TY - JOUR
T1 - Design and evaluation of a non-contact bed-mounted sensing device for automated in-home detection of obstructive sleep apnea
T2 - A pilot study
AU - Mosquera-Lopez, Clara
AU - Leitschuh, Joseph
AU - Condon, John
AU - Hagen, Chad C.
AU - Rajhbeharrysingh, Uma
AU - Hanks, Cody
AU - Jacobs, Peter G.
N1 - Funding Information:
Funding: This research was funded by the National Institutes of Health (NIH) grant number NIH/NIHLB 2R01HL098621-04A1.
Publisher Copyright:
© 2019 by the authors.
PY - 2019/9
Y1 - 2019/9
N2 - We conducted a pilot study to evaluate the accuracy of a custom built non-contact pressure-sensitive device in diagnosing obstructive sleep apnea (OSA) severity as an alternative to in-laboratory polysomnography (PSG) and a Type 3 in-home sleep apnea test (HSAT). Fourteen patients completed PSG sleep studies for one night with simultaneous recording from our load-cell-based sensing device in the bed. Subjects subsequently installed pressure sensors in their bed at home and recorded signals for up to four nights. Machine learning models were optimized to classify sleep apnea severity using a standardized American Academy of Sleep Medicine (AASM) scoring of the gold standard studies as reference. On a per-night basis, our model reached a correct OSA detection rate of 82.9% (sensitivity = 88.9%, specificity = 76.5%), and OSA severity classification accuracy of 74.3% (61.5% and 81.8% correctly classified in-clinic and in-home tests, respectively). There was no difference in Apnea Hypopnea Index (AHI) estimation when subjects wore HSAT sensors versus load cells (LCs) only (p-value = 0.62). Our in-home diagnostic system provides an unobtrusive method for detecting OSA with high sensitivity and may potentially be used for long-term monitoring of breathing during sleep. Further research is needed to address the lower specificity resulting from using the highest AHI from repeated samples.
AB - We conducted a pilot study to evaluate the accuracy of a custom built non-contact pressure-sensitive device in diagnosing obstructive sleep apnea (OSA) severity as an alternative to in-laboratory polysomnography (PSG) and a Type 3 in-home sleep apnea test (HSAT). Fourteen patients completed PSG sleep studies for one night with simultaneous recording from our load-cell-based sensing device in the bed. Subjects subsequently installed pressure sensors in their bed at home and recorded signals for up to four nights. Machine learning models were optimized to classify sleep apnea severity using a standardized American Academy of Sleep Medicine (AASM) scoring of the gold standard studies as reference. On a per-night basis, our model reached a correct OSA detection rate of 82.9% (sensitivity = 88.9%, specificity = 76.5%), and OSA severity classification accuracy of 74.3% (61.5% and 81.8% correctly classified in-clinic and in-home tests, respectively). There was no difference in Apnea Hypopnea Index (AHI) estimation when subjects wore HSAT sensors versus load cells (LCs) only (p-value = 0.62). Our in-home diagnostic system provides an unobtrusive method for detecting OSA with high sensitivity and may potentially be used for long-term monitoring of breathing during sleep. Further research is needed to address the lower specificity resulting from using the highest AHI from repeated samples.
KW - Apnea-Hypopnea index
KW - Automated obstructive sleep apnea diagnosis
KW - Contact-less load cell sensor
KW - Long-term breathing monitoring
KW - Unobtrusive obstructive sleep apnea diagnosis
UR - http://www.scopus.com/inward/record.url?scp=85070446448&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070446448&partnerID=8YFLogxK
U2 - 10.3390/bios9030090
DO - 10.3390/bios9030090
M3 - Article
C2 - 31336678
AN - SCOPUS:85070446448
VL - 9
JO - Biosensors
JF - Biosensors
SN - 2079-6374
IS - 3
M1 - 90
ER -