Search Results (1,401)

Objective—To identify effective data analytics and machine learning solutions that can help in the decision-making process in the medical domain and contribute to the understanding of COVID-19 disease. In this study, we analyze data from anonymized electronic medical records of 4711 patients with COVID-19 disease admitted to hospital in Atlanta. Methods—We used random forest, LightGBM, XGBoost, CatBoost, KNN, SVM, logistic regression, and MLP neural network models in this work. The models are evaluated depending on the type of prediction by relevant metrics, especially accuracy, F1-score, and ROC AUC score. Another aim of the work was to find out which factors most affected severity and mortality risk among the patients. To identify the important features, different statistical methods were used, as well as LASSO regression, and explainable artificial intelligence (XAI) method SHAP values for model explainability. The best models were implemented in a web application and tested by medical experts. The model for prediction of mortality risk was tested on a validation cohort of 45 patients from the Department of Infectiology and Travel Medicine, L. Pasteur University Hospital in Košice (UNLP). Results—Our study shows that the best model for predicting COVID-19 disease severity was the LightGBM model with accuracy of 88.4% using all features and 89.5% using the eight most important features. The best model for predicting mortality risk was also the LightGBM model, which achieved a ROC AUC score of 83.7% and a classification accuracy of 81.2% using all features. Using a simplified model trained on the 15 most important features, the ROC AUC score was 83.6% and the classification accuracy was 80.5%. We deployed the simplified models for predicting COVID-19 disease severity and for predicting the risk of COVID-19-related death in a web-based application and tested them with medical experts. This test resulted in a ROC AUC score of 83.6% and an overall prediction accuracy of 73.3%. Full article

With the arrival of an aging society and the continuous extension of the human lifespan, the quality of life has not improved in a corresponding manner. People’s demand for happiness and health is increasing. As a result, a model emerged that integrates tourism and medical services, which is health tourism. This growing demand has prompted many service providers to see it as a business opportunity and enter the market. Tourism can help travelers release work stress and restore physical and mental balance; meanwhile, health check-ups and disease treatment can help them regain health. Consumers have long favored health and medical tourism because it helps relieve stress and promotes overall well-being. As people age, some consumers experience a gradual decline in physical functions, making it difficult for them to participate in regular travel services provided by traditional travel agencies. Therefore, this study aims to explore the service needs of health and medical tourism customers (tourists/patients) and the interrelationships among these service needs, so that health and medical tourism service providers can develop more customized and diversified services. This study identifies four key drivers of medical tourism services: medical services, medical facilities, tour planning, and hospitality facilities. This study uses the APA (attention and performance analysis) method to assess each dimension and criterion and utilizes the DEMATEL method with the NRM (network relationship map) to identify network relationships. By combining APA and NRM techniques, this study develops the APA-NRM technique to evaluate adoption strategies and identify suitable paths for health tourism services, providing tailored development strategies and recommendations for service providers to enhance the service experience. Full article

Background/Objectives: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. Methods: A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models’ performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. Results: The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. Conclusions: To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery. Full article

Background and Objectives: There is a global rise of public interest in integrative medicine. The principles of integrative medicine combining conventional medicine with evidence-based complementary therapies have been implemented in many medical areas, including plastic surgery, to improve patient’s outcome. The aim of the present study was to systematically analyze the application and use of additional non-pharmacological interventions (NPIs) of patients of a German department of plastic surgery. Materials and Methods: The present real-world data study utilized data from the Network Oncology registry between 2016 and 2021. Patients included in this study were at the age of 18 or above, stayed at the department of plastic surgery and received at least one plastic surgical procedure. Adjusted multivariable logistic regression analyses were performed to detect associations between the acceptance of NPIs and predicting factors such as age, gender, year of admission, or length of hospital stay. Results: In total, 265 patients were enrolled in the study between January 2016 and December 2021 with a median age of 65 years (IQR: 52–80) and a male/female ratio of 0.77. Most of the patients received reconstructive surgery (90.19%), followed by hand surgery (5.68%) and aesthetic surgery (2.64%). In total, 42.5% of the enrolled patients accepted and applied NPIs. Physiotherapy, rhythmical embrocations, and compresses were the most often administered NPIs. Conclusions: This exploratory analysis provides a descriptive overview of the application and acceptance of NPIs in plastic surgery patients within a German integrative care setting. While NPIs appear to be well accepted by a subset of patients, further prospective studies are needed to evaluate their impact on clinical outcomes such as postoperative recovery, pain management, patient-reported quality of life, and overall satisfaction with care. Full article

