Search Results (4,349)

Background: Neonatal jaundice is common and can cause severe hyperbilirubinemia if untreated. The early identification of at-risk newborns is challenging despite the existing guidelines. Objective: This study aimed to identify the key maternal and neonatal risk factors for jaundice requiring phototherapy using machine learning. Methods: In this study hospital, phototherapy was administered following the American Academy of Pediatrics (AAP) guidelines when a neonate’s transcutaneous bilirubin level was in the high-risk zone. To identify the risk factors for phototherapy, we retrospectively analyzed the electronic medical records of 8242 neonates admitted between 2017 and 2022. Predictive models were trained using maternal and neonatal data. XGBoost showed the best performance (AUROC = 0.911). SHAP values interpreted the model. Results: Mode of delivery, neonatal feeding indicators (including daily formula intake and breastfeeding frequency), maternal BMI, and maternal white blood cell count were strong predictors. Cesarean delivery and lower birth weight were linked to treatment need. Conclusions: Machine learning models using perinatal data accurately predict the risk of neonatal jaundice requiring phototherapy, potentially aiding early clinical decisions and improving outcomes. Full article

Heart failure (HF) poses a substantial global burden due to its high morbidity, mortality, and healthcare costs. Accurate prognostication is crucial for optimizing treatment, resource allocation, and patient counseling. Prognostic tools range from simple clinical scores such as ADHERE and MAGGIC to more complex models incorporating biomarkers (e.g., NT-proBNP, sST2), imaging, and artificial intelligence techniques. In acute HF, models like EHMRG and STRATIFY aid early triage, while in chronic HF, tools like SHFM and BCN Bio-HF support long-term management decisions. Despite their utility, most models are limited by poor generalizability, reliance on static inputs, lack of integration into electronic health records, and underuse in clinical practice. Novel approaches involving machine learning, multi-omics profiling, and remote monitoring hold promise for dynamic and individualized risk assessment. However, these innovations face challenges regarding interpretability, validation, and ethical implementation. For prognostic models to transition from theoretical promise to practical impact, they must be continuously updated, externally validated, and seamlessly embedded into clinical workflows. This review emphasizes the potential of prognostic models to transform HF care but cautions against uncritical adoption without robust evidence and practical integration. In the evolving landscape of HF management, prognostic models represent a hopeful avenue, provided their limitations are acknowledged and addressed through interdisciplinary collaboration and patient-centered innovation. Full article

Background: Right ventricular (RV) dysfunction is associated with poor clinical outcomes in critically ill sepsis patients, but its pathophysiology and predictors are incompletely characterized. We aimed to investigate the predictors of RV dysfunction and its outcomes in sepsis patients admitted to the intensive care unit (ICU). Methods: This is a single-center retrospective cohort study of adult patients admitted to the ICU for sepsis who had echocardiography within 72 h of diagnosis. Patients with acute coronary syndrome, acute decompensated heart failure, or significant valvular dysfunction were excluded. RV dysfunction was defined as the presence of RV dilation, hypokinesis, or both. Demographics and clinical outcomes were obtained from electronic medical records. Results: A total of 361 patients were included in our study—47 with and 314 without RV dysfunction. The mean age of the population was 66.8 years and 54.6% were females. Compared to those without RV dysfunction, patients with RV dysfunction were more likely to require mechanical ventilation (63.8% vs. 43.9%, p = 0.01) and vasopressor support (61.7% vs. 36.6%, p < 0.01). On multivariate logistic regression analysis, increasing age (OR 1.03, 95% C.I. 1.00–1.06), a history of HIV infection (OR 5.88, 95% C.I. 1.57–22.11) and atrial fibrillation (OR 4.34, 95% C.I. 1.83–10.29), and presence of LV systolic dysfunction (OR 14.40, 95% C.I. 5.63–36.84) were independently associated with RV dysfunction. Patients with RV dysfunction had significantly worse 30-day survival (Log-Rank p = 0.023). On multivariate Cox regression analysis, older age (HR 1.02, 95% C.I. 1.00–1.04) and peak lactate (HR 1.16, 95% C.I. 1.11–1.21) were independent predictors of 30-day mortality. Conclusions: Among other findings, our data suggests a possible association between a history of HIV infection and RV dysfunction in critically ill sepsis patients, and this should be investigated further in future studies. Patients with evidence of RV dysfunction had poorer survival in this population; however this was not an independent predictor of mortality in the multivariate analysis. A larger cohort with a longer follow-up period may provide further insights. Full article

