Artificial Intelligence ECG Analysis in Patients with Short QT Syndrome to Predict Life-Threatening Arrhythmic Events.

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.

Persistence of DNA from canine parvovirus modified-live virus in canine tissues.

Canine parvovirus (CPV-2) modified-live virus vaccine strain can replicate in lymphoid tissues and intestinal mucosa after administration, being shed through canine faeces. Detection of vaccine strains has been reported in the bloodstream and faeces, potentially interfering with molecular diagnostic tests. The persistence of these strains in canine tissues has not yet been described. With this aim, canine tissues were tested during a molecular survey to screen for the presence of canine enteric viruses. Tissue samples from 165 dead dogs were tested by a conventional PCR assay. Positive samples and five commercial vaccines were subjected to sequence analysis. Vaccinal strains were detected and virus load was measured by using a set of real-time PCR assays using minor-groove binder (MGB) probes. Seventy-five dogs (45.4%) tested positive for CPV-2. Strains from 70 dogs were characterised as field variants. The presence of CPV sequences of vaccine origin was observed in the spleen, intestine, and mesenteric lymph nodes of five young dogs. Vaccinal strains were detected from 12 to 24 days after the last vaccine administration. Viral loads comprised between 6.3 × 102 and 9.95 × 104 DNA copies/10 µl of template. This study confirms that CPV vaccinal strains can be detected in canine tissues after vaccination, so post-mortem diagnosis of CPV infection needs further molecular analyses to assess the viral type (vaccine or field strains). The present study updates the current information on the persistence of CPV vaccine strains in canine tissues and their possible interference with molecular assays.

Study on the Canine Adenovirus Type 1 (CAdV-1) Infection in Domestic Dogs in Southern Italy.

Canine adenovirus type 1 (CAdV-1) is the causative agent of a systemic and potentially fatal viral disease of domestic and wild canids. In Italy, CAdV-1 infection has also been occasionally described in dogs, but information on the epidemiology and its genomic features is still limited. A study was conducted on 291 dogs suspected of infectious gastrointestinal disease. Samples collected from dogs in southern Italy between 2017 and 2020 were analyzed. Virological and histopathological assays were carried out. The presence of CAdVs and other canine viral enteropathogens was investigated, and sequence and phylogenetic analyses were performed. CAdV-1 was detected in six (2.1%) dead stray dogs alone or in mixed infections with other viruses. Gross lesions and histopathological findings referred to CAdV infection were observed, also involving the central nervous system tissues. All inoculated samples were successfully isolated. Sequence analysis evidenced divergences with the circulating strains previously described in Italy and a closer relation with older CAdV-1 strains collected from other countries, suggesting a genetic heterogeneity of CAdV-1 in Italy. The evidence of the circulation of CAdV-1 and its genomic features allows us to have more in-depth knowledge of the epidemiology and evolution of the CAdV-1 genomic variants.

Development and Validation of an Algorithm for the Digitization of ECG Paper Images.

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.

Identification and Molecular Characterization of a Divergent Asian-like Canine Parvovirus Type 2b (CPV-2b) Strain in Southern Italy.

Canine parvovirus type 2 (CPV-2) is an infectious agent relevant to domestic and wild carnivorans. Recent studies documented the introduction and spread of CPV-2c strains of Asian origin in the Italian canine population. We investigated tissue samples from a puppy collected during necropsy for the presence of viral enteropathogens and all samples tested positive only for CPV-2. The full coding sequence of a CPV-2b (VP2 426Asp) strain was obtained. This virus was related to CPV-2c strains of Asian origin and unrelated to European CPV-2b strains. The sequence had genetic signatures typical of Asian strains (NS1: 60Val, 545Val, 630Pro; VP2: 5Gly, 267Tyr, 324Ile) and mutations rarely reported in Asian CPV-2b strains (NS1: 588N; VP2: 370Arg). Phylogenetic analyses placed this strain in well-supported clades, including Asian CPV-2c-like strains, but always as a basal, single-sequence long branch. No recombination was observed for this strain, and we speculate that it could have originated from an Asian CPV-2c-like strain that acquired the 426Asp mutation. This study reports the first evidence of an Asian-like CPV-2b strain in Italy, confirming the occurrence of continuous changes in the global CPV-2 spread. Since positive convergent mutations complicate data interpretation, a combination of phylogenetic and mutation pattern analyses is crucial in studying the origin and evolution of CPV-2 strains.

External validation of a deep-learning model to predict severe acute kidney injury based on urine output changes in critically ill patients.

