AUTHOR=Rothe Felix , Berger Jörn , Welker Pia , Fiebelkorn Richard , Kupper Stefan , Kiesel Denise , Gedat Egbert , Ohrndorf Sarah 

TITLE=Fluorescence optical imaging feature selection with machine learning for differential diagnosis of selected rheumatic diseases

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1228833

DOI=10.3389/fmed.2023.1228833

ISSN=2296-858X

ABSTRACT=Background and Objective: Accurate and fast diagnosis of rheumatic diseases affecting the hands is essential for further treatment decision. Fluorescence optical imaging (FOI) visualizes inflammationinduced impaired microcirculation by increased signal intensity, resulting in different image features. This analysis aimed to find specific image features by FOI, which might be important for the accurate diagnosis of different rheumatic diseases.Patients and methods: FOI images of the hands of patients with different rheumatic diseases such as rheumatoid arthritis (RA), osteoarthritis (OA) and connective tissue diseases (CTD) were assessed in a reading of twenty different image features in three phases of the contrast agent dynamics, yielding sixty different features for each patient. The readings were analyzed for mutual differential diagnosis of the three diseases (One-vs-One) and each disease in all data (One-vs-Rest). In the first step, statistical tools and machine-learning-based methods were applied to reveal importance rankings of the features, that is to find the features that contribute most to the model-based classification. In the second step machine learning with a stepwise increasing number of features was applied, adding successively the most important of the remaining features, to find a reduced set of features which nevertheless achieves maximum diagnostic accuracy.In total, n=605 FOI of both hands were analyzed (n=235 with RA, n=229 with OA and n=141 with CTD). All classification problems showed maximum accuracy with a reduced set of image features. For RA-vs-OA five features were needed for high accuracy, for RA-vs-CTD ten, for OA-vs-CTD sixteen, for RA-vs-Rest five, for OA-vs-Rest eleven and for CTD-vs-Rest fifteen features were FOIfeaturesAI needed, respectively. For all problems, the final importance ranking of the features with respect to the contrast agent dynamics was determined.Conclusions: With the presented investigations, the set of features in FOI examinations relevant to the differential diagnosis of the selected rheumatic diseases, could be remarkably reduced, providing helpful information for the physician.