scholarly journals Prediction of risk of acquiring urinary tract infection during hospital stay based on machine-learning: A retrospective cohort study

PLoS ONE ◽  
2021 ◽  
Vol 16 (3) ◽  
pp. e0248636
Author(s):  
Jens Kjølseth Møller ◽  
Martin Sørensen ◽  
Christian Hardahl
Keyword(s):  
Machine Learning ◽  
Urinary Tract ◽  
Hospital Stay ◽  
Urinary Tract Infections ◽  
Retrospective Cohort ◽  
Area Under The Curve ◽  
Machine Learning Algorithms ◽  
Entry Model ◽  
Tract Infections ◽  
Healthcare Associated

Background Healthcare associated infections (HAI) are a major burden for the healthcare system and associated with prolonged hospital stay, increased morbidity, mortality and costs. Healthcare associated urinary tract infections (HA-UTI) accounts for about 20–30% of all HAI’s, and with the emergence of multi-resistant urinary tract pathogens, the total burden of HA-UTI will most likely increase. Objective The aim of the current study was to develop two predictive models, using data from the index admission as well as historic data on a patient, to predict the development of UTI at the time of entry to the hospital and after 48 hours of admission (HA-UTI). The ultimate goal is to predict the individual patient risk of acquiring HA-UTI before it occurs so that health care professionals may take proper actions to prevent it. Methods Retrospective cohort analysis of approx. 300 000 adult admissions in a Danish region was performed. We developed models for UTI prediction with five machine-learning algorithms using demographic information, laboratory results, data on antibiotic treatment, past medical history (ICD10 codes), and clinical data by transformation of unstructured narrative text in Electronic Medical Records to structured data by Natural Language Processing. Results The five machine-learning algorithms have been evaluated by the performance measures average squared error, cumulative lift, and area under the curve (ROC-index). The algorithms had an area under the curve (ROC-index) ranging from 0.82 to 0.84 for the entry model (T = 0 hours after admission) and from 0.71 to 0.77 for the HA-UTI model (T = 48 hours after admission). Conclusion The study is proof of concept that it is possible to create machine-learning models that can serve as early warning systems to predict patients at risk of acquiring urinary tract infections during admission. The entry model and the HA-UTI models perform with a high ROC-index indicating a sufficient sensitivity and specificity, which may make both models instrumental in individualized prevention of UTI in hospitalized patients. The favored machine-learning methodology is Decision Trees to ensure the most transparent results and to increase clinical understanding and implementation of the models.

scholarly journals 2107. Decision Trees vs. Neural Networks for Supervised Machine Learning-Based Prediction of Healthcare-Associated Urinary Tract Infections

2018 ◽  
Vol 5 (suppl_1) ◽  
pp. S618-S618
Author(s):  
Philip Zachariah ◽  
Elioth Mirsha Sanabria Buenaventura ◽  
Jianfang Liu ◽  
Bevin Cohen ◽  
David Yao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Urinary Tract ◽  
Decision Trees ◽  
Urinary Tract Infections ◽  
Supervised Machine Learning ◽  
Tract Infections ◽  
Healthcare Associated

scholarly journals Catheter-Associated Urinary Tract Infections: Diagnosis, Treatment, and Prevention

2019 ◽  
Vol 2 (1) ◽  
pp. 01-04
Author(s):  
Karen Clarke
Keyword(s):  
Urinary Tract ◽  
Hospital Stay ◽  
Urinary Tract Infections ◽  
Common Type ◽  
Healthcare Associated Infection ◽  
Urinary Catheters ◽  
Treatment And Prevention ◽  
Financial Consequences ◽  
Tract Infections ◽  
Healthcare Associated

The most common type of healthcare-associated infection (HAI) is a urinary tract infection (UTI), and 80 percent of these are associated with the use of indwelling urinary catheters (IUCs). These are termed catheter-associated urinary tract infections (CAUTIs). It has been estimated that about 25 percent of all hospitalized patients have an IUC placed during their hospital stay. In addition to the morbidity and mortality that may be associated with a CAUTI, there are also financial consequences. This is particularly true since as of October 1, 2008, the Centers for Medicare and Medicaid Services stopped reimbursing hospitals for several types of infections acquired during a hospital stay, including CAUTIs. In United States (U.S.) the estimated annual cost of treating these CAUTIs is $350 million. It has been proposed that a large percentage of CAUTIs should be preventable. This article will discuss the diagnosis, treatment, and prevention of CAUTIs

scholarly journals Frequency of Healthcare-Associated Infections in the Elderly Patient Hospitalized

2021 ◽  
Author(s):  
Aria Rahmani ◽  
Alireza Namazi Shabestari ◽  
Maryam Sadeh ◽  
Reza Bidaki ◽  
Saeidreza Jamalimoghadamsiahkli ◽  
...  
Keyword(s):  
Urinary Tract ◽  
Hospital Stay ◽  
Urinary Tract Infections ◽  
Length Of Hospital Stay ◽  
The Elderly ◽  
Central Line ◽  
Ventilator Associated Pneumonia ◽  
Healthcare Associated Infections ◽  
Tract Infections ◽  
Healthcare Associated