OBJECTIVES: The purpose of this study was to externally validate algorithms (previously developed and trained in two United States populations) aimed at early detection of severe oliguric AKI (stage 2/3 KDIGO) in intensive care units patients. METHODS: The independent cohort was composed of 10'596 patients from the university hospital ICU of Amsterdam (the "AmsterdamUMC database") admitted to their intensive care units. In this cohort, we analysed the accuracy of algorithms based on logistic regression and deep learning methods. The accuracy of investigated algorithms had previously been tested with electronic intensive care unit (eICU) and MIMIC-III patients. RESULTS: The deep learning model had an area under the ROC curve (AUC) of 0,907 (± 0,007SE) with a sensitivity and specificity of 80% and 89%, respectively, for identifying oliguric AKI episodes. Logistic regression models had an AUC of 0,877 (± 0,005SE) with a sensitivity and specificity of 80% and 81%, respectively. These results were comparable to those obtained in the two US populations upon which the algorithms were previously developed and trained. CONCLUSION: External validation on the European sample confirmed the accuracy of the algorithms, previously investigated in the US population. The models show high accuracy in both the European and the American databases even though the two cohorts differ in a range of demographic and clinical characteristics, further underlining the validity and the generalizability of the two analytical approaches.

Antimicrobial Resistance (AMR) of Bacteria Isolated from Dogs with Canine Parvovirus (CPV) Infection: The Need for a Rational Use of Antibiotics in Companion Animal Health.

Canine parvovirus type 2 (CPV-2) represents a major viral threat to dogs. Considering the potential effects of pets on antimicrobial resistance, information on the CPV and associated bacterial co-infections is limited. The aim of this study was to analyze the antimicrobial susceptibility and multidrug-resistance profiles of bacterial species from tissue samples of dogs with canine parvovirus infection. A set of PCR assays and sequence analyses was used for the detection and the molecular characterization of the CPV strains and other enteric viruses. Bacterial isolation, the determination of antimicrobial susceptibility via the disk diffusion method, and the determination of the minimum inhibitory concentration were performed. The detection of ß-lactamase genes and toxin genes for specific bacteria was also carried out. CPV infection was confirmed in 23 dogs. Forty-three bacterial strains were isolated and all showed phenotypic resistance. Seventeen multidrug-resistant bacteria and bacteria with high resistance to third- and fourth-generation cephalosporins and metronidazole were detected. Almost 50% of the isolated Enterobacteriaceae were positive for at least one ß-lactamase gene, with the majority carrying more genes as well. The evidence for multi-resistant bacteria with the potential for intra- or cross-species transmission should be further considered in a One Health approach.

A Comparison of Deep Learning Techniques for Arterial Blood Pressure Prediction.

Continuous vital signal monitoring is becoming more relevant in preventing diseases that afflict a large part of the world's population; for this reason, healthcare equipment should be easy to wear and simple to use. Non-intrusive and non-invasive detection methods are a basic requirement for wearable medical devices, especially when these are used in sports applications or by the elderly for self-monitoring. Arterial blood pressure (ABP) is an essential physiological parameter for health monitoring. Most blood pressure measurement devices determine the systolic and diastolic arterial blood pressure through the inflation and the deflation of a cuff. This technique is uncomfortable for the user and may result in anxiety, and consequently affect the blood pressure and its measurement. The purpose of this paper is the continuous measurement of the ABP through a cuffless, non-intrusive approach. The approach of this paper is based on deep learning techniques where several neural networks are used to infer ABP, starting from photoplethysmogram (PPG) and electrocardiogram (ECG) signals. The ABP was predicted first by utilizing only PPG and then by using both PPG and ECG. Convolutional neural networks (ResNet and WaveNet) and recurrent neural networks (LSTM) were compared and analyzed for the regression task. Results show that the use of the ECG has resulted in improved performance for every proposed configuration. The best performing configuration was obtained with a ResNet followed by three LSTM layers: this led to a mean absolute error (MAE) of 4.118 mmHg on and 2.228 mmHg on systolic and diastolic blood pressures, respectively. The results comply with the American National Standards of the Association for the Advancement of Medical Instrumentation. ECG, PPG, and ABP measurements were extracted from the MIMIC database, which contains clinical signal data reflecting real measurements. The results were validated on a custom dataset created at Neuronica Lab, Politecnico di Torino.

Anytime ECG Monitoring through the Use of a Low-Cost, User-Friendly, Wearable Device.

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.

Helminth Infection of the Loggerhead Sea Turtle Caretta caretta along the Coasts of Sicily and the North West Adriatic Sea.

