Search Results (2,465)

Background and Objectives: Pneumonia is a leading cause of intensive care unit (ICU) admission and is associated with high mortality, particularly among patients with multiple comorbidities. Accurate early risk stratification is essential for guiding clinical decision-making in critically ill patients. However, the prognostic benefit of combining clinical scoring systems with nutritional and endothelial stress indices in ICU patients with pneumonia remains unclear. Materials and Methods: This retrospective, single-center cohort study included adult patients admitted to the ICU with a diagnosis of pneumonia between 1 January 2023 and 1 July 2025. Demographic characteristics, comorbidities, clinical variables, laboratory parameters, and prognostic scores were obtained from electronic medical records. The National Early Warning Score (NEWS), Prognostic Nutritional Index (PNI), and Endothelial Activation and Stress Index (EASIX) were calculated at ICU admission. The primary outcome was in-hospital mortality. Univariate and multivariate logistic regression analyses were performed to examine variables associated with in-hospital mortality. The discriminative performance of individual and combined prognostic models was evaluated using receiver operating characteristic (ROC) curve analysis. Results: A total of 221 patients were included; 79 (35.7%) survived and 142 (64.3%) died during hospitalization. Non-survivors had significantly higher NEWS and EASIX values and lower PNI values compared with survivors (all p < 0.05). In multivariate analysis, endotracheal intubation (OR: 12.46; p < 0.001), inotropic use (OR: 5.14; p = 0.001), and serum lactate levels (OR: 1.75; p = 0.003) were identified as being independently associated with in-hospital mortality. Models combining NEWS with PNI or EASIX demonstrated improved discriminatory performance. Conclusions: In critically ill patients with pneumonia, integrating NEWS with nutritional and endothelial stress indices provides numerically improved discrimination compared with NEWS alone, although the incremental gain did not reach statistical significance. Full article

Understanding the decision-making behavior of machine learning models is essential in domains where individual predictions matter, such as medical diagnosis or sports analytics. While explainable artificial intelligence (XAI) methods such as SHAP provide instance-level feature attributions, they mainly summarize typical decision behavior and offer limited support for systematically exploring atypical yet correctly classified cases. In this work, we introduce the Classification Outlier Variability Score (COVAS), a framework designed to support hypothesis generation through the analysis of explanation variability. COVAS operates in the explanation space and builds directly on SHAP value representations. It quantifies how strongly an individual instance’s SHAP-based explanation deviates from class-specific attribution patterns by aggregating standardized SHAP deviations into a single score. Consequently, the applicability of COVAS inherits the model- and data-agnostic properties of SHAP, provided that explanations can be computed for the underlying model and data. We evaluate COVAS on publicly available datasets from the medical and sports domains. The results show that COVAS reveals explanation-space outliers not captured by feature-space outlier detection or prediction uncertainty measures. Robustness analyses demonstrate stability across parameter choices, class imbalance, model initialization, and model classes. Overall, COVAS complements existing XAI techniques by enabling targeted instance-level inspection and facilitating XAI-guided hypothesis formulation. Full article

Background and Objectives: This study aimed to comparatively evaluate the association of commonly used comorbidity scores with survival, mortality, and recurrence in ovarian cancer patients aged 50 years and above. Materials and Methods: In this single-center, retrospective study, 130 female patients diagnosed between 2017 and 2024 who had received systemic therapy and had complete medical records were included. Comorbidity scores—including the Charlson Comorbidity Index (CCI), Cumulative Illness Rating Scale-Geriatric (CIRS-G), Adult Comorbidity Evaluation-27 (ACE-27), Elixhauser Comorbidity Index, Index of Coexistent Disease (ICED), and Functional Comorbidity Index (FCI)—were calculated for each patient. Survival analyses were conducted using the Kaplan–Meier method and Cox regression modeling. The prognostic accuracy of comorbidity scores was assessed via receiver operating characteristic (ROC) curve analysis. Results: Patients with higher CCI scores had significantly shorter survival, and CCI was identified as an independent prognostic factor in multivariate analysis. While other comorbidity scores were associated with overall survival in univariate analyses, they lost statistical significance in multivariate models. Patients with a higher comorbidity burden experienced more frequent disease recurrence and shorter time to recurrence. Conclusions: Comorbidity burden is a key clinical determinant of survival and disease trajectory in older patients with ovarian cancer. The CCI demonstrated the highest prognostic accuracy in this population and may serve as a valuable tool in individualized treatment planning. Integration of comorbidity-based assessments into standard decision-making processes is recommended in geriatric oncology practice. Full article

