Infection Probability Index: Implementation of an Automated Chronic Wound Infection Marker.

Franziska Schollemann,Michael Czaplik,Henriette Dohmeier,Janosch Kunczik,Andreas Follmann,Carina Barbosa Pereira

doi:10.3390/jcm11010169

Franziska Schollemann, Michael Czaplik + Show 4 more

Open Access

https://doi.org/10.3390/jcm11010169

Copy DOI

Abstract

The number of people suffering from chronic wounds is increasing due to demographic changes and the global epidemics of obesity and diabetes. Innovative imaging techniques within the field of chronic wound diagnostics are required to improve wound care by predicting and detecting wound infections to accelerate the application of treatments. For this reason, the infection probability index (IPI) is introduced as a novel infection marker based on thermal wound imaging. To improve usability, the IPI was implemented to automate scoring. Visual and thermal image pairs of 60 wounds were acquired to test the implemented algorithms on clinical data. The proposed process consists of (1) determining various parameters of the IPI based on medical hypotheses, (2) acquiring data, (3) extracting camera distortions using camera calibration, and (4) preprocessing and (5) automating segmentation of the wound to calculate (6) the IPI. Wound segmentation is reviewed by user input, whereas the segmented area can be refined manually. Furthermore, in addition to proof of concept, IPIs’ correlation with C-reactive protein (CRP) levels as a clinical infection marker was evaluated. Based on average CRP levels, the patients were clustered into two groups, on the basis of the separation value of an averaged CRP level of 100. We calculated the IPIs of the 60 wound images based on automated wound segmentation. Average runtime was less than a minute. In the group with lower average CRP, a correlation between IPI and CRP was evident.

Highlights

Due to both demographic changes and the epidemic of obesity and diabetes, the number of chronic wounds is increasing [1,2]
This paper presents a new approach to detect and predict infections in acute and chronic wounds and monitor wound healing using thermal data as a proof of concept
The core of this paper was the elaboration of the infection probability index (IPI) based on medical hypotheses informed by thermal images

Summary

Introduction

Due to both demographic changes and the epidemic of obesity and diabetes, the number of chronic wounds is increasing [1,2]. More than 1% of the German population suffers from chronic wounds, and the numbers are continually rising [3]. People are especially affected—8% of all residents in German nursing homes have chronic wounds [4]. 1–2% of the population in industrialized countries is said to suffer from chronic wounds [5]. The majority of chronic wounds show a rise of presence of bacterial biofilms which indicate infections [7]. Infections can lead to tissue destruction, delayed wound healing and other severe complications such as sepsis [7,8]. There is an economical interest in improving wound management, as 1 to 3% of the healthcare costs are produced by chronic wounds [2]. Wound infections in particular include the highest costs among surgical complications [10]

Methods

Results

Discussion

Conclusion