Factors associated with COVID-19 in children aged 0 to 15 in Niger, 2020.

On January 30, 2020, the WHO declared COVID-19 a global health emergency. Children were affected in less severe forms. Niger had implemented measures in a context where children were a source of contamination. The aim was to determine the factors associated with COVID-19 in children in Niger from February to August 2020 through an analysis of the national database. We conducted an analytical cross-sectional study including all COVID-19 suspects in the database. We used Excel and Epi Info 7.2.4. software for data extraction and analysis. Frequencies and proportions were calculated, and in a logistic regression, we estimated the ORs of association with their 95% confidence intervals, the factors associated with COVID-19 at the threshold of p<0.05. Of 572 notified cases of suspected COVID-19 in children aged 0-15, 11.36% were positive. The median age of infected children was 10 years [IQR: 5- 13 years]. The male/female sex ratio was 2.1. Children aged 11 to 15 accounted for 49.2%, 61.5% lived in Niamey, 4.6% had comorbidities. The notion of travel was 12.3% and 40% had a notion of contact, 24.4% had a fever, 23.2% had a cough, 18% were hospitalized, and a case-fatality rate of 1.5%. In etiological analysis, the factors associated with COVID-19 were sex ORa=0.51 [0.28-0.93] p=0.028, presence of symptoms ORa=2.29 [1.23-4.25] p=0.008 and notion of contact ORa=0.32 [0.13-0.77] p=0.011. Exposed children were sensitive to COVID-19, and all age groups were affected, with a predominance of males. We recommend barrier measures adapted to young people, and early detection and management of infected children.

Kidney Transplantation in ≤15 kg Children: Outcomes and Prognostic Indicators-A Review of the Organ Procurement and Transplantation Database.

BACKGROUND: Approximately 2500 pediatric patients are awaiting kidney transplantation in the United States, with <5% comprising those ≤15 kg. Transplant in this cohort is often delayed by center-based growth parameters, often necessitating transplantation after the initiation of dialysis. Furthermore, prognostication remains somewhat ambiguous. In this report, we scrutinize the Organ Procurement and Transplantation Network (OPTN) data from 2001 to 2021 to help better understand specific variables impacting graft and patient outcomes in these children. METHODS: The OPTN kidney transplant dataset from 2001 to 2021 was analyzed. Inclusion criteria included age <18 years, weight ≤15 kg, and recipient of primary living donor kidney transplantation (LDKT) or deceased donor kidney transplantation (DDKT). Patient and graft survival probabilities were calculated using the Kaplan-Meier method. The Cox proportional hazards model was used to calculate hazard ratio (HR) and identify variables significantly associated with patient and graft survival. RESULTS: Two thousand one hundred sixty-eight pediatric transplant recipients met inclusion criteria. Patient survival at 1 and 3 years was 98% and 97%, respectively. Graft survival at 1 and 3 years was 95% and 92%, respectively. Dialysis was the sole significant variable impacting both patient and graft survival. Graft survival was further impacted by transplant era, recipient gender and ethnicity, and donor type. Infants transplanted at Age 1 had better graft survival compared with older children, and nephrotic syndrome was likewise associated with a better prognosis. CONCLUSION: Pediatric kidney transplantation is highly successful. The balance between preemptive transplantation, medical optimization, and satisfactory technical parameters seems to suggest a "Goldilocks zone" for many children, favoring transplantation between 1 and 2 years of age.

View adaptive unified self-supervised technique for abdominal organ segmentation.

Automatic abdominal organ segmentation is an essential prerequisite for accurate volumetric analysis, disease diagnosis, and tracking by medical practitioners. However, the deformable shapes, variable locations, overlapping with nearby organs, and similar contrast make the segmentation challenging. Moreover, the requirement of a large manually labeled dataset makes it harder. Hence, a semi-supervised contrastive learning approach is utilized to perform the automatic abdominal organ segmentation. Existing 3D deep learning models based on contrastive learning are not able to capture the 3D context of medical volumetric data along three planes/views: axial, sagittal, and coronal views. In this work, a semi-supervised view-adaptive unified model (VAU-model) is proposed to make the 3D deep learning model as view-adaptive to learn 3D context along each view in a unified manner. This method utilizes the novel optimization function that assists the 3D model to learn the 3D context of volumetric medical data along each view in a single model. The effectiveness of the proposed approach is validated on the three types of datasets: BTCV, NIH, and MSD quantitatively and qualitatively. The results demonstrate that the VAU model achieves an average Dice score of 81.61% which is a 3.89% improvement compared to the previous best results for pancreas segmentation in multi-organ dataset BTCV. It also achieves an average Dice score of 77.76% and 76.76% for the pancreas under the single organ non-pathological NIH dataset, and pathological MSD dataset.

KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models.

MOTIVATION: Answering and solving complex problems using a large language model (LLM) given a certain domain such as biomedicine is a challenging task that requires both factual consistency and logic, and LLMs often suffer from some major limitations, such as hallucinating false or irrelevant information, or being influenced by noisy data. These issues can compromise the trustworthiness, accuracy, and compliance of LLM-generated text and insights. RESULTS: Knowledge Retrieval Augmented Generation ENgine (KRAGEN) is a new tool that combines knowledge graphs, Retrieval Augmented Generation (RAG), and advanced prompting techniques to solve complex problems with natural language. KRAGEN converts knowledge graphs into a vector database and uses RAG to retrieve relevant facts from it. KRAGEN uses advanced prompting techniques: namely graph-of-thoughts (GoT), to dynamically break down a complex problem into smaller subproblems, and proceeds to solve each subproblem by using the relevant knowledge through the RAG framework, which limits the hallucinations, and finally, consolidates the subproblems and provides a solution. KRAGEN's graph visualization allows the user to interact with and evaluate the quality of the solution's GoT structure and logic. AVAILABILITY AND IMPLEMENTATION: KRAGEN is deployed by running its custom Docker containers. KRAGEN is available as open-source from GitHub at: https://github.com/EpistasisLab/KRAGEN.

Productivity loss by cancer stage in patients newly diagnosed with hepatocellular carcinoma: A claims database analysis.

BACKGROUND: New cancer diagnoses are associated with employment decrease, workplace absenteeism, and attributable costs to employers. OBJECTIVE: To estimate the workplace productivity loss in the year following a new diagnosis of early-, intermediate-, or advanced-stage hepatocellular carcinoma (HCC) in commercially insured US adults. METHODS: We conducted a retrospective cohort study using Merative MarketScan commercial claims to identify incident HCC diagnoses from 2010 to 2020. Patients were stratified into early-, intermediate-, or advanced-stage cohorts based on presence of secondary malignancy codes or first treatment received. Mean workdays lost and attributable cost in the year following a new diagnosis were calculated using the Kaplan-Meier sample averages to account for censoring. An exploratory analysis was conducted on subgroups in the early and advanced cohorts to assess productivity loss in patients with and without treatment. RESULTS: Mean workdays lost in the year following a new HCC diagnosis among the early, intermediate, and advanced cohorts was 22.6 days (95% CI = 16.0-29.8), 17.4 days (95% CI = 11.9-23.2), and 19.5 days (95% CI = 15.6-23.6), respectively. Corresponding indirect costs were $6,031(95% CI = $4,270-$7,953), $4,644 (95% CI = $3,176-$6,192), and $5,204 (95% CI = $4,163-$6,298). Early-stage patients without a liver transplant and advanced-stage patients who received systemic therapy had 19.7 (95% CI = 12.7-27.4) and 22.0 (95% CI = 16.6-27.7) mean workdays lost, respectively. CONCLUSIONS: Productivity loss varies by stage and appears to be higher in early-stage patients who receive more intensive treatments in the first year following a new HCC diagnosis.

Use of methylphenidate and reporting of valvular heart disease: Global pharmacovigilance analysis in children and adults.

INTRODUCTION: Methylphenidate (MPH) is a common treatment of attention-deficit/hyperactivity disorder (ADHD). Concern has been raised regarding its cardiovascular safety, partly in relation with its micromolar affinity for the 5-HT2B receptor, whose activation may result in valvular heart disease (VHD). METHODS: To explore the association between the use of MPH and VHD reporting, we performed a disproportionality analysis within the WHO global safety database (VigiBase) using data, since inception until March 6th 2024, from: (i) the full database and (ii) different age groups (children/adolescents 6-17 years; adults 18-64 years). To avoid competition bias, safety reports with amphetamine-like appetite suppressants were excluded. Disproportionality was expressed using reporting odds-ratio (ROR) and its 95% confidence interval (CI). RESULTS: Of 29 129 spontaneous reports with MPH, 23 VHD cases (7.9 per 10 000 reports) were identified, including 13 adults and 10 children. Most cases concerned injury on the mitral valve. A disproportionate reporting was observed overall (ROR 1.6, 95% CI 1.1-2.4). Analysis according to age group found that disproportionality in VHD reporting was found in adults only (ROR 2.7, 95% CI 1.6-4.7) but not in children/adolescents (ROR 1.7, 95% CI 0.9-3.2). Furthermore, amongst MPH users only, VHD reporting was higher in adults compared to children (ROR 2.7, 95% CI 1.2-6.3). CONCLUSION: VHD reporting appears rare with MPH compared to other adverse events and is increased in adults only. Our findings support a potential safety signal of VHD in adults exposed to MPH. A risk in that population cannot be excluded and requires further assessment.

