Sleep has been proposed to indicate preserved residual brain functioning in patients suffering from disorders of consciousness (DOC) after awakening from coma. However, a reliable characterization of sleep patterns in this clinical population continues to be challenging given severely altered brain oscillations, frequent and extended artifacts in clinical recordings and the absence of established staging criteria. In the present study, we try to address these issues and investigate the usefulness of a multivariate machine learning technique based on permutation entropy, a complexity measure. Specifically, we used long-term polysomnography (PSG), along with video recordings in day and night periods in a sample of 23 DOC; 12 patients were diagnosed as Unresponsive Wakefulness Syndrome (UWS) and 11 were diagnosed as Minimally Conscious State (MCS). Eight hour PSG recordings of healthy sleepers (N = 26) were additionally used for training and setting parameters of supervised and unsupervised model, respectively. In DOC, the supervised classification (wake, N1, N2, N3 or REM) was validated using simultaneous videos which identified periods with prolonged eye opening or eye closure.The supervised classification revealed that out of the 23 subjects, 11 patients (5 MCS and 6 UWS) yielded highly accurate classification with an average F1-score of 0.87 representing high overlap between the classifier predicting sleep (i.e. one of the 4 sleep stages) and closed eyes. Furthermore, the unsupervised approach revealed a more complex pattern of sleep-wake stages during the night period in the MCS group, as evidenced by the presence of several distinct clusters. In contrast, in UWS patients no such clustering was found. Altogether, we present a novel data-driven method, based on machine learning that can be used to gain new and unambiguous insights into sleep organization and residual brain functioning of patients with DOC.

Human newborns spend up to 18 hours sleeping. The organization of their sleep differs immensely from adult sleep, and its quick maturation and fundamental changes correspond to the rapid cortical development at this age. Manual sleep classification is specifically challenging in this population given major body movements and frequent shifts between vigilance states; in addition various staging criteria co-exist. In the present study we utilized a machine learning approach and investigated how EEG complexity and sleep stages evolve during the very first weeks of life. We analyzed 42 full-term infants which were recorded twice (at week two and five after birth) with full polysomnography. For sleep classification EEG signal complexity was estimated using multi-scale permutation entropy and fed into a machine learning classifier. Interestingly the baby’s brain signal complexity (and spectral power) revealed developmental changes in sleep in the first 5 weeks of life, and were restricted to NREM (“quiet”) and REM (“active sleep”) states with little to no changes in state wake. Data demonstrate that our classifier performs well over chance (i.e., >33% for 3-class classification) and reaches almost human scoring accuracy (60% at week-2, 73% at week-5). Altogether, these results demonstrate that characteristics of newborn sleep develop rapidly in the first weeks of life and can be efficiently identified by means of machine learning techniques.

Past research has demonstrated differential responses of the brain during sleep in response especially to variations in paralinguistic properties of auditory stimuli, suggesting they can still be processed “offline”. However, the nature of the underlying mechanisms remains unclear. Here, we therefore used multivariate pattern analyses to directly test the similarities in brain activity among different sleep stages (non-rapid eye movement stages N1-N3, as well as rapid-eye movement sleep REM, and wake). We varied stimulus salience by manipulating subjective (own vs. unfamiliar name) and paralinguistic (familiar vs. unfamiliar voice) salience in 16 healthy sleepers during an 8-h sleep opportunity. Paralinguistic salience (i.e., familiar vs. unfamiliar voice) was reliably decoded from EEG response patterns during both N2 and N3 sleep. Importantly, the classifiers trained on N2 and N3 data generalized to N3 and N2, respectively, suggesting similar processing mode in these states. Moreover, projecting the classifiers’ weights using a forward model revealed similar fronto-central topographical patterns in NREM stages N2 and N3. Finally, we found no generalization from wake to any sleep stage (and vice versa) suggesting that “processing modes” or the overall processing architecture with respect to relevant oscillations and/or networks substantially change from wake to sleep. However, the results point to a single and rather uniform NREM-specific mechanism that is involved in (auditory) salience detection during sleep.

Human newborns spend up to 18 hours sleeping. The organization of their sleep differs immensely from adult sleep, and its quick maturation and fundamental changes correspond to the rapid cortical development at this age. Manual sleep classification is specifically challenging in this population given major body movements and frequent shifts between vigilance states; in addition various staging criteria co-exist. In the present study we utilized a machine learning approach and investigated how EEG complexity and sleep stages evolve during the very first weeks of life. We analyzed 42 full-term infants which were recorded twice (at week two and five after birth) with full polysomnography. For sleep classification EEG signal complexity was estimated using multi-scale permutation entropy and fed into a machine learning classifier. Interestingly the baby’s brain signal complexity (and spectral power) revealed huge developmental changes in sleep in the first 5 weeks of life, and were restricted to NREM (“quiet”) and REM (“active sleep”) states with little to no changes in state wake. Data demonstrate that our classifier performs well over chance (i.e., >33% for 3-class classification) and reaches almost human scoring accuracy (60% at week-2, 73% at week-5). Altogether, these results demonstrate that characteristics of newborn sleep develop rapidly in the first weeks of life and can be efficiently identified by means of machine learning techniques. Author summary: The organization of newborn sleep differs from adult sleep, and its ongoing maturation over time corresponds with cortical development. However, sleep scoring in this population is challenging given frequent artifacts in polysomnography (PSG) and absence of established staging criteria which results in low inter-scorer reliability. To investigate changes in the early brain activity, we analyzed large sample of newborn data at week 2 and 5 after birth. First we evaluated sleep that was previously scored visually, in terms of both entropy and oscillatory power. Next we accessed the performance of automatic sleep scoring based on machine learning compared with conventional, manual scoring. We observed clear developmental changes on the brain-level in the first 5 weeks of life in human newborns. These changes were limited to “quiet” NREM and “active” REM sleep. Also our classifier data demonstrated that we can classify well above chance and similar to human scorers using multi-scale permutation entropy (and just 6 EEG and 5 physiological channels).