2.50
Hdl Handle:
http://hdl.handle.net/10755/158317
Type:
Presentation
Title:
Implementation & results of a computerized system to capture infant state
Abstract:
Implementation & results of a computerized system to capture infant state
Conference Sponsor:Western Institute of Nursing
Conference Year:2003
Author:Smith, Sandra
P.I. Institution Name:University of Utah, College of Nursing
Title:Assistant Professor
Contact Address:10 South 2000 East, Salt Lake City, UT, 84112, USA
Contact Telephone:801.587.7606
Co-Authors:Keefe, Maureen R.; Kuck K.
Statement of the Problem: Irritable infants have been described as having difficulty getting to sleep, being more easily disturbed, and spending less time in quiet sleep than non-irritable infants. A barrier to the study of sleep patterns in infants is the difficulty in capturing and analyzing data acquired from infant state monitoring systems. A new computer program has been developed which employs a sensor mattress and modified ambulatory cardiac monitor. An algorithm based program was developed to categorize the data into infant behavioral states. Theoretical Framework: Infant irritability is defined as a behavior disorder characterized by recurrent episodes of fussiness, crying, restlessness, diminished soothability, inability to fall asleep, and increased sensitivity to stimuli. These infants spend less time in quiet sleep and more time in active sleep. The gold standard of sleep state identification is direct observation. Direct observation yields a high degree of inter observer reliability but is time intensive for the observers. A computer program was developed to convert physiologic data patterns into infant state categories. Description of the Sample: A subset 20 sleep records (18 infants) were randomly selected from 183 sleep records (164 infants) for validity testing of the computer program. 10 records were from the treatment group (5 pre test and 5 post test) and 10 were from the control group (5 pre test and 5 post test). Participants were predominantly Caucasian middle to upper income families. Infant demographics showed the sample used for validity testing to be representative of the complete data set of 164 infants. Methods: The computer software program to score infant state was developed using Borland’s C++ Builder. Algorithms were implemented using C code. Live observation rules for categorizing quiet sleep, active sleep, awake, and infant-out-of-crib states were the framework for the computer program. The raw data file was initially decoded by the program prior to level 1 feature extraction and state categorization. Level 1 features included mattress signal variance of specified ranges to detect out-of-crib, respiration, small movement, and large movement. More detailed coding was utilized to further determine actual quiet sleep, active sleep, awake, & indeterminate/transition states. A unique feature noted in the sleep files was periodic breathing which was detected and characterized with the use of frequency analysis (FFT). 3 hours of continuous in-crib data was isolated and printed for manual scoring. Sleep data were scored by 2 expert raters (MRK, SLS). Results/Conclusions: Overall percent agreement between the 2 raters was 88.9% and among the 2 raters and computer program was 80.7%. Agreement by state ranged from 75.9-90% agreement for quiet sleep and from 81-89.9% for active sleep. The results of the validity testing indicate that the computer algorithm performs adequately and can be used for automated scoring of infant sleep data, overcoming a significant barrier to the study of sleep patterns in infants.
Repository Posting Date:
26-Oct-2011
Date of Publication:
17-Oct-2011
Sponsors:
Western Institute of Nursing

Full metadata record

DC FieldValue Language
dc.typePresentationen_GB
dc.titleImplementation & results of a computerized system to capture infant stateen_GB
dc.identifier.urihttp://hdl.handle.net/10755/158317-
dc.description.abstract<table><tr><td colspan="2" class="item-title">Implementation &amp; results of a computerized system to capture infant state</td></tr><tr class="item-sponsor"><td class="label">Conference Sponsor:</td><td class="value">Western Institute of Nursing</td></tr><tr class="item-year"><td class="label">Conference Year:</td><td class="value">2003</td></tr><tr class="item-author"><td class="label">Author:</td><td class="value">Smith, Sandra</td></tr><tr class="item-institute"><td class="label">P.I. Institution Name:</td><td class="value">University of Utah, College of Nursing</td></tr><tr class="item-author-title"><td class="label">Title:</td><td class="value">Assistant Professor</td></tr><tr class="item-address"><td class="label">Contact Address:</td><td class="value">10 South 2000 East, Salt Lake City, UT, 84112, USA</td></tr><tr class="item-phone"><td class="label">Contact Telephone:</td><td class="value">801.587.7606</td></tr><tr class="item-email"><td class="label">Email:</td><td class="value">sandra.smith@nurs.utah.edu</td></tr><tr class="item-co-authors"><td class="label">Co-Authors:</td><td class="value">Keefe, Maureen R.; Kuck K. </td></tr><tr><td colspan="2" class="item-abstract">Statement of the Problem: Irritable infants have been described as having difficulty getting to sleep, being more easily disturbed, and spending less time in quiet sleep than non-irritable infants. A barrier to the study of sleep patterns in infants is the difficulty in capturing and analyzing data acquired from infant state monitoring systems. A new computer program has been developed which employs a sensor mattress and modified ambulatory cardiac monitor. An algorithm based program was developed to categorize the data into infant behavioral states. Theoretical Framework: Infant irritability is defined as a behavior disorder characterized by recurrent episodes of fussiness, crying, restlessness, diminished soothability, inability to fall asleep, and increased sensitivity to stimuli. These infants spend less time in quiet sleep and more time in active sleep. The gold standard of sleep state identification is direct observation. Direct observation yields a high degree of inter observer reliability but is time intensive for the observers. A computer program was developed to convert physiologic data patterns into infant state categories. Description of the Sample: A subset 20 sleep records (18 infants) were randomly selected from 183 sleep records (164 infants) for validity testing of the computer program. 10 records were from the treatment group (5 pre test and 5 post test) and 10 were from the control group (5 pre test and 5 post test). Participants were predominantly Caucasian middle to upper income families. Infant demographics showed the sample used for validity testing to be representative of the complete data set of 164 infants. Methods: The computer software program to score infant state was developed using Borland&rsquo;s C++ Builder. Algorithms were implemented using C code. Live observation rules for categorizing quiet sleep, active sleep, awake, and infant-out-of-crib states were the framework for the computer program. The raw data file was initially decoded by the program prior to level 1 feature extraction and state categorization. Level 1 features included mattress signal variance of specified ranges to detect out-of-crib, respiration, small movement, and large movement. More detailed coding was utilized to further determine actual quiet sleep, active sleep, awake, &amp; indeterminate/transition states. A unique feature noted in the sleep files was periodic breathing which was detected and characterized with the use of frequency analysis (FFT). 3 hours of continuous in-crib data was isolated and printed for manual scoring. Sleep data were scored by 2 expert raters (MRK, SLS). Results/Conclusions: Overall percent agreement between the 2 raters was 88.9% and among the 2 raters and computer program was 80.7%. Agreement by state ranged from 75.9-90% agreement for quiet sleep and from 81-89.9% for active sleep. The results of the validity testing indicate that the computer algorithm performs adequately and can be used for automated scoring of infant sleep data, overcoming a significant barrier to the study of sleep patterns in infants. </td></tr></table>en_GB
dc.date.available2011-10-26T20:43:33Z-
dc.date.issued2011-10-17en_GB
dc.date.accessioned2011-10-26T20:43:33Z-
dc.description.sponsorshipWestern Institute of Nursingen_GB
All Items in this repository are protected by copyright, with all rights reserved, unless otherwise indicated.