Related Experiment Videos
Machine classification of infant sleep state using cardiorespiratory measures
Insights
Cardiac and respiratory measures accurately classify infant sleep states. This non-invasive method offers a reliable way to monitor sleep and waking patterns in infants during their first six months.
Area of Science:
- Pediatric Sleep Medicine
- Infant Physiology
- Biomedical Engineering
Background:
- Accurate classification of sleep-wake states in infants is crucial for developmental monitoring.
- Traditional polysomnography relies on electroencephalography (EEG) and somatic criteria, requiring specialized expertise.
- Exploring non-EEG based methods for sleep state classification in infants is an active area of research.
Purpose of the Study:
- To evaluate the efficacy of using only cardiac and respiratory measures for classifying sleep and waking states in infants.
- To determine the accuracy of cardiac and respiratory data in differentiating between quiet sleep, waking, and rapid eye movement sleep.
- To assess the contribution of cardiac versus respiratory measures individually and combined for sleep state classification.
Main Methods:
- Collected 12-hour polysomnography recordings from 25 normal infants at multiple time points from 1 week to 6 months of age.
- Recordings included EEG, eye movements, body movements, electromyography, cardiac, and respiratory activity.
- Trained observers classified sleep states (quiet sleep, waking, REM sleep) using EEG and somatic criteria.
- Discriminant analyses were performed using cardiac (heart rate, variability, interbeat interval variation) and respiratory (rate, variability) measures from a subset of infants to classify sleep states in the remaining infants.
Main Results:
- Combined cardiac and respiratory measures achieved a classification accuracy of 84.8%, comparable to expert observers using full polysomnography.
- Classification accuracy using only cardiac measures was 82.0%.
- Classification accuracy using only respiratory measures was 80.0%.
Conclusions:
- Cardiac and respiratory measures alone provide quantifiable and accurate indications of sleep and waking states in normal infants up to 6 months of age.
- These physiological measures offer a promising, potentially less invasive, alternative for infant sleep state assessment.
- Further research can explore the clinical utility of these measures in diverse infant populations.
Abstract:
We examined the potential to classify sleep and waking state over the first 6 months of life in normal infants using only cardiac and respiratory measures. Twelve hour all-night polygraph recordings which included EEG, eye movement, whole body movement, facial muscle electromyographic, cardiac, and respiratory activity from 25 normal infants were collected at 1 week, and at 1, 2, 3, 4, and 6 months of age. Each minute of these recordings was classified into quiet sleep, waking, or rapid eye movement sleep by trained observers using EEG and somatic criteria. Respiratory rate and variability, heart rate and variability, and cardiac interbeat interval variation at respiratory and lower frequencies from 12 of the 25 infants were used as measures in discriminant analyses of sleep state for test on the 13 remaining infants. Using all 7 cardiac and respiratory measures, sleep states were classified with an accuracy approximating that attained by trained observers who had available all polygraph tracings (84.8% overall correct classification). Using only cardiac measures, the accuracy of classification decreased slightly, with an overall correct classification of 82.0%. Using only respiratory measures, the accuracy of classification diminished further, with an overall correct classification of 80.0%. Cardiac and respiratory measures provide quantifiable indications of sleep and waking states over the first 6 months of life in normal infants.