Over 10% of US children and adolescents have attention-deficit hyperactivity disorder (ADHD), with a similar prevalence among youth athletes. While ADHD may confer certain athletic performance advantages such as heightened quickness, decision-making and periods of hyperfocus, it also poses some challenges including reduced concentration, frustration, and possible increased injury risk. Pharmacologic treatments, including stimulant-based medications, can improve attentiveness and athletic performance but could alter nutritional behaviors such as appetite suppression. This paper reviews the current literature on nutritional strategies to provide practical sports nutrition guidelines for children and adolescent athletes with ADHD. Evidence suggests that optimizing energy intake, emphasizing complex carbohydrates, improving fat quality intake, and consuming adequate amounts of micronutrients may support both athletic performance and ADHD symptom management. In contrast, excessive added sugars and saturated fats are associated with poorer outcomes and manifestation of ADHD symptoms. Although no research examining nutritional interventions in youth athletes with ADHD have been performed, applying established sports nutrition principles for youth athletes with ADHD offers a promising approach to enhance performance, reduce injury risk, and support the long-term health of the athlete. Full article

Background: Language barriers remain a major obstacle to equitable healthcare access for immigrants and refugees across Europe. Greece, as both a transit and host country, faces persistent challenges in providing linguistically and culturally appropriate care. Methods: This study presents a narrative literature review synthesizing international, European, and Greek evidence on the effects of limited language proficiency, professional interpretation, and intercultural mediation on healthcare access, patient safety, satisfaction, and clinical outcomes. Peer-reviewed studies and selected grey literature were identified through searches of PubMed, Scopus, Web of Science, and CINAHL. Results: The evidence consistently demonstrates that the absence of professional interpretation is associated with substantially higher rates of clinically significant communication errors, longer hospital stays, increased readmissions, and higher healthcare costs. In contrast, the use of trained medical interpreters and intercultural mediators improves comprehension, shared decision-making, patient satisfaction, and clinical outcomes. Comparative European data from Italy, Spain, Germany, and Sweden show that institutionalized interpretation systems outperform Greece’s fragmented, NGO-dependent approach. Greek studies further reveal that limited proficiency in Greek is associated with reduced service utilization, longer waiting times, and lower patient satisfaction. Conclusions: This narrative review highlights the urgent need for Greece to adopt a coordinated, professionally staffed interpretation and intercultural mediation framework. Strengthening linguistic support within the healthcare system is essential for improving patient safety, equity, efficiency, and the integration of migrant and refugee populations. Full article

Background/Objectives: Kidney donation remains a critical component of addressing end-stage renal disease. This study examines differences in awareness, willingness to donate, and concerns related to kidney donation among medical and non-medical university students. By comparing these groups within the context of Croatia’s presumed-consent system for organ donation, the study provides insights into how educational backgrounds shape attitudes in a setting with high transplantation rates but limited data on young adults. Methods: A cross-sectional observational study targeted at medical and non-medical university students in Croatia. Data were collected from 640 participants via a self-administered, close-ended, structured questionnaire with 33 items divided across three sections. Responses were analyzed using IBM SPSS Statistics program (v. 30.0), to identify significant differences. Due to the cross-sectional design, causal relationships could not be inferred. Results: Overall, 190 students (28.7%) reported willingness to donate a kidney during their lifetime, which was more common among medical students (N = 59; 39.0%) than non-medical students (N = 131; 26.8%). Collectively, willingness to donate postmortem was high in both groups (N = 527; 82.3%), as was willingness in a brain-dead state (N = 448; 70.0%). Medical and non-medical students mostly cited perceived health risks as a concern and concerns related to surgical complications. Regarding information sources, 33.2% of students reported inadequate knowledge of kidney donation, with social media and internet searches cited more frequently than healthcare professionals. Conclusions: Our findings indicate that medical and non-medical students exhibit distinct gaps in knowledge, risk perception and willingness toward kidney donation. Within Croatia’s presumed-consent framework, these findings highlight the importance of targeted educational strategies to support informed decision-making among future generations. Full article

