Obstructive sleep apnea (OSA) is a significant cause of motor vehicle crashes and chronic diseases. Polysomnography (PSG) has been widely applied in the diagnosis of OSA that a number of physiologic variables are measured and recorded during sleep. Although PSG is treated as the gold standard for diagnosing OSA, it is time-consuming and expensive. Therefore, clinical prediction of high-risk OSA patients using questionnaires and cheap home diagnostic devices has a great potential in reducing healthcare cost and in eliminating environmental variation for some patients tested in the sleeping center.
In this study, a total of 699 patients with possible OSA had been recruited and tested using PSG for overnight attending at the Sleep Center of China Medical University Hospital from Jan. 2004 to Dec. 2005. Subjects with age less than 20 or more than 85 years old were excluded. Therefore only the data of 651 patients were used for further analysis. After statistical analysis and feature selection, support vector machine (SVM) was then used to discriminate normal subjects and patients with different stages of severity.
The results show that oxyhemoglobin desaturation index (ODI) alone has the best prediction outcome for the patients with severe OSA with a sensitivity as high as 87.20%. The sensitivity is only 70.39% in discriminating the normal from abnormal subjects. Based on the cost-benefit analysis, we suggest that home-styled oximeter can be used for sifting severe patients from all suspected patients at the first stage, which is then followed by PSG for discriminate normal subjects and mild and moderate patients. It was found that a cost reduction of NT$1629 (35.72%) per case in average can be achieved under the current Taiwanese insurance setting.
