Sleep spindles are an indicator of the development and integrity of the central nervous system in infants. The visual detection of sleep spindles in EEG is a laborious and time-consuming task. Automated detection of sleep spindles
would reduce the burden associated with the analysis of large datasets and facilitate more rapid identification of sleep abnormalities and an objective means to quantify spindle features.
We developed the Spindle-AI as a web server and is freely available for academic use. The user can choose the sampling frequency of their data and submit a CSV file that contains a single-channel EEG signal. Spindle-AI will predict the start time, end time and the total number of sleep spindles detected in long EEG recordings, allowing for fast and accurate analysis of infant sleep spindles in single-channel EEGs which may act as an early biomarker for abnormal brain maturation.
If you want to know more about Spindle-AI, please visit https://lisda.ucd.ie/Spindle-AI