Given the environmental significance of the textile industry, especially the accumulation of nondegradable materials, there is extensive development of greener approaches to fabric waste management. Here, we investigated the biodegradation potential of three Streptomyces strains in model compost on polyamide (PA) and polyamide-elastane (PA-EA) as synthetic, and on cotton (CO) as natural textile materials. Weight change of the materials was followed, while Fourier-Transform Infrared Spectroscopy (FTIR) and Scanning Electron Microscopy (SEM) were used to analyze surface changes of the materials upon biodegradation. The bioluminescence-based toxicity test employing Vibrio fischeri confirmed the ecological safety of the tested textiles. After 12 months, the increase of 10 and 16% weight loss, of PA-EA and PA, respectively, was observed in compost augmented with Streptomyces sp. BPS43. Additionally, a 14% increase in cotton degradation was recorded after 2 months in compost augmented with Streptomyces sp. NP10. Genome exploration of the strains was carried out for potential plastic-degrading enzymes. It highlighted BPS43 as the most versatile strain with specific amidases that show sequence identity to UMG-SP-1, UMG-SP-2, and UMG-SP-3 (polyurethane degrading enzymes identified from compost metagenome). Our results showcase the behavior of Streptomyces sp. BPS43 in the degradation of PA and PA-EA textiles in composting conditions, with enzymatic potential that could be further characterized and optimized for increased synthetic textile degradation. Full article

Background and Objectives: Although survival after congenital cardiac malformations (CCM) has improved, little is known about Romanian children’s own perceptions of health-related quality of life (HRQoL) or their emotional burden. We compared HRQoL, depressive symptoms, and anxiety across lesion severity strata and explored clinical predictors of impaired HRQoL. Methods: In this cross-sectional study (1 May 2023–30 April 2025), 72 children (mean age 7.9 ± 3.0 years, 52.8% male) attending a tertiary cardiology clinic completed the Romanian-validated Pediatric Quality of Life Inventory (PedsQL), Children’s Depression Inventory (CDI) and the Screen for Child Anxiety-Related Emotional Disorders questionnaire (SCARED-C, child version). Lesions were classified as mild (n = 22), moderate (n = 34), or severe (n = 16). Left-ventricular ejection fraction (LVEF) and unplanned cardiac hospitalisations over the preceding 12 months were extracted from electronic records. Results: Mean PedsQL total scores declined stepwise by severity (mild 80.9 ± 7.3; moderate 71.2 ± 8.4; severe 63.1 ± 5.4; p < 0.001). CDI and SCARED-C scores rose correspondingly (CDI: 9.5 ± 3.0, 13.6 ± 4.0, 18.0 ± 2.7; anxiety: 15.2 ± 3.3, 17.2 ± 3.8, 24.0 ± 3.4; both p < 0.001). PedsQL correlated positively with LVEF (r = 0.51, p < 0.001) and negatively with hospitalisations (r = −0.39, p = 0.001), depression (r = −0.44, p < 0.001), and anxiety (r = −0.47, p < 0.001). In multivariable analysis, anatomical severity remained the sole independent predictor of lower HRQoL (β = −8.4 points per severity tier, p < 0.001; model R² = 0.45). Children with ≥ 1 hospitalisation (n = 42) reported poorer HRQoL (69.6 ± 8.0 vs. 76.1 ± 11.1; p = 0.005) and higher depressive scores (p < 0.001). Conclusions: HRQoL and internalising symptoms in Romanian children with CCM worsen with increasing anatomical complexity and recent hospital utilisation. The severity tier outweighed functional markers as the main determinant of HRQoL, suggesting that psychosocial screening and support should be scaled to lesion complexity. Integrating the routine use of the Romanian-validated PedsQL, CDI, and SCARED-C questionnaire into cardiology follow-up may help identify vulnerable patients early and guide targeted interventions. Full article

