A predictive model for the obstructive sleep apnea hypopnea syndrome

Objective To establish a relatively reliable predictive model for obstructive sleep apnea hypopnea syndrome (OSAHS) based on clinical presentations and pulse oximetry data in OSAHS patients.MethodsA case control study was conducted in 107 OSAHS patients and 129 non OSAHS patients.Their data were analysized by logistic regression and regression equation was established.The cutoff point was determined by receive operator characteristic curve (ROC).Results The predicted probability of OSAHS was calculated using the following equation:P=e x /(1+ e x ),x=-1 977+1 27a-1 13b+0 13c a=1 when respiratory effort related arousal is reported and a=0 when it is not reported;b=1 when the subjects is male and 2 when the subjects is female;c=DI (desaturation index ).A probability cutoff point=0 15 was determined.When the probabilities were greater than 0 15,the diagnosis of OSAHS was made with a sensitivity of 96 3% and a specificity of about 50%.Conclusion This study demonstrate that a predictive model based on clinical features and pulse oximetry data is a valuable tool to predict and screen OSAHS in suspected patients.