Expert System for Automated Sleep Stage Scoring

Implementation and validation of a computerized expert system sleep scoring is proposed. Such a sysincrease productivity of sleep laboratories and increase the quality while reducing the cost of sleeWe will focus on the basic algorithms for automated sleep stage scoring. The algorithms are based ontheory and follow the steps of the human expert in the decision making process when scoring sleep byKales standard. Likelihood estimates of the suggested and alternative decisions will be used to quansuggested scores. The system will flag low confidence scores to be revised by human interaction. Inilevel of agreement between machine and human is similar to that between two human scorers. Softwaredeveloped to test the effect of the parameters of the algorithms on stage score decisions. An initiatest sets of normal and apneic sleep recordings will be established and the algorithms will be optimdata. We will optimize parameters and validate the system on larger data sets for other diagnostic aon-line, real-time capabilities, and extend the decision model to facilitate further research in sle