Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables

Abstract

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18 to 79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models—specifically Gaussian mixtures and hidden Markov models—are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's K statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations.

Visualization of Whole-Night Sleep EEG From 2-Channel Mobile Recording Device Reveals Distinct Deep Sleep Stages with Differential Electrodermal Activity

“…Some have attempted 1 or 2 channel classification schemes in order to move toward a more streamlined approach to sleep assessment (Flexer et al, 2005; Berthomier et al, 2007). Most algorithms use a combination of spectral measures (Pan et al, 2012; Yaghouby and Sunderam, 2015) as inputs to their algorithms, but some use raw data measures (Flexer et al, 2005). The accuracy of the published algorithms falls between 70% and 95% accuracy for at least 1 sleep stage, which is typically either slow-wave sleep or awake.…”

A State Space and Density Estimation Framework for Sleep Staging in Obstructive Sleep Apnea

“…Frequency bands were chosen based on the previous literature and guidance from the AASM Sleep Scoring Manual [4], [5], [14], [20], [21], [23]. …”

An epileptic focus location method based on ECoG

“…Recently, a quasi-supervised classifier that models observations in an unsupervised manner, but mimics human responses whenever training scores are available has also been proposed [8]. Programmable computer-controlled devices have also been employed to automatically analyze EEG results [9]. Although these methods all have clinical applications, a new method is needed to effectively locate epileptic foci and, thereby, diagnose and treat epilepsy.…”