5875 papers
In a 7-year longitudinal study of Zambian people living with HIV, baseline age of 50 years or older was found to be independently associated with a significantly steeper rate of arterial stiffening compared to younger patients, highlighting the need for early cardiovascular screening and management of blood pressure and BMI in routine HIV care.
This mixed-methods study protocol outlines a cross-sectional investigation at Kamenge Teaching Hospital in Burundi to assess the high prevalence (41.2%) of multidrug-resistant bacterial infections and identify key risk factors, including prior antibiotic exposure, self-medication, and prolonged hospitalization, to guide improved infection control and empirical therapy strategies.
This study introduces ResNet-CLAC, a novel deep learning framework incorporating multi-scale attention and gated cross-layer fusion, which achieves state-of-the-art accuracy in predicting microsatellite instability from gastrointestinal cancer histology slides, offering a cost-effective and interpretable alternative to traditional diagnostic methods.
This propensity score-matched cohort study found that immediate postnatal cardiac surgery for selected neonates with critical congenital heart disease is feasible and does not increase perioperative risks compared to conventional neonatal surgery, while potentially reducing the rate of post-discharge unplanned reinterventions.
This study demonstrates that postoperative complication severity is a major driver of hospital costs following colon cancer surgery, with emergency procedures incurring significantly higher expenses than elective ones across all complication grades, particularly for severe (Clavien-Dindo Grade IV) complications.
This pilot study demonstrates that an interpretable 30-feature Ridge regression model, trained on leakage-free data, significantly improves fetal birth weight prediction accuracy and standardizes performance across sonographers of varying experience levels compared to the traditional Hadlock 4 formula.
This quasi-experimental study conducted in Qom, Iran, demonstrates that an eight-session cognitive-behavioral therapy educational program significantly reduced fear of childbirth and improved knowledge and attitudes among pregnant women compared to those receiving routine prenatal care.
This paper proposes a novel framework for osteoporosis screening using plain radiographs that combines entropy-guided adaptive block division, DNA-inspired symbolic encoding with CGR/FCGR features, and a hybrid HTGCA-Net deep learning model to achieve high accuracy in both binary and multiclass classification tasks.
This study developed and validated a machine learning model using five readily available clinical parameters (NLR, AST, BUN, CysC, and plasma PQ concentration) that accurately predicts acute kidney injury in paraquat poisoning patients, demonstrating superior performance compared to the traditional Severity Index of Paraquat Poisoning (SIPP) score.
This retrospective study of non-oncological palliative inpatients found that admission neutrophil-to-lymphocyte ratio and mean platelet volume were not independently associated with pressure ulcer presence or stage, a null result attributed to the confounding effect of pre-existing chronic wounds in a referral-based setting and highlighting clinical risk scores as the primary actionable correlates.