We provide new data on the presence of helminth parasites in 64 individual loggerhead sea turtles Caretta caretta stranded along the coasts of Sicily and the northwest Adriatic Sea between June 2014 and August 2016. The necropsy examination revealed 31 individuals (48.4%) positive for endoparasites, showing a greater prevalence of trematodes than nematodes. In particular, seven species and a single genus of Trematoda (Hapalotrema) and a single species and genus of Nematoda (Kathlania) were identified. Among the Digenea flukes the species with the highest prevalence of infection were Rhytidodes gelatinosus (34.6%) and Hapalotrema sp. (33.3%), while among the Nematoda they were Kathlania sp. (33.3%) and Sulcascaris sulcata (33.3%). Analysis of variance (ANOVA) was applied among the recovery sites of the stranded loggerhead sea turtles and prevalence of endoparasites was used to highlight any relationship between the parasites and the origin of the hosts. ANOVA showed significant differences (p < 0.001) among the data used.

A deep-learning model to continuously predict severe acute kidney injury based on urine output changes in critically ill patients.

BACKGROUND: Acute Kidney Injury (AKI), a frequent complication of pateints in the Intensive Care Unit (ICU), is associated with a high mortality rate. Early prediction of AKI is essential in order to trigger the use of preventive care actions. METHODS: The aim of this study was to ascertain the accuracy of two mathematical analysis models in obtaining a predictive score for AKI development. A deep learning model based on a urine output trends was compared with a logistic regression analysis for AKI prediction in stages 2 and 3 (defined as the simultaneous increase of serum creatinine and decrease of urine output, according to  the Acute Kidney Injury Network (AKIN) guidelines). Two retrospective datasets including 35,573 ICU patients were analyzed. Urine output data were used to train and test the logistic regression and the deep learning model. RESULTS: The deep learning model defined an area under the curve (AUC) of 0.89 (± 0.01), sensitivity = 0.8 and specificity = 0.84, which was higher than the logistic regression analysis. The deep learning model was able to predict 88% of AKI cases more than 12 h before their onset: for every 6 patients identified as being at risk of AKI by the deep learning model, 5 experienced the event. On the contrary, for every 12 patients not considered to be at risk by the model, 2 developed AKI. CONCLUSION: In conclusion, by using urine output trends, deep learning analysis was able to predict AKI episodes more than 12 h in advance, and with a higher accuracy than the classical urine output thresholds. We suggest that this algorithm could be integrated in the ICU setting to better manage, and potentially prevent, AKI episodes.

An enormous sulfur isotope excursion indicates marine anoxia during the end-Triassic mass extinction.

The role of ocean anoxia as a cause of the end-Triassic marine mass extinction is widely debated. Here, we present carbonate-associated sulfate δ34S data from sections spanning the Late Triassic-Early Jurassic transition, which document synchronous large positive excursions on a global scale occurring in ~50 thousand years. Biogeochemical modeling demonstrates that this S isotope perturbation is best explained by a fivefold increase in global pyrite burial, consistent with large-scale development of marine anoxia on the Panthalassa margin and northwest European shelf. This pyrite burial event coincides with the loss of Triassic taxa seen in the studied sections. Modeling results also indicate that the pre-event ocean sulfate concentration was low (<1 millimolar), a common feature of many Phanerozoic deoxygenation events. We propose that sulfate scarcity preconditions oceans for the development of anoxia during rapid warming events by increasing the benthic methane flux and the resulting bottom-water oxygen demand.

The GH-EXIN neural network for hierarchical clustering.

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.

The Growing Curvilinear Component Analysis (GCCA) neural network.

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.

Molecular typing of a novel canine parvovirus type 2a mutant circulating in Italy.

Canine parvovirus (CPV) is the etiological agent of a severe viral disease of dogs. After its emergence in late 1970s, the CPV original type (CPV-2) was rapidly and totally replaced by three antigenic variants named CPV-2a, CPV-2b and CPV-2c. CPV has an evolutionary rate nearest to those of RNA viruses, with consequences on disease diagnosis and epidemiology. This paper reports the molecular characterization of eight CPV-2a strains collected from dogs in Italy in 2016-2017. Genetic analysis was conducted on a CPV genomic region encompassing both open reading frames (ORFs) encoding for nonstructural (NS1-NS2) and structural proteins (VP1-VP2). Sequence analysis indicates new and unreported sequence changes, mainly affecting the VP2 gene, which included the mutation Tyr324Leu. This study represents the first evidence of a new CPV-2a mutant (VP2 324Leu) and illustrates the importance of a continuous molecular survey in order to obtain more information on effective spread of new CPV mutants.