FUZZY EXPERT SYSTEM FOR SEVERITY PREDICTION OF OBSTRUCTIVE SLEEP APNEA HYPOPNEA SYNDROME

Authors : Can ZOROGLU, Serkan TURKELİ

Pages : 37-43

View : 13 | Download : 11

Publication Date : 2017-12-01

Article Type : Research Paper

Abstract :Polysomnography insert ignore into journalissuearticles values(PSG); is standard for both OSAHS diagnosis and severity detection, but it has some disadvantages such as requirement for many equipment, conditions and times to get successful measurements. The aim of the study is to design a fuzzy expert system insert ignore into journalissuearticles values(FES); to predict the severity degree of obstructive sleep apnea hypopnea syndrome insert ignore into journalissuearticles values(OSAHS);. Pre-operation data of 24 patients who had robotic surgery for treatment of OSAHS are used. We divided the data into two: 14 of them for designing the FES and 10 patient data for testing the model. min SpO 2 ,, BMI, Mallampati score, and neck circumference insert ignore into journalissuearticles values(NC); information are used as inputs of the system. The output is fuzzified apnea hypopnea index insert ignore into journalissuearticles values(AHI);. Then, this prediction compared with the actual AHI scores of the patients. Classification accuracy for design step is 100% and correlation between our prediction and AHI is 0.89 after removing 4 patients because of missing data. For the test result, classification accuracy is 100% and value of correlation coefficient is 0.82 after leaving one out due to same reason. Our study shows a possibility of simpler alternative to PSG and proposes fuzziness in standard AHI intervals as different point of view.
Keywords : Fuzzy expert system, Severity detection, prediction, Obstructive Sleep Apnea Hypopnea Syndrome