TY - GEN
T1 - Inference-based subject atypicality and signal quality indicators for physiological data
AU - Tivay, Ali
AU - Kramer, George C.
AU - Hahn, Jin Oh
N1 - Funding Information:
Research supported by National Science Foundation CAREER Award (Grant No. 1748762), and CDMRP (Grant No. W81XWH-19-1-0322).
Funding Information:
Research supported by National Science Foundation CAREERAward (Grant No. 1748762), and CDMRP (Grant No. W81XWH-19-1-0322).
Publisher Copyright:
© 2021 ACM.
PY - 2021/5/18
Y1 - 2021/5/18
N2 - Physiological measurements are an integral part of many established and emerging engineering and biomedical applications that involve physiological modeling, physiological state estimation, and physiological closed loop control. In practice, such measurements exhibit a large degree of variability, which is apparent at multiple levels, including disturbances acting on measured signals and unexpected physiological behavior in certain individuals. In this short paper, we present an inference-based approach to estimating the atypicality of an individual's physiological data both at the level of measurement and physiological behavior. For this purpose, we use data from a cohort of subjects to infer, simultaneously, model representations for measurement disturbances and atypicality of physiological behavior. Using a case study on hematocrit (HCT), cardiac output (CO), and mean arterial pressure (MAP) measurements in response to hemorrhage and colloid infusions, we discuss the merits of the presented approach in deriving reliable subject atypicality and signal quality indicators for physiological data.
AB - Physiological measurements are an integral part of many established and emerging engineering and biomedical applications that involve physiological modeling, physiological state estimation, and physiological closed loop control. In practice, such measurements exhibit a large degree of variability, which is apparent at multiple levels, including disturbances acting on measured signals and unexpected physiological behavior in certain individuals. In this short paper, we present an inference-based approach to estimating the atypicality of an individual's physiological data both at the level of measurement and physiological behavior. For this purpose, we use data from a cohort of subjects to infer, simultaneously, model representations for measurement disturbances and atypicality of physiological behavior. Using a case study on hematocrit (HCT), cardiac output (CO), and mean arterial pressure (MAP) measurements in response to hemorrhage and colloid infusions, we discuss the merits of the presented approach in deriving reliable subject atypicality and signal quality indicators for physiological data.
KW - arterial pressure
KW - cardiac output
KW - hematocrit
KW - hemorrhage
KW - physiological data
KW - probabilistic inference
KW - resuscitation
KW - signal quality
UR - http://www.scopus.com/inward/record.url?scp=85106398867&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106398867&partnerID=8YFLogxK
U2 - 10.1145/3446913.3460316
DO - 10.1145/3446913.3460316
M3 - Conference contribution
AN - SCOPUS:85106398867
T3 - MCPS 2021 - Proceedings of the 2021 Medical Cyber Physical Systems and Internet of Medical Things
SP - 7
EP - 11
BT - MCPS 2021 - Proceedings of the 2021 Medical Cyber Physical Systems and Internet of Medical Things
PB - Association for Computing Machinery, Inc
T2 - 11th Medical Cyber Physical Systems and Internet of Things Workshop, MCPS 2021, part of CPS-IoT Week 2021
Y2 - 18 May 2021
ER -