Each year, around 23 million miscarriages occur worldwide, which have a substantial emotional impact on parents, and impose significant societal costs. While medical care accounts for most expenses, work productivity loss contributes significantly. Addressing underlying causes of miscarriage could improve parents’ mental health and potentially their economic impact. In most countries, investigations into miscarriage causes are only recommended after recurrent cases, focusing mainly on maternal factors. Fetal and placental tissue are rarely examined, as current guidelines do not advise routine genetic analyses of pregnancy tissue, because the impact of further clinical decision making and individual prognosis is unclear. However, this leaves over 90% of all miscarriage cases unexplained and highlights the need for alternative methods. We therefore conducted a narrative review on genetic analysis, autopsy, and imaging of products of conception (POC). Karyotyping, QF-PCR, SNP array, and aCGH were reviewed in different research settings, with QF-PCR being the most cost-effective, while obtaining the highest technical success rate. Karyotyping, historically being considered the gold standard for POC examination, was the least promising. Post-mortem imaging techniques including post-mortem ultrasound (PMUS), ultra-high-field magnetic resonance imaging (UHF-MRI), and microfocus computed tomography (micro-CT) show promising diagnostic capabilities in miscarriages, with micro-CT achieving the highest cost-effective performance. In conclusion, current guidelines do not recommend diagnostic testing for most cases, leaving the majority unexplained. Although genetic and imaging techniques show promising diagnostic potential, they should not yet be implemented in routine clinical care and require thorough evaluation within research settings—assessing not only diagnostic and psychosocial outcomes but also economic implications. Full article

Support Vector Machines (SVMs) are widely used in critical decision-making applications, such as precision agriculture, due to their strong theoretical foundations and their ability to construct an optimal separating hyperplane in high-dimensional spaces. However, the effectiveness of SVMs is highly dependent on the efficiency of the optimization algorithm used to solve their underlying dual problem, which is often complex and constrained. Classical solvers, such as Sequential Minimal Optimization (SMO) and Stochastic Gradient Descent (SGD), present inherent limitations: SMO ensures numerical stability but lacks scalability and is sensitive to heuristics, while SGD scales well but suffers from unstable convergence and limited suitability for nonlinear kernels. To address these challenges, this study proposes a novel hybrid optimization framework based on Open Competency Optimization and Particle Swarm Optimization (OCO–PSO) to enhance the training of SVMs. The proposed approach combines the global exploration capability of PSO with the adaptive competency-based learning mechanism of OCO, enabling efficient exploration of the solution space, avoidance of local minima, and strict enforcement of dual constraints on the Lagrange multipliers. Across multiple datasets spanning medical (diabetes), agricultural yield, signal processing (sonar and ionosphere), and imbalanced synthetic data, the proposed OCO-PSO–SVM consistently outperforms classical SVM solvers (SMO and SGD) as well as widely used classifiers, including decision trees and random forests, in terms of accuracy, macro-F1-score, Matthews correlation coefficient (MCC), and ROC-AUC. On the Ionosphere dataset, OCO-PSO achieves an accuracy of $95.71\%$, an F1-score of $0.954$, and an MCC of $0.908$, matching the accuracy of random forest while offering superior interpretability through its kernel-based structure. In addition, the proposed method yields a sparser model with only 66 support vectors compared to 71 for standard SVC (a reduction of approximately $7\%$), while strictly satisfying the dual constraints with a near-zero violation of $1.3\times {10}^{-3}$. Notably, the optimal hyperparameters identified by OCO-PSO ($\mathrm{C}=2$, $\gamma \approx 0.062$) differ substantially from those obtained via Bayesian optimization for SVC ($\mathrm{C}=10$, $\gamma \approx 0.012$), indicating that the proposed approach explores alternative yet equally effective regions of the hypothesis space. The statistical significance and robustness of these improvements are confirmed through extensive validation using 1000 bootstrap replications, paired Student’s t-tests, Wilcoxon signed-rank tests, and Holm–Bonferroni correction. These results demonstrate that the proposed metaheuristic hybrid optimization framework constitutes a reliable, interpretable, and scalable alternative for training SVMs in complex and high-dimensional classification tasks. Full article