Background and Objectives: Preterm birth and stillbirth are primary adverse pregnancy outcomes. Research during the COVID-19 pandemic revealed reductions in preterm birth in some countries, while stillbirth rates increased or remained unchanged. These findings suggest the presence of preventable risk factors associated with changes in physical activity and lower exposure to community-acquired infections due to lockdown measures, altered social interaction patterns or reduced access to antenatal care. Assessing seasonal variation may offer insights into whether lifestyle changes during the COVID-19 lockdown period influenced preterm birth rates. Materials and Methods: This retrospective cohort study used data from the electronic medical records of Bihor and Sibiu counties. Preterm deliveries (<37 weeks) and stillbirths during the COVID-19 pandemic (2020 and 2021) were compared with the corresponding pre-pandemic (2018 and 2019) and post-pandemic (2022 and 2023) period. Preterm birth rates during summer and winter in the pre-pandemic, pandemic, and post-pandemic years were analyzed. A comparison with rates during strict lockdown was made. Results: Out of 52,021 newborn infants, 4473 were born preterm. Preterm birth rates remained stable across all three periods (p = 0.13), and no significant seasonal pattern was identified (p = 0.65). In contrast, stillbirth rates increased notably during the strict lockdown period, with the median incidence almost doubling compared to other periods (0.87%, p = 0.05), while remaining unchanged during the rest of the pandemic (p = 0.52). Conclusions: Our study found that preterm birth rates remained unaffected by the pandemic and lockdown periods, while stillbirths increased significantly during the strict lockdown. These findings highlight the importance of maintaining access to timely antenatal care during public health emergencies to prevent adverse perinatal outcomes. Full article

Background/Objectives: Antibiotic use is common among hospitalized pediatric patients. However, inappropriate use, including excessive use of Watch antibiotics, can contribute to antimicrobial resistance, adverse events, and increased healthcare costs. Consequently, there is a need to continually assess their usage among this vulnerable population. This was the objective behind this study. Methods: The medical records of all pediatric patients (under 12 years) admitted and treated with antibiotics at a Ghanaian Teaching Hospital between January 2022 and March 2022 were extracted from the hospital’s electronic database. The prevalence and appropriateness of antibiotic use were based on antibiotic choices compared with current guidelines. Influencing factors were also assessed. Results: Of the 410 admitted patients, 319 (77.80%) received at least one antibiotic. The majority (68.65%; n = 219/319) were between 0 and 2 years, and males (54.55%; n = 174/319). Ceftriaxone was the most commonly prescribed antibiotic (20.69%; n = 66/319), and most of the systemic antibiotics used belonged to the WHO Access and Watch groups, including a combination of Access and Watch groups (42.90%; n = 136/319). Neonatal sepsis (24.14%; n = 77/319) and pneumonia (14.42%; n = 46/319) were the most common diagnoses treated with antibiotics. Antibiotic appropriateness was 42.32% (n = 135/319). Multivariate analysis revealed ceftriaxone prescriptions (aOR = 0.12; CI = 0.02–0.95; p-value = 0.044) and surgical prophylaxis (aOR = 0.07; CI = 0.01–0.42; p-value = 0.004) were associated with reduced antibiotic appropriateness, while a pneumonia diagnosis appreciably increased this (aOR = 15.38; CI = 3.30–71.62; p-value < 0.001). Conclusions: There was high and suboptimal usage of antibiotics among hospitalized pediatric patients in this leading hospital. Antibiotic appropriateness was influenced by antibiotic type, diagnosis, and surgical prophylaxis. Targeted interventions, including education, are needed to improve antibiotic utilization in this setting in Ghana and, subsequently, in ambulatory care. Full article

