We have developed a method to predict outcome with oral appliance therapy (OAT) using an artificial intelligence (AI) approach combined with a feedback controlled mandibular positioner (FCMP). We compared the performance of our method against an intuitive approach based on a one-night study used for prediction.
Participants (n=101) with OSA (mean AHI: 30.4 hr-1, mean ODI: 30.6 hr-1, mean BMI: 32.2 kg/m2) received a 2- to 3-night FCMP test and were then treated by OAT. Their response to OAT was predicted by an AI-based approach embedded in MATRx plus (Zephyr Sleep Technologies). This was compared with an intuitive prediction where the ODI from a single night study, i.e., the 2nd night in the FCMP test, with a temporary oral appliance in place was used to predict the responders (ODI < 10 hr-1). Both predictions were compared to the efficacious response (ODI < 10 hr-1) in an outcome study with a custom OA in place. The sensitivity (Sens), specificity (Spec), positive and negative predictive values (PPV & NPV) were calculated for each of the two prediction methods.
The mean ODI from the one-night study (18.1 hr-1) exceeded the mean outcome ODI (12.2 hr-1). Prediction using the intuitive approach resulted in Sens=68%, Spec=90%, PPV=96%, NPV=49%; while the AI-based method performance yielded Sens=88%, Spec=92%, PPV=97%, NPV=72%. Overall accuracy was 89% for AI and 74% for the intuitive approach.
The sensitivity and overall predictive accuracy of the AI-based approach was greater than the intuitive approach, indicating that FCMP test outperformed the intuitive approach. Although it seems counter-intuitive, ODI from a one-night study is not a good estimate of the outcome ODI.
Support (If Any)
Zephyr Sleep Technologies, Prosomnus Sleep Technologies.
Journal Article. 0 words.
Subjects: Neurology ; Sleep Medicine ; Clinical Neuroscience ; Neuroscience