Preliminary Automatic Analysis of Photoplethysmographic and Respiratory Signals for Sleep-Wake Pattern Identification in Young Infants at Risk of SIDS

Sudden Infant Death Syndrome (SIDS) is the leading cause of mortality in the first year of life in industrialized countries and occurs predominantly in young infants (1-6 months) during sleep. 24-hour cardiorespiratory monitoring is a valid diagnostic tool as it continuously records the infant’s vital parameters in the various phases of the day. This exam included 24-hour direct patient observation by a caregiver, who records the infant’s sleep–wake pattern in a diary. These data provide essential insights into the infant’s overall health and neurological development. This study presents a preliminary automated analysis of photoplethysmographic (PPG) and respiratory (RESP) signals acquired through the cardiorespiratory monitor to identify sleep-wake patterns in young infants at risk of SIDS. In particular, a threshold-based algorithm for classifying 30-seconds epochs of PPG and RESP signal into sleep or wake states, validated against 24h diary, was developed. Consequently, the proposed approach eliminates the need for 24-hour continuous, direct patient observation and significantly reduces the time for data analysis by the sleep medicine physician. The developed PPG-RESP-based algorithm demonstrated an overall sensitivity of 83%, a specificity of 79%, and an accuracy of 81% with respect to direct patient observation, with lower performances observed in pathological conditions. Furthermore, the measurement of essential parameters related to sleep quality and cardiorespiratory activity during sleep, including total sleep time (TST), sleep efficiency (SE%), mean heart rate (HR), mean breathing rate (BR), and mean SpO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> levels, showed strong concordance with the assessments manually obtained by the physicians. These findings suggest that the herein-developed method is a valuable preliminary tool to define sleep-wake pattern and sleep quality, thus enhancing the effectiveness of cardiorespiratory monitoring in the diagnostic approach of young infants at risk of SIDS.