Background: Artificial intelligence (AI) and machine learning (ML) have been reshaping maternal, fetal, neonatal, and reproductive healthcare by enhancing risk prediction, diagnostic accuracy, and operational efficiency across the perinatal continuum. However, no comprehensive synthesis has yet been published. Objective: To conduct a scoping review of reviews of AI/ML applications spanning reproductive, prenatal, postpartum, neonatal, and early child-development care. Methods: We searched PubMed, Embase, the Cochrane Library, Web of Science, and Scopus through April 2025. Two reviewers independently screened records, extracted data, and assessed methodological quality using AMSTAR 2 for systematic reviews, ROBIS for bias assessment, SANRA for narrative reviews, and JBI guidance for scoping reviews. Results: Thirty-nine reviews met our inclusion criteria. In preconception and fertility treatment, convolutional neural network-based platforms can identify viable embryos and key sperm parameters with over 90 percent accuracy, and machine-learning models can personalize follicle-stimulating hormone regimens to boost mature oocyte yield while reducing overall medication use. Digital sexual-health chatbots have enhanced patient education, pre-exposure prophylaxis adherence, and safer sexual behaviors, although data-privacy safeguards and bias mitigation remain priorities. During pregnancy, advanced deep-learning models can segment fetal anatomy on ultrasound images with more than 90 percent overlap compared to expert annotations and can detect anomalies with sensitivity exceeding 93 percent. Predictive biometric tools can estimate gestational age within one week with accuracy and fetal weight within approximately 190 g. In the postpartum period, AI-driven decision-support systems and conversational agents can facilitate early screening for depression and can guide follow-up care. Wearable sensors enable remote monitoring of maternal blood pressure and heart rate to support timely clinical intervention. Within neonatal care, the Heart Rate Observation (HeRO) system has reduced mortality among very low-birth-weight infants by roughly 20 percent, and additional AI models can predict neonatal sepsis, retinopathy of prematurity, and necrotizing enterocolitis with area-under-the-curve values above 0.80. From an operational standpoint, automated ultrasound workflows deliver biometric measurements at about 14 milliseconds per frame, and dynamic scheduling in IVF laboratories lowers staff workload and per-cycle costs. Home-monitoring platforms for pregnant women are associated with 7–11 percent reductions in maternal mortality and preeclampsia incidence. Despite these advances, most evidence derives from retrospective, single-center studies with limited external validation. Low-resource settings, especially in Sub-Saharan Africa, remain under-represented, and few AI solutions are fully embedded in electronic health records. Conclusions: AI holds transformative promise for perinatal care but will require prospective multicenter validation, equity-centered design, robust governance, transparent fairness audits, and seamless electronic health record integration to translate these innovations into routine practice and improve maternal and neonatal outcomes. Full article

Ozone is a powerful destructive agent in the oxidative process of polymer composites. The destructive ability of ozone depends primarily on its concentration, duration of exposure, the type of polymer, and its matrix structure. In this work, nonwoven PLA/NR fibers with natural rubber contents of 5, 10, and 15 wt.% were obtained, which were then subjected to ozone oxidation for 800 min. The effect of ozone treatment was estimated using various methods of physicochemical analysis. The visual effect was manifested in the form of a change in the color of PLA/NR fibers. The method of differential scanning calorimetry revealed a change in the thermophysical characteristics. The glass transition and cold crystallization temperatures of polylactide shifted toward lower temperatures, and the degree of crystallinity increased. It was found that in PLA/NR fiber samples, the degradation process predominates over the crosslinking process, as an increase in the melt flow rate by 1.5–1.6 times and a decrease in the correlation time determined by the electron paramagnetic resonance method were observed. The IR Fourier method recorded a change in the chemical structure during ozone oxidation. The intensity of the ether bond bands changed, and new bands appeared at 1640 and 1537 cm⁻¹, which corresponded to the formation of –C=C– bonds. Full article

Healthcare data rapidly increases, and patients seek customized, effective healthcare services. Big data and machine learning (ML) enabled smart healthcare systems hold revolutionary potential. Unlike previous reviews that separately address AI or big data, this work synthesizes their convergence through real-world case studies, cross-domain ML applications, and a critical discussion on ethical integration in smart diagnostics. The review focuses on the role of big data analysis and ML towards better diagnosis, improved efficiency of operations, and individualized care for patients. It explores the principal challenges of data heterogeneity, privacy, computational complexity, and advanced methods such as federated learning (FL) and edge computing. Applications in real-world settings, such as disease prediction, medical imaging, drug discovery, and remote monitoring, illustrate how ML methods, such as deep learning (DL) and natural language processing (NLP), enhance clinical decision-making. A comparison of ML models highlights their value in dealing with large and heterogeneous healthcare datasets. In addition, the use of nascent technologies such as wearables and Internet of Medical Things (IoMT) is examined for their role in supporting real-time data-driven delivery of healthcare. The paper emphasizes the pragmatic application of intelligent systems by highlighting case studies that reflect up to 95% diagnostic accuracy and cost savings. The review ends with future directions that seek to develop scalable, ethical, and interpretable AI-powered healthcare systems. It bridges the gap between ML algorithms and smart diagnostics, offering critical perspectives for clinicians, data scientists, and policymakers. Full article

