Discriminating Bacterial Infection from Other Causes of Fever Using Body Temperature Entropy Analysis

Abstract

Body temperature is usually employed in clinical practice by strict binary thresholding, aiming to classify patients as having fever or not. In the last years, other approaches based on the continuous analysis of body temperature time series have emerged. These are not only based on absolute thresholds but also on patterns and temporal dynamics of these time series, thus providing promising tools for early diagnosis. The present study applies three time series entropy calculation methods (Slope Entropy, Approximate Entropy, and Sample Entropy) to body temperature records of patients with bacterial infections and other causes of fever in search of possible differences that could be exploited for automatic classification. In the comparative analysis, Slope Entropy proved to be a stable and robust method that could bring higher sensitivity to the realm of entropy tools applied in this context of clinical thermometry. This method was able to find statistically significant differences between the two classes analyzed in all experiments, with sensitivity and specificity above 70% in most cases.

Keywords: Approximate Entropy; Sample Entropy; Slope Entropy; body temperature; classification; fever; time series.

Figure 1

Example of body temperature records from the experimental database. B: Bacterial infection. NB: Nonbacterial cause of fever.

Figure 2

Example of ROC curve using Slope Entropy (SlpEn), $m=3$, and $\gamma =0.20$.

Figure 3

Example of graphical results for each method tested with $N=1100$. SlpEn results have been inverted and rescaled for better visualization. (a) Results for ApEn with $r=0.2$ and $m=3$. (b) Results for SlpEn with $\gamma =0.2$ and $m=3$ (In absolute value and normalized by 100). (c) Results for SampEn with $r=0.2$ and $m=3$.