Predicting Hospital-Acquired Infections by Scoring System with Simple Parameters

Abstract

BackgroundHospital-acquired infections (HAI) are associated with increased attributable morbidity, mortality, prolonged hospitalization, and economic costs. A simple, reliable prediction model for HAI has great clinical relevance. The objective of this study is to develop a scoring system to predict HAI that was derived from Logistic Regression (LR) and validated by Artificial Neural Networks (ANN) simultaneously.Methodology/Principal FindingsA total of 476 patients from all the 806 HAI inpatients were included for the study between 2004 and 2005. A sample of 1,376 non-HAI inpatients was randomly drawn from all the admitted patients in the same period of time as the control group. External validation of 2,500 patients was abstracted from another academic teaching center. Sixteen variables were extracted from the Electronic Health Records (EHR) and fed into ANN and LR models. With stepwise selection, the following seven variables were identified by LR models as statistically significant: Foley catheterization, central venous catheterization, arterial line, nasogastric tube, hemodialysis, stress ulcer prophylaxes and systemic glucocorticosteroids. Both ANN and LR models displayed excellent discrimination (area under the receiver operating characteristic curve [AUC]: 0.964 versus 0.969, p = 0.507) to identify infection in internal validation. During external validation, high AUC was obtained from both models (AUC: 0.850 versus 0.870, p = 0.447). The scoring system also performed extremely well in the internal (AUC: 0.965) and external (AUC: 0.871) validations.ConclusionsWe developed a scoring system to predict HAI with simple parameters validated with ANN and LR models. Armed with this scoring system, infectious disease specialists can more efficiently identify patients at high risk for HAI during hospitalization. Further, using parameters either by observation of medical devices used or data obtained from EHR also provided good prediction outcome that can be utilized in different clinical settings.

A Clinical Adverse Drug Reaction Prediction Model for Patients with Chagas Disease Treated with Benznidazole

“…However, adverse drug reactions (ADRs) occur in 30% to 87% of the patients treated with BZN (19-21), and 12% to 29% of patients fail to complete their full course of treatment (19-21). Therefore, the development of tools to identify patients with high probabilities of developing ADRs to BZN is highly desirable, as this strategy would improve compliance to BZN treatment and minimize complications (21,22).Logistic regression (LR) is a method often used to predict outcomes in health studies (23,24), and it can be used to identify which variables are associated with the occurrence of ADRs to BZN. Therefore, the present study aimed to identify predictive factors for ADRs and ADRs that caused BZN treatment to be discontinued among patients with chronic Chagas disease treated with BZN.…”

“…Logistic regression (LR) is a method often used to predict outcomes in health studies (23,24), and it can be used to identify which variables are associated with the occurrence of ADRs to BZN. Therefore, the present study aimed to identify predictive factors for ADRs and ADRs that caused BZN treatment to be discontinued among patients with chronic Chagas disease treated with BZN.…”

Nosocomial infections in intensive care and medical rehabilitation units, and evaluation of antibiotics prescription

“…Torii et al (2003) emphasized that even low concentrations (10 times lower than safety level) of Ligionella pneumophila found in the water used for washing is pathogenic and can cause serious infections in immunocompromised patients (Torii et al, 2003). Furthermore, Legionnaires' disease is estimated to be present in 3 to 15% of community acquired pneumonia and 10 to 50% of nosocomial infections in European countries and the United States (Chang et al, 2011). It has been reported that about 36% of the water samples are contaminated with L. pneumophila (Yamamoto et al, 2003;Suzuki et al, 2000).…”

Using What You Get

“…92 It has also been applied in medicine. 93–96 Machine learning is applicable to a broad scope of acute care settings, including ED triage, 97 and the ICU. 98, 99 It is also applicable to specific diseases like sepsis 100–103 and traumatic hemorrhage.…”