Using spectral continuity to extract breathing rate from heart rate and its applications in sleep physiology.

Introduction: ECG Derived Respiration (EDR) are a set of methods used for extracting the breathing rate from the Electrocardiogram (ECG). Recent studies revealed a tight connection between breathing rate and more specifically the breathing patterns during sleep and several related pathologies. Yet, while breathing rate and more specifically the breathing pattern is recognised as a vital sign it is less employed than Electroencephalography (EEG) and heart rate in sleep and polysomnography studies. Methods: This study utilised open-access data from the ISRUC sleep database to test a novel spectral-based EDR technique (scEDR). In contrast to previous approaches, the novel method emphasizes spectral continuity and not only the power of the different spectral peaks. scEDR is then compared against a more widely used spectral EDR method that selects the frequency with the highest power as the respiratory frequency (Max Power EDR). Results: scEDR yielded improved performance against the more widely used Max Power EDR in terms of accuracy across all sleep stages and the whole sleep. This study further explores the breathing rate across sleep stages, providing evidence in support of a putative sleep stage "REM0" which was previously proposed based on analysis of the Heart Rate Variability (HRV) but not yet widely discussed. Most importantly, this study observes that the frequency distribution of the heart rate during REM0 is closer to REM than other NREM periods even though most of REM0 was previously classified as NREM sleep by sleep experts following either the original or revised sleep staging criteria. Discussion: Based on the results of the analysis, this study proposes scEDR as a potential low-cost and non-invasive method for extracting the breathing rate using the heart rate during sleep with further studies required to validate its accuracy in awake subjects. In this study, the autonomic balance across different sleep stages, including REM0, was examined using HRV as a metric. The results suggest that sympathetic activity decreases as sleep progresses to NREM3 until it reaches a level similar to the awake state in REM through a transition from REM0.

AI-Driven Thoracic X-ray Diagnostics: Transformative Transfer Learning for Clinical Validation in Pulmonary Radiography.

Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients and DenseNet121 achieved an area under the curve (AUC) of 94% in identifying the conditions of pneumothorax and oedema. The model's performance surpassed that of expert radiologists, though further improvements are necessary for diagnosing complex conditions such as emphysema, effusion, and hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) and Named Entity Recognition (NER) demonstrated the potential of natural language processing (NLP) in clinical workflows. The NER system achieved a precision of 92% and a recall of 88%. Sentiment analysis using DistilBERT provided a nuanced understanding of clinical notes, which is essential for refining diagnostic decisions. XGBoost and SHapley Additive exPlanations (SHAP) enhanced feature extraction and model interpretability. Local Interpretable Model-agnostic Explanations (LIME) and occlusion sensitivity analysis further enriched transparency, enabling healthcare providers to trust AI predictions. These AI techniques reduced processing times by 60% and annotation errors by 75%, setting a new benchmark for efficiency in thoracic diagnostics. The research explored the transformative potential of AI in medical imaging, advancing traditional diagnostics and accelerating medical evaluations in clinical settings.

Enhancing Clinical Validation for Early Cardiovascular Disease Prediction through Simulation, AI, and Web Technology.

Cardiovascular diseases (CVDs) remain a major global health challenge and a leading cause of mortality, highlighting the need for improved predictive models. We introduce an innovative agent-based dynamic simulation technique that enhances our AI models' capacity to predict CVD progression. This method simulates individual patient responses to various cardiovascular risk factors, improving prediction accuracy and detail. Also, by incorporating an ensemble learning model and interface of web application in the context of CVD prediction, we developed an AI dashboard-based model to enhance the accuracy of disease prediction and provide a user-friendly app. The performance of traditional algorithms was notable, with Ensemble learning and XGBoost achieving accuracies of 91% and 95%, respectively. A significant aspect of our research was the integration of these models into a streamlit-based interface, enhancing user accessibility and experience. The streamlit application achieved a predictive accuracy of 97%, demonstrating the efficacy of combining advanced AI techniques with user-centered web applications in medical prediction scenarios. This 97% confidence level was evaluated by Brier score and calibration curve. The design of the streamlit application facilitates seamless interaction between complex ML models and end-users, including clinicians and patients, supporting its use in real-time clinical settings. While the study offers new insights into AI-driven CVD prediction, we acknowledge limitations such as the dataset size. In our research, we have successfully validated our predictive proposed methodology against an external clinical setting, demonstrating its robustness and accuracy in a real-world fixture. The validation process confirmed the model's efficacy in the early detection of CVDs, reinforcing its potential for integration into clinical workflows to aid in proactive patient care and management. Future research directions include expanding the dataset, exploring additional algorithms, and conducting clinical trials to validate our findings. This research provides a valuable foundation for future studies, aiming to make significant strides against CVDs.

Prevalence of and risk factors for Enterobius vermicularis infestation in preschool children, West Bank, Palestine, 2015.

BACKGROUND: Enterobius vermicularis (pinworm) infestation is a common condition that primarily affects children. AIMS: The aim of this study was to assess the prevalence of and the risk factors for E. vermicularis infestation in preschool children in north West Bank. METHODS: A cross-sectional study that included the six main governorates in north West Bank was carried out on a sample of 384 preschool children from 86 day-care centres. The perianal cellophane tape method was used to detect E. vermicularis infestation. Parents/guardians of participating children completed a questionnaire to collect information about: demographic characteristics; hygiene behaviour; socioeconomic status; history of previous infestation; and presence of symptoms. Risk factors for infestation were assessed using logistic regression analysis. RESULTS: Of the 384 children, 85 (22.1%) had E. vermicularis infestation. Age (P = 0.04), governorate (P = 0.01), residency (P = 0.03), number of household members (P < 0.001) and washing hands after toilet use (P = 0.01) were significantly associated with E. vermicularis infestation. In the logistic regression analysis, factors that increased the probability of infection were: living in villages (odds ratio (OR) 2.25; 95% confidence interval (CI): 1.01-5.00), living in a household with ≥ nine family members (OR 3.63; 95% CI: 1.42-9.26) and not washing hands after using the toilet (OR 2.4; 95% CI: 1.30-4.40). CONCLUSIONS: E. vermicularis is an important helminthic infestation among preschool children in Palestine. Efforts are needed to ensure the availability of treatment for infected children at primary care centres and to reinforce hygiene behaviour.