The incorporation of digital health into the medical curricula is becoming more important to better prepare doctors in the future. Digital health comprises a wide range of tools such as electronic health records, health information technology, telemedicine, telehealth, mobile health applications, wearable devices, artificial intelligence, and virtual reality. The present study aimed to explore the medical and biomedical students’ perspectives on the integration of digital health in medical curricula. A cross-sectional study was conducted on the medical and biomedical undergraduate students at the College of Medicine and Health Sciences at Sultan Qaboos University. Data was collected using a self-administered questionnaire. The response rate was 37%. The majority of respondents were in the MD (Doctor of Medicine) program (84.4%), while 29 students (15.6%) were from the BMS (Biomedical Sciences) program. A total of 55.38% agreed that they were familiar with the term ‘e-Health’. Additionally, 143 individuals (76.88%) reported being aware of the definition of e-Health. Specifically, 69 individuals (37.10%) utilize e-Health technologies every other week, 20 individuals (10.75%) reported using them daily, while 44 individuals (23.66%) indicated that they never used such technologies. Despite having several benefits, challenges exist in integrating digital health into the medical curriculum. There is a need to overcome the lack of infrastructure, existing educational materials, and digital health topics. In conclusion, embedding digital health into medical curricula is certainly beneficial for creating a digitally competent healthcare workforce that could help in better data storage, help in diagnosis, aid in patient consultation from a distance, and advise on medications, thereby leading to improved patient care which is a key public health priority. Full article

Background: Unlike most cancers, breast cancer poses a persistent risk of distant recurrence—often years after initial treatment—making long-term risk stratification uniquely challenging. Current tools fall short in predicting late metastatic events, particularly for early-stage patients. Methods: We present an interpretable machine learning (ML) pipeline to predict distant recurrence-free survival at 5, 10, and 15 years, integrating Bayesian network-based causal feature selection, deep feed-forward neural network models (DNMs), and SHAP-based interpretation. Using electronic health record (EHR)-based clinical data from over 6000 patients, we first applied the Markov blanket and interactive risk factor learner (MBIL) to identify minimally sufficient predictor subsets. These were then used to train optimized DNM classifiers, with hyperparameters tuned via grid search and benchmarked against models from 10 traditional ML methods and models trained using all predictors. Results: Our best models achieved area under the curve (AUC) scores of 0.79, 0.83, and 0.89 for 5-, 10-, and 15-year predictions, respectively—substantially outperforming baselines. MBIL reduced input dimensionality by over 80% without sacrificing accuracy. Importantly, MBIL-selected features (e.g., nodal status, hormone receptor expression, tumor size) overlapped strongly with top SHAP contributors, reinforcing interpretability. Calibration plots further demonstrated close agreement between predicted probabilities and observed recurrence rates. The percentage performance improvement due to grid search ranged from 25.3% to 60%. Conclusions: This study demonstrates that combining causal selection, deep learning, and grid search improves prediction accuracy, transparency, and calibration for long-horizon breast cancer recurrence risk. The proposed framework is well-positioned for clinical use, especially to guide long-term follow-up and therapy decisions in early-stage patients. Full article

