The use of neural networks in the analysis of sleep stages and the diagnosis of narcolepsy
Jens Stephansen, Aditya Ambati, Eileen Leary, Hyatt Moore, Oscar Carrillo, Ling Lin, Birgit Hogl, Ambra Stefani, Seung-Chul Hong, Tae Won Kim, Fabio Pizza, Giuseppe Plazzi, Stefano Vandi, Elena Antelmi, Dimitri Perrin, Samuel Kuna, Paula Schweitzer, Clete Kushida, Paul Peppard, Poul Jennum, Helge Sorensen, Dr. Emmanuel Mignot
Received: 1st October 17
We used neural networks in ~3,000 sleep recordings from over 10 locations to automate sleep stage scoring, producing a probability distribution called an hypnodensity graph. Accuracy was validated in 70 subjects scored by six technicians (gold standard). Our best model performed better than any individual scorer, reaching an accuracy of 0.87 (and 0.95 when predictions are weighed by scorer agreement). It also scores sleep stages down to 5-second instead of the conventional 30-second scoring-epochs. Accuracy did not vary by sleep disorder except for narcolepsy, suggesting scoring difficulties by machine and/or humans. A narcolepsy biomarker was extracted and validated in 105 type-1 narcoleptics versus 331 controls producing a specificity of 0.96 and a sensitivity of 0.91. Similar performances were obtained against a high pretest probability sample of type-2 narcolepsy and idiopathic hypersomnia patients. Addition of HLA-DQB1*06:02 increased specificity to 0.99. Our method streamlines scoring and diagnoses narcolepsy accurately.
This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.