Classification of Medical Thermograms Belonging Neonates by Using Segmentation, Feature Engineering and Machine Learning Algorithms

Abstract

Monitoring and evaluating the skin temperature value are considerably important for neonates. A system detecting diseases without any harmful radiation in early stages could be developed thanks to thermography. This study is aimed at detecting healthy/unhealthy neonates in neonatal intensive care unit (NICU). We used 40 different thermograms belonging 20 healthy and 20 unhealthy neonates. Thermograms were exported to thermal maps, and subsequently, the thermal maps were converted to a segmented thermal map. Local binary pattern and fast correlation-based filter (FCBF) were applied to extract salient features from thermal maps and to select significant features, respectively. Finally, the obtained features are classified as healthy and unhealthy with decision tree, artificial neural networks (ANN), logistic regression, and random forest algorithms. The best result was obtained as 92.5% accuracy (100% sensitivity and 85% specificity). This study proposes fast and reliable intelligent system for the detection of healthy/unhealthy neonates in NICU.

Computer Management Design and Optimization of City Smart Medical Laboratory Service

“…With the proliferation of permanent residents and floating populations, cities will inevitably face many problems during the development process, including resource depletion, pollution, traffic congestion, and ecosystem destruction. At the same time, the existing medical service system can no longer satisfy the people brought about by economic growth with the increasing demand for medical services; how to solve these problems-system construction based on "smart medical care" may be a feasible solution [1][2][3][4][5][6]. e word "wisdom" of "smart medical care" lies in the fact that its construction method, operation mode, and achieved effects are very different from traditional medical construction.…”

Robust Identification of Subtypes in Non-Small Cell Lung Cancer Using Radiomics

“…Nonetheless, its disadvantage is that it cannot achieve satisfactory classification effect for complicated data as a linear model. However, the LR model attains favorable effects on numerous datasets, which can be easily realized and can be used as a basic modeling method [26,27]. SVM is another extensively utilized classification algorithm, which attempts to calculate the decision-making boundary to separate data.…”