Background: Despite significant advancements in diabetes care, many individuals with type 2 diabetes (T2D) do not receive optimal care and treatment. Digital interventions promoting behavioral changes have shown promising long-term results in supporting healthier lifestyles but are not implemented in most healthcare offerings, maybe due to lack of general practice support and collaboration. This study evaluates the efficacy of the Digital, Individualized, and Collaborative Treatment of T2D in General Practice Based on Decision Aid (DICTA), a randomized controlled trial integrating a patient-centered smartphone application for lifestyle support in conjunction with a clinical decision support (CDS) tool to assist general practitioners (GPs) in optimizing antidiabetic treatment. Methods: The present randomized controlled trial aims to recruit 400 individuals with T2D from approximately 70 GP clinics (GPCs) in Denmark. The GPCs will be cluster-randomized in a 2:3 ratio to intervention or control groups. The intervention group will receive one year of individualized eHealth lifestyle coaching via a smartphone application, guided by patient-reported outcomes (PROs). Alongside this, the GPCs will have access to the CDS tool to optimize pharmacological decision-making through electronic health records. The control group will receive usual care for one year, followed by the same intervention in the second year. Results: The primary outcome is the one-year change in estimated ten-year cardiovascular risk, assessed by SCORE2-Diabetes calculated from age, smoking status, systolic blood pressure, total and high-density lipoprotein cholesterol, age at diabetes diagnosis, HbA1c, and eGFR. Conclusions: If effective, DICTA could offer a scalable, digital-first approach for improving T2D management in primary care by combining patient-centered lifestyle coaching with real-time pharmacological clinical decision support. Full article

Introduction: The use of 3D-printed models in surgical planning has gained traction in light of its potential to improve precision and patient outcomes. The objective of this study was to review data and provide a time and value analysis of the use of 3D printing at a National Cancer Institute (NCI)-designated comprehensive cancer center. The estimated time of surgical procedures for surgical planning was compared with the time required for procedures that did not use 3D printing. Providers who used 3D printing completed surveys, and then the results of said surveys were analyzed to assess the value of 3D printing. Materials and Methods: Electronic health records were reviewed for patients who underwent hemipelvectomies with and without 3D printing. A list of 20 observations involving 3D printing was used as a baseline sample and matched with another 20 observations that did not utilize 3D printing. Electronic health records were reviewed to obtain mean estimates of the procedure time. The data was collected and analyzed between January 2018 and April 2025. Results: The mean surgery time for procedures using 3D printing was 868 min, compared to 993 min for procedures that did not utilize 3D printing. In contrast, the median procedure times were 907.5 min for procedures using 3D printing and 945.0 min for those that did not utilize 3D printing. Most providers (85.7%) felt that using 3D-printed models or guides was important. Similarly, 80% responded that using a 3D-printed model or guide saved them time, and another 73.3% responded that after using the 3D-printed model, they were confident in their treatment plan. Conclusions: Using 3D printing for surgical cases at the comprehensive cancer center saved procedure time and added value for the surgeons. Full article

The increasing complexity and scale of electronic health records (EHRs) demand advanced tools for efficient data retrieval, summarization, and comparative analysis in clinical practice. MERA (Medical Electronic Records Assistant) is a Retrieval-Augmented Generation (RAG)-based AI system that addresses these needs by integrating domain-specific retrieval with large language models (LLMs) to deliver robust question answering, similarity search, and report summarization functionalities. MERA is designed to overcome key limitations of conventional LLMs in healthcare, such as hallucinations, outdated knowledge, and limited explainability. To ensure both privacy compliance and model robustness, we constructed a large synthetic dataset using state-of-the-art LLMs, including Mistral v0.3, Qwen 2.5, and Llama 3, and further validated MERA on de-identified real-world EHRs from the MIMIC-IV-Note dataset. Comprehensive evaluation demonstrates MERA’s high accuracy in medical question answering (correctness: 0.91; relevance: 0.98; groundedness: 0.89; retrieval relevance: 0.92), strong summarization performance (ROUGE-1 F1-score: 0.70; Jaccard similarity: 0.73), and effective similarity search (METEOR: 0.7–1.0 across diagnoses), with consistent results on real EHRs. The similarity search module empowers clinicians to efficiently identify and compare analogous patient cases, supporting differential diagnosis and personalized treatment planning. By generating concise, contextually relevant, and explainable insights, MERA reduces clinician workload and enhances decision-making. To our knowledge, this is the first system to integrate clinical question answering, summarization, and similarity search within a unified RAG-based framework. Full article