Optimized Detection of Central Apneas Preceding Late-Onset Sepsis in Premature Infants.

In neonatal intensive care units, respiratory traces of premature infants developing late onset sepsis (LOS) may also show episodes of apneas. However, since clinical patient monitors often underdetect apneas, clinical experts are required to investigate patients' traces looking for these events. In this work we present a method to optimize an existing algorithm for central apnea (CA) detection and how we used it together with human annotations to investigate the occurrence of CAs preceding LOS.The algorithm was optimized by using a previously-annotated dataset consisting of 90 hours, extracted from 10 premature infants. This allowed to double precision (19.7% vs 9.3%, median values per patient) without affecting recall (90.5% vs 94.5%) compared to the original algorithm. This choice caused the missed identification of just 1 additional CA (4 vs 3) in the whole dataset. The optimized algorithm was then used to annotate a second dataset consisting of 480 hours, extracted from 10 premature infants diagnosed with LOS. Annotations were corrected by two clinical experts.A significantly higher number of CA annotations was found in the 6 hours prior to sepsis onset (p-value < 0.05). The use of the optimized algorithm followed by human annotations proved to be a suitable, time-efficient method to annotate CAs before sepsis in premature infants, enabling future use in large datasets.

Sleep onset (mis)perception in relation to sleep fragmentation, time estimation and pre-sleep arousal.

STUDY OBJECTIVE: To elucidate the contribution of time estimation and pre sleep arousal to the component of sleep onset misperception not explained by sleep fragmentation. METHODS: At-home ambulatory polysomnograms (PSGs) of 31 people with insomnia were recorded. Participants performed a time estimation task and completed the Pre Sleep Arousal Scale (PSAS). Based on previous modelling of the relationship between objectively measured sleep fragmentation and sleep onset misperception, the subjective sleep onset was estimated for each participant as the start of the first uninterrupted sleep bout longer than 30 min. Subsequently, the component of misperception not explained by sleep fragmentation was calculated as the residual error between estimated sleep onset and perceived sleep onset. This residual error was correlated with individual time estimation task results and PSAS scores. RESULTS: A negative correlation between time estimation task results and the residual error of the sleep onset model was found, indicating that participants who overestimated a time interval during the day also overestimated their sleep onset latency (SOL). No correlation was found between PSAS scores and residual error. CONCLUSIONS: Interindividual variations of sleep architecture possibly obscure the correlation of sleep onset misperception with time estimation and pre sleep arousal, especially in small groups. Therefore, we used a previously proposed model to account for the influence of sleep fragmentation. Results indicate that time estimation is associated with sleep onset misperception. Since sleep onset misperception appears to be a general characteristic of insomnia, understanding the underlying mechanisms is probably important for understanding and treating insomnia.