A preliminary fuzzy model for screening obstructive sleep apnea

Obstructive sleep apnea (OSA) is a common sleep disorder, especially in middle-aged and obese patients. OSA only occurs during sleep, and is a condition that may go unnoticed for years. OSA is associated with increased risk for hypertension, congestive heart failure and coronary artery disease. Furthermore, patients with OSA have higher risk during and after anesthesia. While undiagnosed OSA is a hazard for the patient, treatment is relatively simple and effective. Therefore, analysis of OSA risk factors and early detection of OSA are critical. This paper describes a fuzzy model for the screening of OSA. The screening questionnaire we are focused on is the STOP-Bang questionnaire. It is made up of eight yes or no questions to assess the risk of OSA. The problem with this model is that lines of low and high risk are too clearly drawn. There are certain predictors and combinations of predictors that have a greater weight in assessing the patient´s risk. Thus, we introduce a fuzzy-logic based model for the screening of OSA. This model more accurately assesses the risk of OSA by assigning weights to certain predictors that play a greater role in OSA.