Introduction: Healthcare- Associated Infections (HAI) are known to be one of the most important health issues in developed and developing countries. The most common infections include central line-associated bloodstream infections, catheter-associated urinary tract infections, ventilator-associated pneumonia and surgical site infection. The aim of this study was to investigate the incidence of nosocomial infections in the elderly patients. Methods: In this cross-sectional study, 1279 patients were 60 years of age or older. Patients who had been admitted for more than 48 hours in the hospital and had no signs of infection at the time of admission, were entered into the study. It was evaluated four most common HAI, according to CDC include bacteremia, central line-associated blood stream infections, urinary tract infections, and ventilator-associated pneumonia. Infections may also occur at surgery sites, known as surgical site infections. The Chi-square and T- test or analysis of variance was used for data analysis. Results: Of the total patients, 93 (7.3%) developed HAI at duration admission. The highest rate of infection was bacteremia, which was 48.4 % and then urinary tract infection 21.5%. The prevalence of HAI among patients with cardiovascular diseases was relatively higher than underlying diseases. The frequency of length of hospital stay was significant in patients > 7 days with 68.8% in the HAI group. Conclusion: Our findings showed that patients with cardiovascular, renal and pulmonary disease are more susceptible to HAIs. Due to the increased length of hospital stay increases the risk of infection, it is recommended to discharge patients as soon as possible.

Bacteremia due to healthcare-associated urinary tract infections in children

2021 ◽  
Vol 28 (2) ◽  
pp. 147-149
Author(s):  
F. Devrim ◽  
İ. Çağlar ◽  
N. Demiray ◽  
Y. Oruç ◽  
Y. Ayhan ◽  
...  
Keyword(s):  
Urinary Tract ◽  
Urinary Tract Infections ◽  
Tract Infections ◽  
Healthcare Associated

scholarly journals Fosfomycin versus Ertapenem for Outpatient Treatment of Complicated Urinary Tract Infections: A Multicenter, Retrospective Cohort Study

2021 ◽  
Author(s):  
Noah Wald-Dickler ◽  
Todd C Lee ◽  
Soodtida Tangpraphaphorn ◽  
Susan M Butler-Wu ◽  
Nina Wang ◽  
...  
Keyword(s):  
Cohort Study ◽  
Urinary Tract ◽  
Los Angeles ◽  
Urinary Tract Infections ◽  
Retrospective Cohort Study ◽  
Outpatient Treatment ◽  
Retrospective Cohort ◽  
Clinical Success ◽  
Public Hospitals ◽  
Tract Infections

Abstract Objectives We sought to determine the comparative efficacy of fosfomycin vs. ertapenem for outpatient treatment of complicated urinary tract infections (cUTI). Methods We conducted a multi-centered, retrospective cohort study involving patients with cUTI treated with outpatient oral fosfomycin vs. intravenous ertapenem at three public hospitals in Los Angeles County between January 2018 and September 2020. The primary outcome was resolution of clinical symptoms 30 days after diagnosis. Results We identified 322 patients with cUTI treated with fosfomycin (n = 110) or ertapenem (n = 212) meeting study criteria. Study arms had similar demographics, although patients treated with ertapenem more frequently had pyelonephritis or bacteremia while fosfomycin-treated patients had more retained catheters, nephrolithiasis, or urinary obstruction. Most infections were due to extended-spectrum β-lactamase-producing E. coli and Klebsiella pneumoniae; 80-90% of which were resistant to other oral options. Adjusted odds ratios for clinical success at 30 days, clinical success at last follow up, and relapse were 1.21 (0.68 to 2.16), 0.84 (0.46 to 1.52), and 0.94 (0.52 to 1.70), for fosfomycin vs. ertapenem, respectively. Patients treated with fosfomycin had significant reductions in length of hospital stay and length of antimicrobial therapy, and fewer adverse events (1 vs. 10). Fosfomycin outcomes were similar irrespective of duration of lead-in IV therapy or fosfomycin dosing interval (daily, every other day, every third day). Conclusion These results would support the conduct of a randomized controlled trial to verify efficacy. In the meantime, they suggest fosfomycin may be a reasonable stepdown from IV antibiotics for cUTI.

Development and evaluation of a website for surveillance of healthcare-associated urinary tract infections in Australia

2018 ◽  
Vol 99 (1) ◽  
pp. 98-102
Author(s):  
O. Fasugba ◽  
J. Koerner ◽  
N. Bennett ◽  
S. Burrell ◽  
R. Laguitan ◽  
...  
Keyword(s):  
Urinary Tract ◽  
Urinary Tract Infections ◽  
Tract Infections ◽  
Healthcare Associated
Sign in / Sign up

Export Citation Format

Share Document