To access the session recording, navigate to the content tab and click the view video button. 

Session Schedule

Find a specific presentation in the course by navigating to the timestamp indicated below.

0:01:05
Characterizing the complexity of REM sleep across pediatric development: A chaos-driven approach
Diane Lim on behalf of Toshihiro Imamura (United States)

0:25:55
Time-of-day rhythms of memory function in Chinese university students
Fan Li (China)

0:42:50
Extracting polysomnographic insights before and after adenotonsillectomy for pediatric OSA through advanced recurrence analysis
Toshihiro Imamura (United States) on behalf of Cheng-Bang Chen (United States)

Presentation not available: Digital approaches to delivering parent-based sleep interventions for insomnia in children with ASD/ADHD
Shirley Xin Li (Hong Kong)

1:01:30
Question and answer

Summary

Sleep is essential for the neurodevelopment of children, influencing cognitive, emotional, and physical growth. Traditional methods of analyzing pediatric sleep, such as polysomnography and behavioral assessments, often lack scalability and the capacity for real-time, personalized insights. Recent advancements in artificial intelligence (AI) present promising alternatives, offering more efficient, accurate, and individualized assessments of pediatric sleep. This symposium will explore the integration of AI-driven techniques into pediatric sleep research and clinical practice, highlighting their potential to revolutionize pediatric sleep medicine and developmental health. One of the key applications of AI in pediatric sleep research is its ability to analyze complex and dynamic sleep issues across developmental stages. This symposium will introduce a novel, chaos-driven approach to understanding rapid eye movement (REM) sleep in pediatric populations (ages 6-18). Using Multilevel Heterogeneous Recurrence Analysis (MHRA), a method that visualizes and quantifies complex EEG dynamics, we will explore how age-specific micro- and macrostructural features of REM sleep evolve from childhood to adolescence. This framework allows for the detection of neurodevelopmental signatures embedded within REM sleep patterns, providing valuable insights for diagnosing developmental delays and facilitating early intervention strategies.
Additionally, the symposium will present findings from a study examining the effects of time-of-day fluctuations on memory performance in 75 university students, all of whom were free from sleep disorders. Participants' memory retention was assessed at four distinct time points: before sleep, after sleep, morning, and afternoon, to investigate the temporal rhythms of cognitive performance. These findings will offer insight into how time-of-day variations impact memory function, with implications for understanding cognitive rhythms in other populations.
Another key focus will be the use of AI to analyze polysomnographic data before and after adenotonsillectomy in children with obstructive sleep apnea (OSA). Advanced recurrence analysis techniques are applied to detect subtle changes in sleep architecture, which could improve patient selection for surgical interventions. The integration of AI in this context enables more precise insights that can optimize treatment strategies for pediatric OSA and other sleep disorders.
Finally, the symposium will highlight the use of digital approaches for delivering parent-based sleep interventions in children with sleep disorders related to Autism Spectrum Disorder/Attention Deficit Hyperactivity Disorder. By leveraging telehealth platforms and mobile applications, these interventions provide scalable and accessible solutions that overcome the limitations of traditional face-to-face models.
We will present clinical trial findings, clinical data, and experimental design findings demonstrating the efficacy of digital interventions, showcasing how AI can enhance the delivery of personalized diagnostic and therapeutic sleep interventions tailored to individual needs.
Through these discussions, the symposium will underscore the transformative potential of AI-driven methods in pediatric sleep research and clinical practice, offering new avenues for diagnosis, treatment, and intervention in developmental sleep issues.

Learning Objectives:

Upon completion of this CME activity, participants will be able to:
• Identify challenges in assessing the developing brain
• Recognize methods to analyze complex signals and recognize clinical applications for detecting atypical neurodevelopment in children
• Explore the temporal patterns of memory function in young individuals and understand their cognitive performance rhythms
• Investigate the effects of chronotype and napping habits on memory retention in university students
• Identify specific polysomnographic changes in sleep following adenotonsillectomy in pediatric OSA patients
• Apply the insights gained in this research to improve patient selection for adenotonsillectomy in clinical practice
• Identify the obstacles and barriers to implementing traditional face-to-face service models in pediatric sleep care
• Learn about the efficacy of digital approaches to delivering parent-based sleep intervention for children with insomnia