TY - JOUR
T1 - Non-invasive machine learning estimation of effort differentiates sleep-disordered breathing pathology
AU - Hanif, Umaer Rashid
AU - Schneider, Logan D.
AU - Trap, Lotte
AU - Leary, Eileen B.
AU - Moore, Hyatt
AU - Guilleminault, Christian
AU - Jennum, Poul
AU - Sørensen, Helge Bjarup Dissing
AU - Mignot, Emmanuel J. M.
PY - 2019
Y1 - 2019
N2 -
Objective: Obstructive sleep-disordered breathing (SDB) events, unlike central events, are associated with increased respiratory effort. Esophageal pressure (P-es) monitoring is the gold standard for measuring respiratory effort, but it is typically poorly tolerated because of its invasive nature. The objective was to investigate whether machine learning can be applied to routinely collected non-invasive, polysomnography (PSG) measures to accurately model peak negative P-es. Approach: One thousand one hundred and nineteen patients from the Stanford Sleep Clinic with PSGs containing P-es served as the sample. The selected non-invasive PSG signals included nasal pressure, oral airflow, thoracoabdominal effort, and snoring. A long short-term memory neural network was implemented to achieve a context-based mapping between the non-invasive features and the P(es )values. A holdout dataset served as a prospective validation of the algorithm without needing to undertake a costly new study with the impractically invasive P-es. Main results: The median difference between the measured and predicted P-es was 0.61 cmH(2)O with an interquartile range (IQR) of 2.99 cmH(2)O and 5th and 95th percentiles of -5.85 cmH(2)O and 5.47 cmH(2)O, respectively. The model performed well when compared to actual esophageal pressure signal (rho(median) = 0.581, p = 0.01; IQR = 0.298; rho(5%) = 0.106; rho(95%) = 0.843). Significance: A significant difference in predicted P-es was shown between normal breathing and all obstructive SDB events; whereas, central apneas did not significantly differ from normal breathing. The developed system may be used as a tool for quantifying respiratory effort from the existing clinical practice of PSG without the need for P-es, improving characterization of SDB events as obstructive or not.
AB -
Objective: Obstructive sleep-disordered breathing (SDB) events, unlike central events, are associated with increased respiratory effort. Esophageal pressure (P-es) monitoring is the gold standard for measuring respiratory effort, but it is typically poorly tolerated because of its invasive nature. The objective was to investigate whether machine learning can be applied to routinely collected non-invasive, polysomnography (PSG) measures to accurately model peak negative P-es. Approach: One thousand one hundred and nineteen patients from the Stanford Sleep Clinic with PSGs containing P-es served as the sample. The selected non-invasive PSG signals included nasal pressure, oral airflow, thoracoabdominal effort, and snoring. A long short-term memory neural network was implemented to achieve a context-based mapping between the non-invasive features and the P(es )values. A holdout dataset served as a prospective validation of the algorithm without needing to undertake a costly new study with the impractically invasive P-es. Main results: The median difference between the measured and predicted P-es was 0.61 cmH(2)O with an interquartile range (IQR) of 2.99 cmH(2)O and 5th and 95th percentiles of -5.85 cmH(2)O and 5.47 cmH(2)O, respectively. The model performed well when compared to actual esophageal pressure signal (rho(median) = 0.581, p = 0.01; IQR = 0.298; rho(5%) = 0.106; rho(95%) = 0.843). Significance: A significant difference in predicted P-es was shown between normal breathing and all obstructive SDB events; whereas, central apneas did not significantly differ from normal breathing. The developed system may be used as a tool for quantifying respiratory effort from the existing clinical practice of PSG without the need for P-es, improving characterization of SDB events as obstructive or not.
KW - Sleep-disordered breathing
KW - Esophageal pressure
KW - Machine learning
U2 - 10.1088/1361-6579/ab0559
DO - 10.1088/1361-6579/ab0559
M3 - Journal article
C2 - 30736016
SN - 0967-3334
VL - 40
JO - Physiological Measurement
JF - Physiological Measurement
IS - 2
M1 - 025008
ER -