Data-Driven Identification of Potentially Successful Intervention Implementations Using 5 Years of Opioid Prescribing Data: Retrospective Database Study.

BACKGROUND: We have previously demonstrated that opioid prescribing increased by 127% between 1998 and 2016. New policies aimed at tackling this increasing trend have been recommended by public health bodies, and there is some evidence that progress is being made. OBJECTIVE: We sought to extend our previous work and develop a data-driven approach to identify general practices and clinical commissioning groups (CCGs) whose prescribing data suggest that interventions to reduce the prescribing of opioids may have been successfully implemented. METHODS: We analyzed 5 years of prescribing data (December 2014 to November 2019) for 3 opioid prescribing measures-total opioid prescribing as oral morphine equivalent per 1000 registered population, the number of high-dose opioids prescribed per 1000 registered population, and the number of high-dose opioids as a percentage of total opioids prescribed. Using a data-driven approach, we applied a modified version of our change detection Python library to identify reductions in these measures over time, which may be consistent with the successful implementation of an intervention to reduce opioid prescribing. This analysis was carried out for general practices and CCGs, and organizations were ranked according to the change in prescribing rate. RESULTS: We identified a reduction in total opioid prescribing in 94 (49.2%) out of 191 CCGs, with a median reduction of 15.1 (IQR 11.8-18.7; range 9.0-32.8) in total oral morphine equivalence per 1000 patients. We present data for the 3 CCGs and practices demonstrating the biggest reduction in opioid prescribing for each of the 3 opioid prescribing measures. We observed a 40% proportional drop (8.9% absolute reduction) in the regular prescribing of high-dose opioids (measured as a percentage of regular opioids) in the highest-ranked CCG (North Tyneside); a 99% drop in this same measure was found in several practices (44%-95% absolute reduction). Decile plots demonstrate that CCGs exhibiting large reductions in opioid prescribing do so via slow and gradual reductions over a long period of time (typically over a period of 2 years); in contrast, practices exhibiting large reductions do so rapidly over a much shorter period of time. CONCLUSIONS: By applying 1 of our existing analysis tools to a national data set, we were able to identify rapid and maintained changes in opioid prescribing within practices and CCGs and rank organizations by the magnitude of reduction. Highly ranked organizations are candidates for further qualitative research into intervention design and implementation.

Prognostic effect of triglyceride glucose-related parameters on all-cause and cardiovascular mortality in the United States adults with metabolic dysfunction-associated steatotic liver disease.

