98%
921
2 minutes
20
In order to estimate patient length of stay (LOS) and determine the variables that affect, machine learning techniques use intricate datasets and algorithms. Support vector machines (SVMs), neural networks, decision trees, regression models, random forests, and so forth are among the most popular learning techniques. In this paper, for LOS prediction, neural networks process sequence and image data. This study uses patient data undergoing the kidney surgery at Federico II hospital based in Naples. The effectiveness of several machine learning methods was examined. Additionally, the patient characteristics that have the greatest impact on length of stay (LOS) are identified by five different types of neural networks.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.3233/SHTI250703 | DOI Listing |
World J Pediatr Congenit Heart Surg
September 2025
Heart Center, Children's Healthcare of Atlanta; Division of Cardiothoracic Surgery, Department of Surgery, Emory University School of Medicine, Atlanta, GA, USA.
Delayed sternal closure (DSC) is frequently utilized to facilitate the recovery of myocardial function and edema following the Norwood procedure. At our institution, most patients undergo primary sternal closure (PSC), unless specified high-risk characteristics are present. We sought to analyze the outcomes of our approach.
View Article and Find Full Text PDFPLoS One
September 2025
Graduate Program in Public Health - PPGSC/UFES, Vitória, Espírito Santo, Brazil.
A comprehensive understanding of the factors influencing the epidemiological dynamics of COVID-19 across the pandemic waves-particularly in terms of disease severity and mortality-is critical for optimizing healthcare services and prioritizing high-risk populations. Here we aim to analyze the factors associated with short-term and prolonged hospitalization for COVID-19 during the first three pandemic waves. We conducted a retrospective observational study using data from individuals reported in the e-SUS-VS system who were hospitalized for COVID-19 in a state in a southeast state of Brazil.
View Article and Find Full Text PDFPLoS One
September 2025
Queen Alexandra Hospital, Portsmouth University Hospitals NHS Trust, Portsmouth, United Kingdom.
Background: The Hospital Frailty Risk Score (HFRS) has been widely used to identify patients at high risk of poor outcomes and to predict poor outcomes for older people. Although poor health outcomes are associated more with frailty than age, HFRS has been validated only for older people. This study aimed to explore for the first time whether age influences the predictive power of Hospital Frailty Risk Score to predict a long length of stay.
View Article and Find Full Text PDFWorld J Pediatr Congenit Heart Surg
September 2025
Texas Center for Pediatric and Congenital Heart Disease, The University of Texas at Austin Dell Medical School, Austin, TX, USA.
Pericardial effusion (PCE) represents a significant postoperative complication following congenital heart surgery (CHS), contributing to more complex postoperative care and heightened morbidity. In this study, we aim to elucidate the risk factors contributing to PCE development post-CHS through analysis of data from a nationwide, multi-institutional database. Review of the Pediatric Health Information System Database from January 1, 2004, to December 30, 2023.
View Article and Find Full Text PDFInfection
September 2025
General Intensive Care Unit, University Hospital Southampton NHS Foundation Trust, Tremona Road, Southampton, SO16 6YD, UK.
Introduction: Severe viral infections are common in patients requiring admission to intensive care units (ICU). Furthermore, these patients often have additional secondary or co-infections. Despite their prevalence, it remains uncertain to what extent those additional infections contribute to worse outcomes for patients with severe viral infections requiring ICU admission.
View Article and Find Full Text PDF