Background: Healthcare is a large contributor to greenhouse gas (GHG) emissions, contributing to climate change and health impairments. However, the magnitude of health and climate benefits of local and regional GHG mitigation strategies has not been well quantified. Few studies have demonstrated the use of public tools for this purpose in healthcare facilities. Methods: We evaluated several renewable energy and energy efficiency scenarios focused on one academic medical center in New York State. We used the Environmental Protection Agency’s (EPA) publicly available AVoided Emissions and geneRation Tool to estimate avoided GHG and health-harmful air pollutant emissions. The economic value of the resulting avoided health and climate damages was quantified using EPA’s CO-Benefits Risk Assessment screening tool. Results: Transitioning one healthcare institution to 100% solar energy and improving energy efficiency by 25% could yield approximately $807,000 to $1.5 million in annual health savings, with an additional $2.3 million benefits in avoided climate damages. There is an approximate $108.5–$196.6 million in annual climate and health benefits when extrapolating these energy solutions to hospitals across the same state. Conclusions: There are significant health savings from healthcare GHG mitigation strategies. This application of publicly available and accessible tools demonstrates ways to integrate climate and health benefits into local decision-making around climate change mitigation and sustainability efforts. Full article

Background: Effective preoperative patient counseling is essential to shared decision-making. In thyroid surgery, patient communication can be complicated by the complex anatomy and variable surgical approaches, which may not be fully conveyed through conventional verbal explanations or schematic drawings. Virtual three-dimensional (3D) thyroid models may provide an intuitive tool to enhance patient comprehension. Methods: We conducted a randomized controlled trial at Peking Union Medical College Hospital with 94 newly-diagnosed thyroid cancer patients scheduled for thyroidectomy. Participants were assigned to either the control group (n = 47), which received preoperative drawing-based counseling, or the intervention group (n = 47), which utilized a virtual 3D model for communication. The Thyroid Navigator app, developed by Kuma Hospital, was used to provide dynamic 3D representation of the thyroid gland, surrounding structures, and potential surgical procedures. After standardized preoperative consultations, patients were surveyed to assess their understanding in pertinent anatomy and postoperative complications. Results: Patients in the 3D model group demonstrated similar correct response rates in lesion localization (p = 0.536) or parathyroid gland recognition (p = 0.071), but significantly higher accuracy in identifying the recurrent laryngeal nerve and the extent of lymph node dissection compared with the control group (p < 0.05). Moreover, comprehension of the causes of major postoperative complications—including hoarseness (recurrent laryngeal nerve injury, p = 0.004), hypocalcemia (parathyroid gland impairment, p = 0.015), and bleeding (inadequate hemostasis, p = 0.008)—was significantly improved in the 3D model group. Conclusions: Use of a virtual 3D thyroid model significantly improves patient comprehension of thyroid anatomy, surgical procedures, and potential complications, thereby enhancing clinician–patient communication. Virtual 3D models represent a practical and cost-effective supplement to conventional counseling in thyroid surgery, offering clear benefits in patient education and shared decision-making. Full article

Background/Objective: Glucagon-like peptide-1 receptor agonists (GLP-1RAs) have received widespread attention as effective obesity treatments. However, limited research has examined the perspectives of patients contemplating GLP-1RAs. This study explored perceptions, motivations, and barriers among individuals considering GLP-1RA therapy for obesity treatment, with the goal of informing patient-centered care and enhancing clinician engagement. Methods: Adults completed surveys and interviews between June and November 2025. In this pragmatic mixed-methods study, both survey and interview questions explored perceived benefits, barriers, and decision-making processes. Qualitative data, describing themes based on the Health Belief Model, were analyzed using Dedoose (version 9.0.107), and quantitative data were analyzed using SAS (version 9.4). Participant characteristics included marital status, income, educational attainment, employment status, insurance status, age, race/ethnicity, and sex. Anticipated length on GLP-1RA medication and selected self-reported health conditions (depression, anxiety, hypertension, heart disease, back pain, joint pain), reported physical activity level, and perceived weight loss competency were also recorded. Results: Among the 31 non-diabetic participants who were considering GLP-1RA medication for weight loss, cost emerged as the most significant barrier. Life course events, particularly (peri)menopause among women over 44, were commonly cited as contributors to weight gain. Participants expressed uncertainty about eligibility, long-term safety, and treatment expectations. Communication gaps were evident, as few participants initiated discussions and clinician outreach was rare, reflecting limited awareness and discomfort around the topic. Conclusions: Findings highlight that individuals considering GLP-1RA therapy face multifaceted emotional, financial, and informational barriers. Proactive, empathetic clinician engagement, through validation of prior efforts, clear communication of risks and benefits, and correction of misconceptions, can support informed decision-making and align treatment with patient goals. Full article