BACKGROUNDS: Insulin resistance (IR) plays a vital role in the pathogenesis of the metabolic dysfunction-associated steatotic liver disease (MASLD). However, it remains unclear whether triglyceride-glucose (TyG) related parameters, which serve as useful biomarkers to assess IR, have prognostic effects on mortality outcomes of MASLD. METHODS: Participants in the National Health and Nutrition Examination Survey (NHANES) database from 1999 to 2018 years were included. TyG and its related parameters [TyG-waist circumference (TyG-WC) and TyG-waist to height ratio (TyG-WHtR)] were calculated. Kaplan-Meier curves, Cox regression analysis, and restricted cubic splines (RCS) were conducted to evaluate the association between TyG-related indices with the all-cause and cardiovascular mortality of adults with MASLD. The concordance index (C-index) was used to evaluate the prediction accuracy of TyG-related indices. RESULTS: A total of 8208 adults (4209 men and 3999 women, median age 49.00 years) with MASLD were included in this study. Multivariate-adjusted Cox regression analysis revealed that high quartile levels of TyG-related indices were significantly associated with the all-cause mortality of participants with MASLD [TyGadjusted hazard ratio (aHR) = 1.25, 95% confidence interval (CI) 1.05-1.50, P = 0.014; TyG-WCaHR for all-cause mortality = 1.28, 95% CI 1.07-1.52, P = 0.006; TyG-WHtRaHR for all-cause mortality = 1.50, 95% CI 1.25-1.80, P < 0.001; TyG-WCaHR for cardiovascular mortality = 1.81, 95% CI 1.28-2.55, P = 0.001; TyG-WHtRaHR for cardiovascular mortality = 2.22, 95% CI 1.55-3.17, P < 0.001]. The C-index of TyG-related indices for predicting all-cause mortality was 0.563 for the TyG index, 0.579 for the TyG-WC index, and 0.585 for the TyG-WHtR index, respectively. Regarding cardiovascular mortality, the C-index was 0.561 for the TyG index, 0.607 for the TyG-WC index, and 0.615 for the TyG-WHtR index, respectively. Nonlinear trends were observed between TyG and TyG-WC indices with all-cause mortality of MASLD (P < 0.001 and = 0.012, respectively). A non-linear relationship was observed between the TyG index and cardiovascular mortality of MASLD (P = 0.025). Subgroup analysis suggested that adults aged < 65 years old and those without comorbidities were more sensitive to the mortality prediction of TyG-related indices. CONCLUSION: Findings of this study highlight the predictive value of TyG-related indices, especially the TyG-WHtR index, in the mortality outcomes of adults with MASLD. TyG-related indices would be surrogate biomarkers for the clinical management of MASLD.

Evaluating the risk of return to the operating room across all elective orthopaedic procedures.

BACKGROUND: Although elective procedures have life-changing potential, all surgeries come with an inherent risk of reoperation. There is a gap in knowledge investigating the risk of reoperation across orthopaedics. We aimed to identify the elective orthopaedic procedures with the highest rate of unplanned reoperation and the reasons for these procedures having such high reoperation rates. METHODS: Patients in the NSQIP database were identified using CPT and ICD-10 codes. We isolated 612,815 orthopaedics procedures from 2018 to 2020 and identified the 10 CPT codes with the greatest rate of unplanned return to the operating room. For each index procedure, we identified the ICD-10 codes for the reoperation procedure and categorized them into infection, mechanical failure, fracture, wound disruption, hematoma or seroma, nerve pathology, other, and unspecified. RESULTS: Below knee amputation (BKA) (CPT 27880) had the highest reoperation rate of 6.92% (37 of 535 patients). Posterior-approach thoracic (5.86%) or cervical (4.14%) arthrodesis and cervical laminectomy (3.85%), revision total hip arthroplasty (5.23%), conversion to total hip arthroplasty (4.33%), and revision shoulder arthroplasty (4.22%) were among the remaining highest reoperation rates. The overall leading causes of reoperation were infection (30.1%), mechanical failure (21.1%), and hematoma or seroma (9.4%) for the 10 procedures with the highest reoperation rates. CONCLUSIONS: This study successfully identified the elective orthopaedic procedures with the highest 30-day return to OR rates. These include BKA, posterior thoracic and cervical spinal arthrodesis, revision hip arthroplasty, revision total shoulder arthroplasty, and cervical laminectomy. With this data, we can identify areas across orthopaedics in which revising protocols may improve patient outcomes and limit the burden of reoperations on patients and the healthcare system. Future studies should focus on the long-term physical and financial impact that these reoperations may have on patients and hospital systems. LEVEL OF CLINICAL EVIDENCE: IV.

Patterns of kidney function and risk assessment in a nationwide laboratory database: the Brazilian CHECK-CKD study.

BACKGROUND: Chronic kidney disease (CKD) is a global health problem with rising prevalence, morbidity, mortality, and associated costs. Early identification and risk stratification are key to preventing progression to kidney failure. However, there is a paucity of data on practice patterns of kidney function assessment to guide the development of improvement strategies, particularly in lower-income countries. METHODS: A retrospective observational analysis was conducted in a nationwide laboratory database in Brazil. We included all adult patients with at least one serum creatinine assessment between June 2018 and May 2021. Our primary objective was to determine the proportion of patients with estimated glomerular filtration rate (eGFR) evaluations accompanied by predicted levels of urinary albumin-to-creatinine ratio (pACR) assessments within 12 months. RESULTS: Out of 4,5323,332 serum creatinine measurements, 42% lacked pACR measurements within 12 months. Approximately 10.8% of tests suggested CKD, mostly at stage 3a. The proportion of serum creatinine exams paired with pACR assessment varied according to the CKD stage. Internal Medicine, Cardiology, and Obstetrics/Gynecology were the specialties requesting most of the creatinine tests. Nephrology contributed with only 1.1% of serum creatinine requests for testing. CONCLUSION: Our findings reveal that a significant proportion of individuals with a creatinine test lack an accompanying urinary albuminuria measurement in Brazil, contrary to the recommendations of the international guidelines. Non-Nephrologists perform most kidney function evaluations, even among patients with presumable advanced CKD. This highlights the urge to incorporate in clinical practice the early detection of CKD and to encourage more collaborative multidisciplinary care to improve CKD management.

