Principles of automatic analysis of sleep records with a hybrid system
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This program has been tested by comparisons with human scoring of the same records, and has proved to have a good accuracy and is actually used as a clinical tool in the exploration of sleep disturbances.
Abstract
A program for automatic sleep staging of whole nights polygraphic records of human subjects is described. The electronic system consists of an analog component, performing a first reduction of data, and a digital one, a small general purpose computer. The computer program assesses first the technical quality of the record, by recognition of artefacts, which may impair the diagnosis procedure. It performs second a two steps analysis, based upon electroencephalogram, muscle activity and eye movements. The first step of analysis is a recognition of elementary patterns on the tape and the second step is a calculation of a minute by minute sleep stage diagnosis, based upon these elementary patterns. This program has been tested by comparisons with human scoring of the same records, and has proved to have a good accuracy. This system is actually used as a clinical tool in the exploration of sleep disturbances.
