Enhancing the fever workup utilizing a multi-technique modeling approach to diagnose infections more accurately

Abstract

Background: Differentiation between infectious and non-infectious etiologies of the systemic inflammatory response syndrome (SIRS) in trauma patients remains elusive. We hypothesized that mathematical modeling in combination with computerized clinical decision support would assist with this differentiation. The purpose of this study was to determine the capability of various mathematical modeling techniques to predict infectious complications in critically ill trauma patients and compare the performance of these models with a standard fever workup practice (identifying infections on the basis of fever or leukocytosis).

Methods: An 18-mo retrospective database was created using information collected daily from critically ill trauma patients admitted to an academic surgical and trauma intensive care unit. Two hundred forty-three non-infected patient-days were chosen randomly to combine with the 243 infected-days, which created a modeling sample of 486 patient-days. Utilizing ten variables known to be associated with infectious complications, decision trees, neural networks, and logistic regression analysis models were created to predict the presence of urinary tract infections (UTIs), bacteremia, and respiratory tract infections (RTIs). The data sample was split into a 70% training set and a 30% testing set. Models were compared by calculating sensitivity, specificity, positive predictive value, negative predictive value, overall accuracy, and discrimination.

Results: Decision trees had the best modeling performance, with a sensitivity of 83%, an accuracy of 82%, and a discrimination of 0.91 for identifying infections. Both neural networks and decision trees outperformed logistic regression analysis. A second analysis was performed utilizing the same 243 infected days and only those non-infected patient-days associated with negative microbiologic cultures (n = 236). Decision trees again had the best modeling performance for infection identification, with a sensitivity of 79%, an accuracy of 83%, and a discrimination of 0.87.

Conclusion: The use of mathematical modeling techniques beyond logistic regression can improve the robustness and accuracy of predicting infections in critically ill trauma patients. Decision tree analysis appears to have the best potential to use in assisting physicians in differentiating infectious from non-infectious SIRS.

FIG. 1.

Flow diagram of patient selection to evaluate our surgical and trauma intensive care unit culture practice and impact of fever workup. Infected patient-day = day an infectious complication was identified by positive culture (blood, urine, or respiratory secretions); non-infected patient-day: any day with negative cultures or when clinical suspicion of infection was so low that no cultures were obtained; fever workup = cultures of blood, urine, or respiratory secretions because of fever, leukocytosis, or both.

FIG. 2.

Flow diagram of patient selection to evaluate mathematical models. Sample was created by randomly choosing 243 non-infected patient-days to combine with the 243 infected patient-days. This sample was then split into a 70% model training set and a 30% testing set.

FIG. 3.

Flow diagram of patient selection to evaluate mathematical models in patient-days with a microbiologic culture workup. Sample was created by identifying the 236 non-infected patient-days (negative culture) and combining them with the 243 infected patient-days. This sample was then split into a 70% model training set and a 30% testing set.