and self-organized way. It is a top-down technique which defines the horizontal growth by means of an anisotropic region of influence, based on the novel idea of neighborhood convex hull. It also reallocates data and detects outliers by using a novel approach on all the leaves, simultaneously. Its complexity is estimated and an analysis of its user-dependent parameters is given. The advantages of the proposed approach, with regard to the best existing networks, are shown and analyzed, qualitatively and quantitatively, both in benchmark synthetic problems and in a real application (image recognition from video), in order to test the performance in building hierarchical trees. Furthermore, an important and very promising application of GH-EXIN in two-way hierarchical clustering, for the analysis of gene expression data in the study of the colorectal cancer is described. [ABSTRACT FROM AUTHOR]

Characterization of dynamics inside clouds remains a challenging task for weather forecasting and climate modeling as cloud properties depend on interdependent natural processes at micro- and macro-scales. Turbulence plays an important role in particle dynamics inside clouds; however, turbulence mechanisms are not yet fully understood partly due to the difficulty of measuring clouds at the smallest scales. To address these knowledge gaps, an experimental method for measuring the influence of small-scale turbulence in cloud formation in situ and producing an in-field cloud Lagrangian dataset is being developed by means of innovative ultralight radioprobes. This paper presents the electronic system design along with the obtained results from laboratory and field experiments regarding these compact (diameter ≈30 cm), lightweight (≈20 g), and expendable devices designed to passively float and track small-scale turbulence fluctuations inside warm clouds. The fully customized mini-radioprobe board (5 cm × 5 cm) embeds sensors to measure local fluctuations and transmit data to the ground in near real time. The tests confirm that the newly developed probes perform well, providing accurate information about atmospheric turbulence as referenced in space. The integration of multiple radioprobes allows for a systematic and accurate monitoring of atmospheric turbulence and its impact on cloud formation. [ABSTRACT FROM AUTHOR]