Revisiting the value of polysomnographic data in insomnia: more than meets the eye.

BACKGROUND: Polysomnography (PSG) is not recommended as a diagnostic tool in insomnia. However, this consensual approach might be tempered in the light of two ongoing transformations in sleep research: big data and artificial intelligence (AI). METHOD: We analyzed the PSG of 347 patients with chronic insomnia, including 59 with Sleep State Misperception (SSM) and 288 without (INS). 89 good sleepers (GS) were used as controls. PSGs were compared regarding: (1) macroscopic indexes derived from the hypnogram, (2) mesoscopic indexes extracted from the electroencephalographic (EEG) spectrum, (3) sleep microstructure (slow waves, spindles). We used supervised algorithms to differentiate patients from GS. RESULTS: Macroscopic features illustrate the insomnia conundrum, with SSM patients displaying similar sleep metrics as GS, whereas INS patients show a deteriorated sleep. However, both SSM and INS patients showed marked differences in EEG spectral components (meso) compared to GS, with reduced power in the delta band and increased power in the theta/alpha, sigma and beta bands. INS and SSM patients showed decreased spectral slope in NREM. INS and SSM patients also differed from GS in sleep microstructure with fewer and slower slow waves and more and faster sleep spindles. Importantly, SSM and INS patients were almost indistinguishable at the meso and micro levels. Accordingly, unsupervised classifiers can reliably categorize insomnia patients and GS (Cohen's κ = 0.87) but fail to tease apart SSM and INS patients when restricting classifiers to micro and meso features (κ=0.004). CONCLUSION: AI analyses of PSG recordings can help moving insomnia diagnosis beyond subjective complaints and shed light on the physiological substrate of insomnia.

Nonstationary filtered shot-noise processes and applications to neuronal membranes.

Filtered shot noise processes have proven to be very effective in modeling the evolution of systems exposed to shot noise sources and have been applied to a wide variety of fields ranging from electronics through biology. In particular, they can model the membrane potential V(m) of neurons driven by stochastic input, where these filtered processes are able to capture the nonstationary characteristics of V(m) fluctuations in response to presynaptic input with variable rate. In this paper we apply the general framework of Poisson point processes transformations to analyze these systems in the general case of nonstationary input rates. We obtain exact analytic expressions, as well as different approximations, for the joint cumulants of filtered shot noise processes with multiplicative noise. These general results are then applied to a model of neuronal membranes subject to conductance shot noise with a continuously variable rate of presynaptic spikes. We propose very effective approximations for the time evolution of the V(m) distribution and a simple method to estimate the presynaptic rate from a small number of V(m) traces. This work opens the perspective of obtaining analytic access to important statistical properties of conductance-based neuronal models such as the first passage time.