Association Between Geriatric Nutrition Risk Index and 90-Day Mortality in Older Adults with Chronic Obstructive Pulmonary Disease: a Retrospective Cohort Study.

Background: Malnutrition adversely affects prognosis in various medical conditions, but its implications in older adults with Chronic Obstructive Pulmonary Disease (COPD) in the ICU are underexplored. The geriatric nutritional risk index (GNRI) is a novel tool for assessing malnutrition risk. This study investigates the association between GNRI and 90-day mortality in this population. Methods: We selected older adults with COPD admitted to the ICU from Medical Information Mart for Intensive Care (MIMIC)-IV 2.2 database. A total of 666 patients were categorized into four groups based on their GNRI score: normal nutrition (>98), mild malnutrition (92-98), moderate malnutrition (82-91), and severe malnutrition (≤81) groups. We employed a restricted cubic spline (RCS) analysis to assess the presence of a curved relationship between them and to investigate any potential threshold saturation effect. Results: In multivariate Cox regression analyses, compared with individuals had normal nutrition (GNRI in Q4 >98), the adjusted HR values for GNRI in Q3 (92-98), Q2 (82-91), and Q1 (≤81) were 1.81 (95% CI: 1.27-2.58, p=0.001), 1.23 (95% CI: 0.84-1.79, p=0.296), 2.27 (95% CI: 1.57-3.29, p<0.001), respectively. The relationship between GNRI and 90-day mortality demonstrates an L-shaped curve (p=0.016), with an approximate inflection point at 101.5. Conclusion: These findings imply that GNRI is a useful prognostic tool in older adults with COPD in the ICU. An L-shaped relationship was observed between GNRI and 90-day mortality in these patients.

Multiscale dilated convolutional neural network for Atrial Fibrillation detection.

Atrial Fibrillation (AF), a type of heart arrhythmia, becomes more common with aging and is associated with an increased risk of stroke and mortality. In light of the urgent need for effective automated AF monitoring, existing methods often fall short in balancing accuracy and computational efficiency. To address this issue, we introduce a framework based on Multi-Scale Dilated Convolution (AF-MSDC), aimed at achieving precise predictions with low cost and high efficiency. By integrating Multi-Scale Dilated Convolution (MSDC) modules, our model is capable of extracting features from electrocardiogram (ECG) datasets across various scales, thus achieving an optimal balance between precision and computational savings. We have developed three MSDC modules to construct the AF-MSDC framework and assessed its performance on renowned datasets, including the MIT-BIH Atrial Fibrillation Database and Physionet Challenge 2017. Empirical results unequivocally demonstrate that our technique surpasses existing state-of-the-art (SOTA) methods in the AF detection domain. Specifically, our model, with only a quarter of the parameters of a Residual Network (ResNet), achieved an impressive sensitivity of 99.45%, specificity of 99.64% (on the MIT-BIH AFDB dataset), and an [Formula: see text] score of 85.63% (on the Physionet Challenge 2017 AFDB dataset). This high efficiency makes our model particularly suitable for integration into wearable ECG devices powered by edge computing frameworks. Moreover, this innovative approach offers new possibilities for the early diagnosis of AF in clinical applications, potentially improving patient quality of life and reducing healthcare costs.

Introducing Isotòpia: A stable isotope database for Classical Antiquity.

