Predicting Age with Deep Neural Networks from Polysomnograms
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Predicting Age with Deep Neural Networks from Polysomnograms. / Brink-Kjaer, Andreas; Mignot, Emmanuel; Sorensen, Helge B.D.; Jennum, Poul.
42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society: Enabling Innovative Technologies for Global Healthcare, EMBC 2020. IEEE, 2020. p. 146-149 9176254 (I E E E Engineering in Medicine and Biology Society. Conference Proceedings).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Predicting Age with Deep Neural Networks from Polysomnograms
AU - Brink-Kjaer, Andreas
AU - Mignot, Emmanuel
AU - Sorensen, Helge B.D.
AU - Jennum, Poul
N1 - Publisher Copyright: © 2020 IEEE.
PY - 2020
Y1 - 2020
N2 - The aim of this study was to design a new deep learning framework for end-to-end processing of polysomnograms. This framework can be trained to analyze whole-night polysomnograms without the limitations of and bias towards clinical scoring guidelines. We validated the framework by predicting the age of subjects. We designed a hierarchical attention network architecture, which can be pre-trained to predict labels based on 5-minute epochs of data and fine-tuned to predict based on whole-night polysomnography recordings. The model was trained on 511 recordings from the Cleveland Family study and tested on 146 test subjects aged between 6 to 88 years. The proposed network achieved a mean absolute error of 7.36 years and a correlation to true age of 0.857. Sleep can be analyzed using our end-to-end deep learning framework, which we expect can generalize to learning other subject-specific labels such as sleep disorders. The difference in the predicted and chronological age is further proposed as an estimate of biological age.
AB - The aim of this study was to design a new deep learning framework for end-to-end processing of polysomnograms. This framework can be trained to analyze whole-night polysomnograms without the limitations of and bias towards clinical scoring guidelines. We validated the framework by predicting the age of subjects. We designed a hierarchical attention network architecture, which can be pre-trained to predict labels based on 5-minute epochs of data and fine-tuned to predict based on whole-night polysomnography recordings. The model was trained on 511 recordings from the Cleveland Family study and tested on 146 test subjects aged between 6 to 88 years. The proposed network achieved a mean absolute error of 7.36 years and a correlation to true age of 0.857. Sleep can be analyzed using our end-to-end deep learning framework, which we expect can generalize to learning other subject-specific labels such as sleep disorders. The difference in the predicted and chronological age is further proposed as an estimate of biological age.
U2 - 10.1109/EMBC44109.2020.9176254
DO - 10.1109/EMBC44109.2020.9176254
M3 - Article in proceedings
C2 - 33017951
AN - SCOPUS:85091007362
T3 - I E E E Engineering in Medicine and Biology Society. Conference Proceedings
SP - 146
EP - 149
BT - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
PB - IEEE
T2 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020
Y2 - 20 July 2020 through 24 July 2020
ER -
ID: 262746552