Abstract
Objectives. To quantitatively predict the risk of obstructive sleep apnea (OSA) without measuring the patient's AHI, based solely on the anthrophometric risk factors in a relevant population, validated with our previous network-based methodology (Mihaicuta et. al, ERJ Sept. 2013, pp.407s).
Methods. A reference database of 1367 patients and a newer 231 validation database from Timisoara “Victor Babes” Hospital (2005-2012; Fall 2013), with over 100 measured criteria, were used to define a methodology inspired by Network Medicine. The AER Score considers 4 relevant metrics: BMI, blood pressure, neck circumference and the Epworth score. The AER scale from 1 to 7 is divided in four risk-severity intervals: low, moderate, high and very high risk of OSA.
Results. The AER predictor emerges from the statistical analysis of both patient databases and helps easily assess the risk of OSA of a new patient. Using it to prioritize patient treatment/evaluation we manage to achieve an overall risk-class correlation of 68.8% between the predicted OSA severity and actual severity determined by measuring the AHI. The rate of cumulative AHI is diagnosed based on patient scheduling
.
Conclusion. The score serves as a predictive classifier of severity, with a high degree of accuracy, if a patient is prone to developing OSA. This model is used to categorize OSA severity and triage patients for diagnostic evaluation without the need for expensive and time-consuming investigations.
- © 2014 ERS