We present Isotòpia, an open-access database compiling over 36,000 stable isotope measurements (δ13C, δ15N, δ18O, δ34S, 87Sr/86Sr, 206Pb/204Pb, 207Pb/204Pb, 208Pb/204Pb, 207Pb/206Pb, and 208Pb/206Pb) on human, animal, and plant bioarchaeological remains dating to Classical Antiquity (approximately 800 BCE - 500 CE). These were recovered from different European regions, particularly from the Mediterranean. Isotòpia provides a comprehensive characterisation of the isotopic data, encompassing various historical, archaeological, biological, and environmental variables. Isotòpia is a resource for meta-analytical research of past human activities and paleoenvironments. The database highlights data gaps in isotopic classical archaeology, such as the limited number of isotopic measurements available for plants and animals, limited number of studies on spatial mobility, and spatial heterogeneity of isotopic research. As such, we emphasise the necessity to address and fill these gaps in order to unlock the reuse potential of this database.

Financial burden in a US cohort of patients with HCC.

BACKGROUND: High financial burden for patients has been reported for multiple types of cancer, but there are limited data in those with HCC. We aimed to describe the financial burden for patients diagnosed with HCC and identify correlates of high financial burden. METHODS: We used the IQVIA PharMetrics Plus for Academics database to identify commercially insured patients diagnosed with HCC between 2006 and 2021. Patient financial liability was defined as the difference between allowed and paid amounts from adjudicated insurance claims. We reported total and HCC-related financial liabilities (i.e., cost for HCC-related claims), with high total financial liability defined as ≥$3000 annually and high HCC-related financial liability as ≥$1000 annually. We used multivariable logistic regression modeling to identify factors associated with high total and HCC-related financial liability. RESULTS: Among 11,609 patients with HCC, the median total financial liability during the year after HCC diagnosis was $2955 (Q1-Q3: $972-$6293). Nearly half (45%) of patients experienced high total financial liability, with the greatest liability incurred in the 3-month period immediately following HCC diagnosis. Older age, increased comorbidity, and cirrhosis-related complications were associated with higher total patient liability. Patient liability also varied by type of HCC treatment, with systemic therapy and liver transplantation having the highest financial liability in multivariable analysis. However, only 66.7% of the patients experienced HCC-related liability. CONCLUSIONS: Patients with HCC experience significant financial liability underscoring a need for price transparency as well as financial counseling in this population.

VOLKSMED Database: A Source for Forgotten Wound Healing Plants in Austrian Folk Medicine.

The global increase in the incidence of wounds is concerning and fuels the search for new treatment options. The use of traditional medicinal plants in wound healing represents an appreciated available therapeutic possibility. This work introduces the VOLKSMED database, which contains plants and other materials used in Austrian folk medicine, either as monographs or mixtures. This work focuses on the monographs of the database. Concerning wound healing, Hypericum sp., Arnica montana, Calendula officinalis, Plantago sp., and Malva sp. are the most commonly used plants. The focus of this paper is set on selected lesser-known plants (Abies alba, Anthyllis vulneraria, Brassica sp., Gentiana sp., Larix decidua, Picea abies, Sambucus sp., Sanicula europaea) and their status quo in literature concerning wound healing. A systematic search using the databases SciFinder, SCOPUS, and PubMed yielded substantial evidence for the wound healing potential of Brassica sp., Gentiana sp., the Pinaceae A. abies, L. decidua, and P. abies, as well as Sambucus nigra. In vivo and clinical studies substantiate their use in Austrian folk medicine. According to the literature, especially A. vulneraria, Sambucus racemosa, and S. europaea would be worth investigating in-depth since data concerning their wound healing effects - even though scarce - are convincing. In conclusion, the VOLKSMED database contains promising opportunities for further treatment options in the field of wound healing. Future research should consider the listed plants to support their traditional use in Austrian folk medicine and possibly promote the implementation of old knowledge in modern medicine.

xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features.

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

An enhanced speech emotion recognition using vision transformer.

In human-computer interaction systems, speech emotion recognition (SER) plays a crucial role because it enables computers to understand and react to users' emotions. In the past, SER has significantly emphasised acoustic properties extracted from speech signals. The use of visual signals for enhancing SER performance, however, has been made possible by recent developments in deep learning and computer vision. This work utilizes a lightweight Vision Transformer (ViT) model to propose a novel method for improving speech emotion recognition. We leverage the ViT model's capabilities to capture spatial dependencies and high-level features in images which are adequate indicators of emotional states from mel spectrogram input fed into the model. To determine the efficiency of our proposed approach, we conduct a comprehensive experiment on two benchmark speech emotion datasets, the Toronto English Speech Set (TESS) and the Berlin Emotional Database (EMODB). The results of our extensive experiment demonstrate a considerable improvement in speech emotion recognition accuracy attesting to its generalizability as it achieved 98%, 91%, and 93% (TESS-EMODB) accuracy respectively on the datasets. The outcomes of the comparative experiment show that the non-overlapping patch-based feature extraction method substantially improves the discipline of speech emotion recognition. Our research indicates the potential for integrating vision transformer models into SER systems, opening up fresh opportunities for real-world applications requiring accurate emotion recognition from speech compared with other state-of-the-art techniques.

