Analysis of EEG to Quantify Depth of Anesthesia Using Hidden Markov Model

Abstract

Real-time quantification of the patient's consciousness level during anesthesia is an important issue to avoid intraoperative awareness and post-operative side effects. A depth-of-anesthesia (DoA) monitoring method called Bispectral Index (BIS) is generally used for this purpose. However, BIS is known to be inaccurate at the transitory state, and also shows a critical time delay in quantifying the patient's consciousness level. This paper introduces a novel method to reduce the response time in the quantification process. This thesis develops a new index called HDoA by analyzing EEG using Hidden Markov Model. The proposed approach is composed by two steps, training and testing. In the training step, two HMM, awakened and anesthetized model are learned based on each training set. In the testing step, by evaluating the probability of producing the testing EEG from two models respectively, the index HDoA is derived. Since the evaluation of DoA using HMM is training based method, it have better performance with more training process. Experiments show that HDoA has a high correlation with BIS at a steady state, and outperforms BIS in two ways: (1) shorter delay time in transition state, and (2) higher Fisher Score. The validity of HDoA has been tested by 8 real clinical data.