Background: Maternal and newborn health disparities remain a challenge in Puerto Rico, especially in underserved communities. Comienzo Saludable Puerto Rico, sponsored by the U.S. Department of Health and Human Services’ Healthy Start Initiative (HRSA), addresses these gaps through an integrated Networks of Care model known as Cuidado Compartido. Comienzo Saludable Puerto Rico is a maternal, paternal, and child health program aimed at improving the health and well-being of pregnant women, mothers, fathers, newborns, and children in Puerto Rico, particularly those from disadvantaged communities. Methods: This paper presents the Comienzo Saludable Puerto Rico program’s Cuidado Compartido model to integrate a network of healthcare providers and services across hospitals, community organizations, and families. This model aims to improve maternal and newborn/child health outcomes by focusing on the importance of integrated, hospital-community-based care networks. Results: Participants experienced significant improvements in key birth outcomes: low birth weight prevalence declined by 27.2% compared to the community baseline, premature birth rates decreased by 30.9%, and infant mortality dropped by 75%, reaching 0% by 2021 and remaining there through 2023. These results were complemented by increases in maternal mental health screening, paternal involvement, and breastfeeding practices. Conclusions: The Cuidado Compartido model demonstrates a scalable, culturally responsive strategy to improve maternal, newborn, and child health outcomes. It offers critical insights for implementation in other high-need contexts. Full article

In recent years, data augmentation techniques have become the predominant approach for addressing highly imbalanced classification problems in machine learning. Algorithms such as the Synthetic Minority Over-sampling Technique (SMOTE) and Conditional Tabular Generative Adversarial Network (CTGAN) have proven effective in synthesizing minority class samples. However, these methods often introduce distributional bias and noise, potentially leading to model overfitting, reduced predictive performance, increased computational costs, and elevated cybersecurity risks. To overcome these limitations, we propose a novel architecture, FADEL, which integrates feature-type awareness with a supervised discretization strategy. FADEL introduces a unique feature augmentation ensemble framework that preserves the original data distribution by concurrently processing continuous and discretized features. It dynamically routes these feature sets to their most compatible base models, thereby improving minority class recognition without the need for data-level balancing or augmentation techniques. Experimental results demonstrate that FADEL, solely leveraging feature augmentation without any data augmentation, achieves a recall of 90.8% and a G-mean of 94.5% on the internal test set from Kaohsiung Chang Gung Memorial Hospital in Taiwan. On the external validation set from Kaohsiung Medical University Chung-Ho Memorial Hospital, it maintains a recall of 91.9% and a G-mean of 86.7%. These results outperform conventional ensemble methods trained on CTGAN-balanced datasets, confirming the superior stability, computational efficiency, and cross-institutional generalizability of the FADEL architecture. Altogether, FADEL uses feature augmentation to offer a robust and practical solution to extreme class imbalance, outperforming mainstream data augmentation-based approaches. Full article

Sepsis is a serious public health problem. sTREM-1 is a marker of inflammatory and infectious processes that has the potential to become a useful tool for predicting the evolution of sepsis. A prediction model for sepsis was constructed by combining sTREM-1, CRP, and a leukogram via a Bayesian network. A translational study carried out with 32 children with congenital heart disease who had undergone surgical correction at a public referral hospital in Northeast Brazil. In the postoperative period, the mean value of sTREM-1 was greater among patients diagnosed with sepsis than among those not diagnosed with sepsis (394.58 pg/mL versus 239.93 pg/mL, p < 0.001). Analysis of the ROC curve for sTREM-1 and sepsis revealed that the area under the curve was 0.761, with a 95% CI (0.587–0.935) and p = 0.013. With the Bayesian model, we found that a 100% probability of sepsis was related to postoperative blood concentrations of CRP above 71 mg/dL, a leukogram above 14,000 cells/μL, and sTREM-1 concentrations above the cutoff point (283.53 pg/mL). The proposed model using the Bayesian network approach with the combination of CRP, leukocyte count, and postoperative sTREM-1 showed promise for the diagnosis of sepsis. Full article