A bidirectional autoimmune cluster between vitiligo and rheumatoid arthritis: a large-scale population-based study.

A knowledge gap exists regarding the association between vitiligo and rheumatoid arthritis (RA) due to the absence of large-scale cohort studies designed to investigate this association. To investigate the bidirectional epidemiological association between vitiligo and RA. A population-based study was conducted using Clalit Health Services (CHS) database (2002-2019) using both a cohort study and a case-control study design. Adjusted hazard ratio (HR) and odds ratio (OR) were calculated by multivariate Cox and logistic regressions, respectively. Overall, 20,851 vitiligo patients and 102,475 controls were included. The incidence of new-onset RA was 4.1 (95% CI 3.0-5.4) and 2.9 (95% CI 2.4-3.3) cases per 10,000 person-years among patients with vitiligo and controls, respectively. Patients with vitiligo had a significantly increased risk of developing new-onset RA (adjusted HR, 1.44; 95% confidence interval [CI], 1.02-2.02, P = 0.036). The likelihood of having vitiligo was significantly elevated after a preexisting diagnosis of RA (adjusted OR, 1.67; 95% CI, 1.38-2.03; P < 0.001). Relative to the remaining patients with vitiligo, those with vitiligo and comorbid RA demonstrated an elevated risk of all-cause mortality (adjusted HR, 1.61; 95% CI, 1.03-2.51; P = 0.037). Our study confirms the bidirectional association between vitiligo and RA. Physicians treating patients with vitiligo should be aware of the association in clinical practice.

The Hospital Burden of Flu in Italy: a retrospective study on administrative data from season 2014-2015 to 2018-2019.

BACKGROUND: Every year in Italy, influenza affects about 4 million people. Almost 5% of them are hospitalised. During peak illness, enormous pressure is placed on healthcare and economic systems. This study aims to quantify the clinical and economic burden of severe influenza during 5 epidemic seasons (2014-2019) from administrative claims data. METHODS: Patients hospitalized with a diagnosis of influenza between October 2014, and April 2019, were analyzed. Clinical characteristics and administrative information were retrieved from health-related Administrative Databases (ADs) of 4 Italian Local Health Units (LHUs). The date of first admission was set as the Index Date (ID). A follow-up period of six months after ID was considered to account for complications and re-hospitalizations, while a lookback period (2 years before ID) was set to assess the prevalence of underlying comorbidities. RESULTS: Out of 2,333 patients with severe influenza, 44.1% were adults ≥ 65, and 25.6% young individuals aged 0-17. 46.8% had comorbidities (i.e., were at risk), mainly cardiovascular and metabolic diseases (45.3%), and chronic conditions (24.7%). The highest hospitalization rates were among the elderly (≥ 75) and the young individuals (0-17), and were 37.6 and 19.5/100,000 inhabitants/year, respectively. The average hospital stay was 8 days (IQR: 14 - 4). It was higher for older individuals (≥ 65 years, 11 days, [17 - 6]) and for those with comorbidities (9 days, [16 - 6]), p-value < 0.001. Similarly, mortality was higher in elderly and those at risk (p-value < 0.001). Respiratory complications occurred in 12.7% of patients, and cardiovascular disorders in 5.9%. Total influenza-related costs were €9.7 million with hospitalization accounting for 95% of them. 47.3% of hospitalization costs were associated with individuals ≥ 65 and 52.9% with patients at risk. The average hospitalisation cost per patient was € 4,007. CONCLUSIONS: This retrospective study showed that during the 2014-2019 influenza seasons in Italy, individuals of extreme ages and those with pre-existing medical conditions, were more likely to be hospitalized with severe influenza. Together with complications and ageing, they worsen patient's outcome and may lead to a prolonged hospitalization, thus increasing healthcare utilization and costs. Our data generate real-world evidence on the burden of influenza, useful to inform public health decision-making.