Very preterm infants may require neonatal intensive care for several months, and the developmental outcome of the care depends on how well brain function can be managed. Direct monitoring of brain function with electroencephalography (EEG) is currently not a part of routine care, since it is perceived challenging due to difficulties in its interpretation. Therefore, automated methods for EEG interpretation are needed in order to make brain monitoring part of the routine in neonatal intensive care. This thesis investigates the detection of spontaneous activity transients (SATs), which form the majority of brain activity in preterm infants. Using manual markings by three doctors in 18 short recordings of preterm EEG, I show that SATs can be recognized by doctors in a consistent manner. A commercially available algorithm is then tested for its ability to detect SATs automatically. The performance of the algorithm is clearly insufficient and therefore it is developed further. The parameters of the new, streamlined algorithm are optimized using unanimous markings by the three doctors as a gold standard. Estimates for the performance of the algorithm on unseen data are obtained by running the optimization 18 times, each time leaving out one of the recordings. The algorithm is then run on the EEG left out from the optimization using the optimized parameters. The estimated performance of the algorithm is found to be excellent, with sensitivity of 96.6 +- 2.8 % and specificity of 95.1 +- 5.6 %. Segmentation of the EEG into SATs and periods between SATs is a starting point for further analysis. One promising direction for future studies is to use SAT%, the proportion of time covered by SATs, to detect cycles of different vigilance stages in preterm infants. Such cyclicity could become a marker of the brain's wellbeing. The algorithm presented in this thesis may contribute to better care of preterm infants.
|Publication status||Published - 2013|
|MoE publication type||G3 Licentiate thesis|
- Spontaneous activity transient
- Automated detection