Purpose: Candidemia is a highly lethal infection; several scores have been developed to assist the diagnosis process and recently different models have been proposed. Aim of this work was to assess predictive performance of a Random Forest (RF) algorithm for early detection of candidemia in the internal medical wards (IMWs).
Methods: A set of 42 potential predictors was acquired in a sample of 295 patients (male: 142, age: 72 ± 15 years; candidemia: 157/295; bacteremia: 138/295). Using tenfold cross-validation, a RF algorithm was compared with a classic stepwise multivariable logistic regression model; discriminative performance was assessed by C-statistics, sensitivity and specificity, while calibration was evaluated by Hosmer-Lemeshow test.
Results: The best tuned RF algorithm demonstrated excellent discrimination (C-statistics = 0.874 ± 0.003, sensitivity = 84.24% ± 0.67%, specificity = 91% ± 2.63%) and calibration (Hosmer-Lemeshow statistics = 12.779 ± 1.369, p = 0.120), markedly greater than the ones guaranteed by the classic stepwise logistic regression (C-statistics = 0.829 ± 0.011, sensitivity = 80.21% ± 1.67%, specificity = 84.81% ± 2.68%; Hosmer-Lemeshow statistics = 38.182 ± 15.983, p < 0.001). In addition, RF suggests a major role of in-hospital antibiotic treatment with microbioma highly impacting antimicrobials (MHIA) that are found as a fundamental risk of candidemia, further enhanced by TPN. When in-hospital MHIA therapy is not performed, PICC is the dominant risk factor for candidemia, again enhanced by TPN. When PICC is not used and MHIA therapy is not performed, the risk of candidemia is minimum, slightly increased by in-hospital antibiotic therapy.
Conclusion: RF accurately estimates the risk of candidemia in patients admitted to IMWs. Machine learning technique might help to identify patients at high risk of candidemia, reduce the delay in empirical treatment and improve appropriateness in antifungal prescription.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s15010-020-01488-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Hospital attendance, malaria prevalence and self-medication with an antimalarial drug before and after the start of COVID-19 pandemic in a sentinel site for malaria surveillance in Gabon.
Malar J
January 2025
Department of Parasitology-Mycology and Tropical Medicine, Université Des Sciences de La Santé de Libreville, BP 4009, Libreville, Gabon.
Background: The negative impact of COVID-19 pandemic on healthcare service utilization has been reported in several countries. In Gabon, data on the preparedness for future pandemic are lacking. The aim of the present study was to assess the trends of hospital attendance, malaria and self-medication prevalences as well as ITN use before and during Covid-19 first epidemic waves in a paediatric wards of a sentinel site for malaria surveillance, in Libreville, Gabon.
View Article and Find Full Text PDFIntroducing and establishing birth companionship in labour ward of a tertiary care centre in North India: a quality improvement journey through and beyond COVID-19 pandemic.
BMJ Open Qual
January 2025
Professor Department of Obstetrics and Gynaecology, Lady Hardinge Medical College, New Delhi, India.
Background: Allowing a birth companion is the basic right of a mother and is identified as an important component of respectful maternity care. The implementation of this intervention has been a challenge in heavy-load public health facilities in India.
Local Problem: Despite the proven benefits of the presence of birth companions on maternal-fetal outcomes, there was no policy of allowing birth companions in our hospital.
Differences in Characteristics of Peripartum Patients Who Did and Did Not Require an Upgrade to the Intensive Care Unit: A Propensity Score Matching Study.
Medicina (Kaunas)
January 2025
Department of Emergency Medicine, University of Maryland School of Medicine, Baltimore, MD 21201, USA.
This study sought to identify predictors for peripartum patients admitted to non-intensive care wards who later upgraded to the Intensive Care Unit (ICU). This was a retrospective observational study of patients admitted to the Maternal Fetal Ward between 01/2017 and 12/2022, who later upgraded to the ICU. Upgraded patients were 1:1 propensity score matched with those who remained on the Maternal Fetal Ward (control).
View Article and Find Full Text PDFLogistic Stewardship: Supporting Antimicrobial Stewardship Programs Based on Antibiotics Goods Flow.
Antibiotics (Basel)
January 2025
Institute for Hygiene and Public Health, Medical Faculty, University of Bonn, Haus 33, 53113 Bonn, Germany.
Background/objectives: Antimicrobial resistance is a global threat to safe health care, and a reduction in antibiotic consumption seems to be an appropriate preventive measure. In Germany, the reporting of hospital antibiotics consumption to an independent institution is only voluntary. Although a high level of willingness to improve can be assumed in the case of participation, the median consumptions of reporting hospitals change only slightly.
View Article and Find Full Text PDFAn Overlooked Challenge: A Retrospective Audit of Overnutrition in Hospital Rehabilitation Wards.
Healthcare (Basel)
January 2025
Nutrition Research Collaborative, Royal Brisbane & Women's Hospital, Metro North Health, Brisbane, QLD 4029, Australia.
Research shows that obesity has risen among rehabilitation patients. Despite this, nutrition care in subacute rehabilitation wards focuses primarily on preventing and treating protein-energy malnutrition. The continued provision of energy-dense meals during lengthy rehabilitation admissions may present a risk of overnutrition for some patients, which can adversely affect functional outcomes.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!