Validation of computer analysed polygraphic patterns during drowsiness and sleep onset

Joel Hasan, Kari Hirvonen (Corresponding Author), Alpo Värri, Veikko Häkkinen, Pekka Loula

Research output: Contribution to journalArticleScientificpeer-review

32 Citations (Scopus)


A computer system for the automatic analysis of polygraphic records was validated. Records from 9 subjects made during routine MSLT tests were analysed both by two preliminary and one consensus scorer and by a computer system. Special attention was paid to the analysis of drowsiness periods. Therefore a classification system including 7 stages, three for wakefulness and movement, one for drowsiness and three for the sleep stages S1, S2 and SREM was used. Adaptive segmentation was used to divide the records into short segments of variable length (mean 1.6 sec, range 0.5–13.7 sec).

The agreements between the computer and visual scores were relatively good for 5 subjects having a prominent occipital alpha activity during wakefulness (range 70–79%) but less promising (range 64–70%) for the other 4 subjects with “poor” occipital alpha activity. The values obtained corresponded to the inter-scorer agreements. Most of the discrepancies were between adjacent stages. At times in the presence of strongly fluctuating EEG amplitudes and especially with the “low-alpha” subjects it was very difficult to determine exactly even by visual scoring when, for instance, drowsiness became sleep.

It is concluded that the reliability of the system is sufficient for practical purposes especially if critical parts of the records are visually reexamined. It was found to be difficult to define unambiguous scoring criteria for subjects with poorly defined EEG rhythms giving insufficient landmarks for stage determination.

Original languageEnglish
Pages (from-to)117-127
JournalElectroencephalography and Clinical Neurophysiology
Issue number3
Publication statusPublished - 1993
MoE publication typeA1 Journal article-refereed


Dive into the research topics of 'Validation of computer analysed polygraphic patterns during drowsiness and sleep onset'. Together they form a unique fingerprint.

Cite this