Methodology of Bayesian Model Averaging

The methodology of Bayesian Model Averaging (BMA) is applied for assessment of newborn brain maturity from sleep EEG. In theory this methodology provides the most accurate assessments of uncertainty in decisions. However, the existing BMA techniques have been shown providing biased assessments in the absence of some prior information enabling to explore model parameter space in details within a reasonable time. The lack in details leads to disproportional sampling from the posterior distribution. In case of the EEG assessment of brain maturity, BMA results can be biased because of the absence of information about EEG feature importance. In this paper we explore how the posterior information about EEG features can be used in order to reduce a negative impact of disproportional sampling on BMA performance. We use EEG data recorded from sleeping newborns to test the efficiency of the proposed BMA technique.

Assessment of brain maturity can be obtained by estimating newborn’s age from sleep EEG [1] - [3]. This approach is based on the clinical evidences that the post-conceptional and EEG estimated ages of healthy newborns typically match each other, and the newborn’s brain maturity is most likely abnormal if the ages mismatch [2], [4]. Thus, the mismatch alerts about abnormal brain development.

The established assessment methodologies are based on learning models from EEGs recorded from sleeping newborns whose brain maturity was already assessed by clinicians. The regression models are made capable of mapping the brain maturity into EEG based index [5]. The classification models are made capable of distinguishing maturity levels: at least one with normal and other with abnormal brain maturity [4], [6]. The established methodo...

... middle of paper ...

...heir impact on the outcome is negligible. On the contrary, when the number of weak attributes is large, the disproportion in models becomes significant. Therefore we could improve the BMA results by reducing the disproportional sampling. In this research we aim to explore whether discarding the models using weak EEG attributes will reduce the bias in the assessment of brain maturity.

A trivial strategy of using the posterior information for feature selection within BMA is to use this information to learn a new ensemble from a data set in which the weak attributes were deleted. This strategy reduces a model parameter space, and therefore it enables to explore this space in more detail. The other strategy that can be thought of is refining the ensemble by discarding models which use weak attributes. We expect that such refinement can improve the BMA performance.