TY - JOUR
T1 - PhysioMTL
T2 - 3rd Conference on Health, Inference, and Learning, CHIL 2022
AU - Zhu, Jiacheng
AU - Darnell, Gregory
AU - Kumar, Agni
AU - Zhao, Ding
AU - Li, Bo
AU - Nguyen, Xuanlong
AU - Ren, Shirley You
N1 - Funding Information:
We would like to thank Guillermo Sapiro, Calum MacRae, Nick Foti, Russ Webb, Haraldur Hallgrímsson, Gary Shin, Laixi Shi, and Jielin Qiu for valuable feedback and comments on our manuscript.
Publisher Copyright:
© 2022 J. Zhu‡, G. Darnell†, A. Kumar†, D. Zhao‡, B. Li§, X. Nguyen¶ & S.Y. Ren†.
PY - 2022
Y1 - 2022
N2 - Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only 20% of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.
AB - Heart rate variability (HRV) is a practical and noninvasive measure of autonomic nervous system activity, which plays an essential role in cardiovascular health. However, using HRV to assess physiology status is challenging. Even in clinical settings, HRV is sensitive to acute stressors such as physical activity, mental stress, hydration, alcohol, and sleep. Wearable devices provide convenient HRV measurements, but the irregularity of measurements and uncaptured stressors can bias conventional analytical methods. To better interpret HRV measurements for downstream healthcare applications, we learn a personalized diurnal rhythm as an accurate physiological indicator for each individual. We develop Physiological Multitask-Learning (PhysioMTL) by harnessing Optimal Transport theory within a Multitask-learning (MTL) framework. The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task. Our model outperforms competing MTL methodologies on unobserved predictive tasks for synthetic and two real-world datasets. Specifically, our method provides remarkable prediction results on unseen held-out subjects given only 20% of the subjects in real-world observational studies. Furthermore, our model enables a counterfactual engine that generates the effect of acute stressors and chronic conditions on HRV rhythms.
UR - http://www.scopus.com/inward/record.url?scp=85136019239&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136019239&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85136019239
SN - 2640-3498
VL - 174
SP - 354
EP - 374
JO - Proceedings of Machine Learning Research
JF - Proceedings of Machine Learning Research
Y2 - 7 April 2022 through 8 April 2022
ER -