Background: Overcrowded emergency departments (EDs) create significant challenges for patient management and hospital efficiency. In response, Amiens Picardy University Hospital (APUH) developed the “Prediction of the Patient Pathway in the Emergency Department” (3P-U) model to enhance patient flow management. Objectives: To develop and clinically validate an explainable artificial intelligence (XAI) model for hospital admission predictions, using structured triage data, and demonstrate its real-world applicability in the ED setting. Methods: Our retrospective, single-center study involved 351,019 patients consulting in APUH’s EDs between 2015 and 2018. Various models (including a cross-validation artificial neural network (ANN), a k-nearest neighbors (KNN) model, a logistic regression (LR) model, and a random forest (RF) model) were trained and assessed for performance with regard to the area under the receiver operating characteristic curve (AUROC). The best model was validated internally with a test set, and the F1 score was used to determine the best threshold for recall, precision, and accuracy. XAI techniques, such as Shapley additive explanations (SHAP) and partial dependence plots (PDP) were employed, and the clinical explanations were evaluated by emergency physicians. Results: The ANN gave the best performance during the training stage, with an AUROC of 83.1% (SD: 0.2%) for the test set; it surpassed the RF (AUROC: 71.6%, SD: 0.1%), KNN (AUROC: 67.2%, SD: 0.2%), and LR (AUROC: 71.5%, SD: 0.2%) models. In an internal validation, the ANN’s AUROC was 83.2%. The best F1 score (0.67) determined that 0.35 was the optimal threshold; the corresponding recall, precision, and accuracy were 75.7%, 59.7%, and 75.3%, respectively. The SHAP and PDP XAI techniques (as assessed by emergency physicians) highlighted patient age, heart rate, and presentation with multiple injuries as the features that most specifically influenced the admission from the ED to a hospital ward. These insights are being used in bed allocation and patient prioritization, directly improving ED operations. Conclusions: The 3P-U model demonstrates practical utility by reducing ED crowding and enhancing decision-making processes at APUH. Its transparency and physician validation foster trust, facilitating its adoption in clinical practice and offering a replicable framework for other hospitals to optimize patient flow. Full article

Sport-related injuries are common presentations to primary care and hospital settings. Australian osteopaths practice mainly in private clinical settings in which the frequency of sport-related injury presentations, and how these injuries are managed, is unknown. The objective of the study was to describe the demographic, practice, and clinical management characteristics of Australian osteopaths who report often treating sport-related injuries. The study is a secondary analysis of data derived from the Australian osteopathy practice-based research network. Respondents indicated the frequency treating sports-related injuries in addition to other demographic, practice, and patient management characteristics. Backward logistic regression identified significant characteristics associated with often treating sport injuries. Over half (51%) of a nationally representative sample of Australian osteopaths reported treating sport-related injuries often. Those osteopaths who treat sports injuries often were likely to be male (p < 0.01) and utilise exercise prescription (OR2.34) and sports taping (OR5.99). Australian osteopaths who often treat sports-related injuries provide advice to patients and use exercise prescription more frequently than osteopaths who do not treat these injuries often. The data in the current work begin to explore how osteopaths manage sports-related injuries and highlights how they may be able to provide sports injury care for both recreational and elite sport populations. Full article

Background/Objectives: Guillain–Barré syndrome (GBS) is a rare autoimmune peripheral neuropathy that affects both the myelin sheaths and axons of the peripheral nervous system. It is the leading cause of acute neuromuscular paralysis worldwide, with an annual incidence of less than two cases per 100,000 people. Although most patients recover, a small proportion do not regain mobility and even remain dependent on mechanical ventilation. In this study, we refer to the analysis of samples collected from GBS patients at different defined time points during hospital recovery and performed by a medical or research group. Methods: The conditions for whole blood collection, peripheral blood mononuclear cell isolation, and serum collection from GBS patients and volunteer donors are explained. Aliquots of these human samples have been used for red blood cell phenotyping, transcriptomic and proteomic analyses, and serum biochemical parameter studies. Results: The initial sporadic preservation of human samples from GBS patients and control volunteers enabled the creation of a biobank collection for current and future studies related to the diagnosis and treatment of GBS. Conclusions: In this article, we describe the laboratory procedures and the integration of a GBS biobank collection, local medical services, and academic institutions collaborating in its respective field. The report establishes the intra-disciplinary and inter-institutional network to conduct long-term longitudinal studies on GBS. Full article