Objective—Partial do-not-resuscitate (DNR) orders, directives specifying limited resuscitative efforts, are intended to align medical interventions with patient preferences. However, their complexity may introduce ambiguity, inconsistent care, and ethical challenges. Design—A retrospective review was conducted of inpatient partial code order entries over a three-year period at a single institution with a pediatric oncology and immunology cohort. Partial DNR orders were identified and categorized based on included or excluded interventions (chest compressions, defibrillation, intubation, mechanical ventilation, medications). Data was analyzed to assess the frequency, variation, and internal consistency of documented preferences as well as alignment with institutional definitions and clinical feasibility. Results—Partial DNR orders represented a small (n = 15, 7%) but notable proportion of total code status entries. Wide variability was observed in the combinations of permitted and withheld interventions, with orders containing internally conflicting instructions. Documentation of inconsistencies and unclear terminology were common, raising concerns about interpretability during emergent situations. Conclusions—Partial DNR orders demonstrate heterogeneity and potential for miscommunication. These findings suggest that while partial codes may reflect nuanced patient preferences, they pose operational and ethical risks that could compromise care clarity. Clinical implications are reviewed. These findings will guide institutional deliberations regarding whether to refine, restrict, or eliminate partial code order options to enhance patient safety and decision-making transparency. Full article

Artificial intelligence (AI) is rapidly transforming medical diagnostics by allowing for early, accurate, and data-driven clinical decision-making. This review provides an overview of how machine learning (ML), deep learning, and emerging multimodal foundation models have been used in diagnostic procedures across imaging, pathology, molecular analysis, physiological monitoring, and electronic health record (EHR)-integrated decision-support systems. We have discussed the basic computational foundations of supervised, unsupervised, and reinforcement learning and have also shown the importance of data curation, validation metrics, interpretability methods, and feature engineering. The use of AI in many different applications has shown that it can find abnormalities and integrate some features from multi-omics and imaging, which has shown improvements in prognostic modeling. However, concerns about data heterogeneity, model drift, bias, and strict regulatory guidelines still remain and are yet to be addressed in this field. Looking forward, future advancements in federated learning, generative AI, and low-resource diagnostics will pave the way for adaptable and globally accessible AI-assisted diagnostics. Full article

Asthma is a common chronic disease in children, contributing to significant morbidity and healthcare utilization worldwide. The integration of artificial intelligence (AI) and machine learning (ML) into pediatric asthma care is rapidly advancing, offering new opportunities for early diagnosis, risk stratification, and personalized management. AI-driven tools can analyze complex clinical, genetic, and environmental data to identify asthma phenotypes and endotypes, predict exacerbations, and support timely interventions. In pediatric populations, these technologies enable non-invasive diagnostic approaches, remote monitoring through wearable devices, and improved medication adherence via smart inhalers and digital health platforms. Despite these advances, challenges remain, including the need for pediatric-specific datasets, transparency in AI decision-making, and careful attention to data privacy and equity. The integration of AI in pediatric asthma care and into the clinical decision system can offer personalized treatment plans, reducing the burden of the disease both for patients and health professionals. This is a narrative review on the applications of AI and ML in pediatric asthma care. Full article

People with intellectual disabilities frequently use psychotropic and other medications, sometimes inappropriately. To promote shared decision-making, they require accessible information about their medication. This study combined data from two similar intervention studies, conducted in two different settings, to assess the appropriateness of medication use and the shared decision-making process among adults with mild intellectual disabilities who used psychotropic medication. The intervention consisted of a structured, multidisciplinary medication review, including the provision of accessible psychotropic medication leaflets, and a discussion of the pharmacotherapeutic treatment plan with the patient by either a pharmacist or physician, depending on the setting. Outcomes included medication use, pharmacotherapeutic problems, implementation of recommendations, and perceived shared decision-making, measured with the Shared Decision-Making Questionnaire Q9. The 15 included participants used an average of nearly seven medications, which were mainly neurotropic, gastrointestinal, cardiovascular, and respiratory agents. On average, two pharmacotherapeutic problems were identified; the most common were overtreatment, side effects, and administration difficulties. Recommendations often involved dose reduction or tapering, and about 75% were fully or partially implemented. Both participants and clinicians reported high satisfaction with shared decision-making. Multidisciplinary, structured medication reviews, incorporating accessible medication leaflets, may enhance appropriate medication use and shared decision-making, but more research is needed. Full article