Camera-Based Peripheral Edema Measurement Using Machine Learning

• Published in: 2018 IEEE International Conference on Healthcare Informatics (ICHI) pp. 115 - 122
• Main Authors: Junbo Chen, Tingyu Mao, Yunlei Qiu, Duoying Zhou, Masterson Creber, Ruth, Kostic, Zoran
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: artificial-neural-networks-(ANN); Computational modeling; deep-learning-(DL); Heart; heart-failure; histogram-of-oriented-gradients-(HOG); Histograms; Machine learning; machine-learning-(ML); peripheral-edema; Skin; Support vector machines
• ISSN: 2575-2634
• DOI: 10.1109/ICHI.2018.00020

Peripheral edema is the most common symptom of heart failure. Reliable measurement of edema and continuous monitoring of trends provide critical clinical information and can be used for averting episodes of acute decompensation and hospitalizations. Based on the edema pitting-test, new videobased methods for measurement of peripheral edema stages are presented. The methods use videos of skin during the pittingtest, which are processed by machine learning or deep learning techniques to provide classification into one of four edema stages. The proposed methods are implemented and evaluated on videos taken on edema simulators. Variations of the proposed models applied to edema simulators yield classification accuracies in the range between 87% and 98%.