Background/Objectives: BRIGHTLIGHT was the national evaluation of adolescent and young adult (AYA) cancer services in England. BRIGHTLIGHT results were not available when the most recent healthcare policy (NHSE service specifications for AYA Cancer) for AYA was drafted and therefore did not consider BRIGHTLIGHT findings and recommendations. We describe the co-development and delivery of a Policy Lab to expedite the implementation of the new service specification in the context of BRIGHTLIGHT results, examining the roles of multi-stakeholders to ensure service delivery is optimised to benefit AYA patients. We address the key question, “What is the roadmap for empowering different stakeholders to shape how the AYA service specifications are implemented?”. Methods: A 1-day face-to-face policy lab was facilitated, utilising a unique, user-centric engagement approach by bringing diverse AYA stakeholders together to co-design strategies to translate BRIGHTLIGHT evidence into policy and impact. This was accompanied by an online workshop and prioritisation survey, individual interviews, and an AYA patient workshop. Workshop outputs were analysed thematically and survey data quantitatively. Results: Eighteen professionals and five AYAs attended the face-to-face Policy Lab, 16 surveys were completed, 13 attended the online workshop, three professionals were interviewed, and three AYAs attended the patient workshop. The Policy Lab generated eight national and six local recommendations, which were prioritised into three national priorities: 1. Launching the service specification supported by compelling communication; 2. Harnessing the ideas of young people; and 3. Evaluation of AYA patient outcomes/experiences and establishing a national dashboard of AYA cancer network performance. An animation was created by AYAs to inform local hospitals what matters to them most in the service specification. Conclusions: Policy and research evidence are not always aligned, so when emerging evidence does not support current guidance, further exploration is required. We have shown through multi-stakeholder involvement including young people that it was possible to gain a different interpretation based on current knowledge and context. This additional insight enabled practical recommendations to be identified to support the implementation of the service specification. Full article

Accurate classification of chest X-ray (CXR) images is crucial for diagnosing lung diseases in medical imaging. Existing deep learning models for CXR image classification face challenges in distinguishing non-lung features. In this work, we propose a new segmentation-assisted fusion-based classification method. The method involves two stages: first, we use a lightweight segmentation model, Partial Convolutional Segmentation Network (PCSNet) designed based on an encoder–decoder architecture, to accurately obtain lung masks from CXR images. Then, a fusion of the masked CXR image with the original image enables classification using the improved lightweight ShuffleNetV2 model. The proposed method is trained and evaluated on segmentation datasets including the Montgomery County Dataset (MC) and Shenzhen Hospital Dataset (SH), and classification datasets such as Chest X-Ray Images for Pneumonia (CXIP) and COVIDx. Compared with seven segmentation models (U-Net, Attention-Net, SegNet, FPNNet, DANet, DMNet, and SETR), five classification models (ResNet34, ResNet50, DenseNet121, Swin-Transforms, and ShuffleNetV2), and state-of-the-art methods, our PCSNet model achieved high segmentation performance on CXR images. Compared to the state-of-the-art Attention-Net model, the accuracy of PCSNet increased by 0.19% (98.94% vs. 98.75%), and the boundary accuracy improved by 0.3% (97.86% vs. 97.56%), while requiring 62% fewer parameters. For pneumonia classification using the CXIP dataset, the proposed strategy outperforms the current best model by 0.14% in accuracy (98.55% vs. 98.41%). For COVID-19 classification with the COVIDx dataset, the model reached an accuracy of 97.50%, the absolute improvement in accuracy compared to CovXNet was 0.1%, and clinical metrics demonstrate more significant gains: specificity increased from 94.7% to 99.5%. These results highlight the model’s effectiveness in medical image analysis, demonstrating clinically meaningful improvements over state-of-the-art approaches. Full article

