Background: Clinical severity scores, such as acute physiology, age, chronic health evaluation II (APACHE II), sequential organ failure assessment (SOFA), Pitt Bacteremia Score (PBS), and European Confederation of Medical Mycology Quality (EQUAL) score, may not reliably predict candidemia prognosis owing to their prespecified scorings that can limit their adaptability and applicability.
Objectives: Unlike those fixed and prespecified scorings, we aim to develop and validate a machine learning (ML) approach that is able to learn predictive models adaptively from available patient data to increase adaptability and applicability.
Methods: Different ML algorithms follow different design philosophies and consequently, they carry different learning biases. We have designed an ensemble meta-learner based on stacked generalisation to integrate multiple learners as a team to work at its best in a synergy to improve predictive performances.
Results: In the multicenter retrospective study, we analysed 512 patients with candidemia from January 2014 to July 2019 and compared a stacked generalisation model (SGM) with APACHE II, SOFA, PBS and EQUAL score to predict the 14-day mortality. The cross-validation results showed that the SGM significantly outperformed APACHE II, SOFA, PBS, and EQUAL score across several metrics, including F1-score (0.68, p < .005), Matthews correlation coefficient (0.54, p < .05 vs. SOFA, p < .005 vs. the others) and the area under the curve (AUC; 0.87, p < .005). In addition, in an independent external test, the model effectively predicted patients' mortality in the external validation cohort, with an AUC of 0.77.
Conclusions: ML models show potential for improving mortality prediction amongst patients with candidemia compared to clinical severity scores.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1111/myc.13667 | DOI Listing |
PLoS One
January 2025
WorldFish Kenya, C/O International Livestock Researtablech Institute, Nairobi, Kenya.
Gender equality and women's empowerment have been increasingly emphasised in food production systems, including fisheries and aquaculture. Accurate assessment and understanding of the state, progress and changes in women's empowerment in the sub-sectors is required. We applied the project level Women's Empowerment in Fisheries and Aquaculture Index (pro-WEFI), which is based on the project-level women's empowerment in agriculture index (pro-WEAI) to standardize the measurement of women's agency and empowerment in fisheries and aquaculture.
View Article and Find Full Text PDFCrit Care Med
December 2024
Department of Psychiatry and Human Behavior, Brown University, Alpert Medical School, Providence, RI.
Objectives: Neurocritically ill patients are at high risk for developing delirium, which can worsen the long-term outcomes of this vulnerable population. However, existing delirium assessment tools do not account for neurologic deficits that often interfere with conventional testing and are therefore unreliable in neurocritically ill patients. We aimed to determine the accuracy and predictive validity of the Fluctuating Mental Status Evaluation (FMSE), a novel delirium screening tool developed specifically for neurocritically ill patients.
View Article and Find Full Text PDFAdv Skin Wound Care
January 2025
Öznur Tiryaki, PhD, RN, is Associate Professor, Faculty of Health Sciences, Department of Midwifery, Sakarya University, Sakarya, Turkey. Hamide Zengin, PhD, RN, is Associate Professor, Faculty of Health Science, Department of Pediatric Nursing, Eskişehir Osmangazi University, Eskişehir, Turkey. Also at Sakarya University, Nursan Çınar, PhD, RN, is Professor, Faculty of Health Sciences, Department of Pediatric Nursing; Meltem Karabay, MD, is Associate Professor, Faculty of Medicine, Research and Training Hospital of Sakarya, Division of Neonatology, Department of Pediatrics; İbrahim Caner, MD, is Professor, Faculty of Medicine, Research and Training Hospital of Sakarya, Division of Neonatology, Department of Pediatrics; and Ertuğrul Güçlü, MD, is Professor, Faculty of Medicine, Department of Infectious Diseases and Clinical Microbiology.
Objective: To determine the effects of sunflower seed oil and coconut oil on the skin integrity and weight gain of preterm infants in the neonatal ICU.
Methods: In this randomized controlled trial, 66 preterm neonates (34-37 weeks' gestation) in the neonatal ICU of a training and research hospital were equally divided into three groups: sunflower seed oil, coconut oil, and control. The weights of neonates in all three groups were measured at admission to the neonatal ICU, at discharge, and at 1 month postdischarge.
Insights Imaging
January 2025
Department of Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, 510515, China.
Objectives: To investigate the image quality and diagnostic performance with ultra-low dose dual-layer detector spectral CT (DLSCT) by various reconstruction techniques for evaluation of pulmonary nodules.
Materials And Methods: Between April 2023 and December 2023, patients with suspected pulmonary nodules were prospectively enrolled and underwent regular-dose chest CT (RDCT; 120 kVp/automatic tube current) and ultra-low dose CT (ULDCT; 100 kVp/10 mAs) on a DLSCT scanner. ULDCT was reconstructed with hybrid iterative reconstruction (HIR), electron density map (EDM), and virtual monoenergetic images at 40 keV and 70 keV.
BJS Open
December 2024
Department of Cardiology, Thorax Centre, Cardiovascular Institute, Erasmus MC, Rotterdam, The Netherlands.
Background: Contrary to the impact of screening, the effect of long-term surveillance on the quality of life of patients with an abdominal aortic aneurysm is not well known. Therefore, the aim of this study was to describe patient-reported outcomes of patients with an abdominal aortic aneurysm approaching the surgical threshold.
Methods: This multicentre, observational cohort study included patients with an abdominal aortic aneurysm with a maximum aneurysm diameter of greater than or equal to 40 mm.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!