Assessing microbial community stability and soil quality requires understanding the role of keystone microbial taxa in maintaining diversity and functionality. This study collected soil samples from four major habitats in the urban and peri-urban areas of 20 highly urbanized provinces in China using both the five-point method and the S-shape method and explored their microbiota through high-throughput sequencing techniques. The data was used to investigate changes in the structural diversity and co-occurrence patterns of keystone microbial communities from peri-urban (agricultural land) to urban environments (hospitals, wastewater treatment plants, and zoos) across different regions. Using network analysis, we examined the structure and symbiosis of soil keystone taxa and their association with environmental factors during urbanization. Results revealed that some urban soils exhibited higher microbial diversity, network complexity, and community stability compared to peri-urban soil. Significant differences were observed in the composition, structure, and potential function of keystone microbial taxa between these environments. Correlation analysis showed a significant negative relationship between keystone taxa and mean annual precipitation (p < 0.05), and a strong positive correlation with soil nutrients, microbial diversity, and community stability (p < 0.05). These findings suggest that diverse keystone taxa are vital for sustaining microbial community stability and that urbanization-induced environmental changes modulate their composition. Shifts in keystone taxa composition reflect alterations in soil health and ecosystem functioning, emphasizing their role as indicators of soil quality during urban development. This study highlights the ecological importance of keystone taxa in shaping microbial resilience under urbanization pressure. Full article

This study examines the complex process of Islam’s localization in Sudan, focusing on how hospitality, Sufi dhikr, and Mawlid celebrations integrate with Islamic practices. Drawing on three years of qualitative fieldwork, it demonstrates how Sudan’s geography, ethnic diversity, and historical heritage enable the blending of core religious principles with local customs. Sufi brotherhoods—particularly Qādiriyya, Tījāniyya, Shādhiliyya, and Khatmiyya—play a pivotal role in local culture by incorporating traditional musical, choreographic, and narrative art forms into their rituals, resulting in highly dynamic worship and social interaction. In Sudan, hospitality emerges as a near-sovereign social norm, reflecting the Islamic ethics of charity and mutual assistance while remaining deeply intertwined with local traditions. Islam’s adaptability toward local customs is further illustrated by the vibrant drumming, chanting, and dancing that enhance large-scale Mawlid al-Nabi celebrations, uniting Muslims under a religious identity that goes beyond dogmatic definitions. Beyond their spiritual meanings, these Sufi practices and networks also serve as tools for social cohesion, often functioning as support systems in regions with minimal state presence. They help prevent disputes and foster unity, demonstrating the positive impact of a flexible Islam—one that draws on both scripture and local traditions—on peacebuilding in Sudan. While highlighting the country’s social realities, this study offers insights into how Islam can function as a transformative force within society. Full article

Background/Objectives: Despite advancements in surgery, esophagectomy remains one of the most challenging and complex gastrointestinal surgical procedures, burdened by significant perioperative morbidity and mortality rates, as well as high financial costs. Recognizing the need for standardized care provided by a multidisciplinary healthcare team, the EUropean PErioperative MEdical Networking (EUPEMEN) initiative developed a dedicated protocol for perioperative care of patients undergoing esophagectomy, aiming to enhance recovery, reduce morbidity, and homogenize care delivery across European healthcare systems. Methods: Developed through a multidisciplinary European collaboration of five partners, the protocol incorporates expert consensus and the latest scientific evidence. It addresses the entire perioperative pathway, from preoperative preparation to hospital discharge and postoperative recovery, emphasizing patient-centered care, risk mitigation, and early functional restoration. Results: The implementation of the EUPEMEN esophagectomy protocol is expected to improve patient outcomes through a day-by-day structured prehabilitation plan, meticulous intraoperative management, and proactive postoperative rehabilitation. The approach promotes reduced postoperative complications, earlier return to oral intake, and shorter hospital stays, while supporting multidisciplinary coordination. Conclusions: The EUPEMEN protocol for esophagectomy provides a comprehensive guideline framework for optimizing perioperative care in esophageal surgery. In addition, it serves as a practical guide for healthcare professionals committed to advancing surgical recovery and standardizing clinical practice across diverse care environments across Europe. Full article