SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules

Irfan Al-Hussaini, Cao Xiao, M. Brandon Westover, Jimeng Sun
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:721-739, 2019.

Abstract

Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient’s polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interpretability which defines other desiderata, has largely remained unexplored. In this study, we propose Sleep staging via Prototypes from Expert Rules (SLEEPER ), which combines deep learning models with expert defined rules using a prototype learning framework to generate simple interpretable models. In particular, SLEEPER utilizes sleep scoring rules and expert defined features to derive prototypes which are embeddings of PSG data fragments via convolutional neural networks. The final models are simple interpretable models like a shallow decision tree defined over those phenotypes. We evaluated SLEEPER using two PSG datasets collected from sleep studies and demonstrated that SLEEPER could provide accurate sleep stage classification comparable to human experts and deep neural networks with about 85% ROC-AUC and .7 $\kappa$.

Cite this Paper

BibTeX
@InProceedings{pmlr-v106-al-hussaini19a, title = {SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules}, author = {Al-Hussaini, Irfan and Xiao, Cao and Westover, M. Brandon and Sun, Jimeng}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {721--739}, year = {2019}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {106}, series = {Proceedings of Machine Learning Research}, month = {09--10 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v106/al-hussaini19a/al-hussaini19a.pdf}, url = {https://proceedings.mlr.press/v106/al-hussaini19a.html}, abstract = {Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient’s polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interpretability which defines other desiderata, has largely remained unexplored. In this study, we propose Sleep staging via Prototypes from Expert Rules (SLEEPER ), which combines deep learning models with expert defined rules using a prototype learning framework to generate simple interpretable models. In particular, SLEEPER utilizes sleep scoring rules and expert defined features to derive prototypes which are embeddings of PSG data fragments via convolutional neural networks. The final models are simple interpretable models like a shallow decision tree defined over those phenotypes. We evaluated SLEEPER using two PSG datasets collected from sleep studies and demonstrated that SLEEPER could provide accurate sleep stage classification comparable to human experts and deep neural networks with about 85% ROC-AUC and .7 $\kappa$.} }
Endnote
%0 Conference Paper %T SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules %A Irfan Al-Hussaini %A Cao Xiao %A M. Brandon Westover %A Jimeng Sun %B Proceedings of the 4th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2019 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v106-al-hussaini19a %I PMLR %P 721--739 %U https://proceedings.mlr.press/v106/al-hussaini19a.html %V 106 %X Sleep staging is a crucial task for diagnosing sleep disorders. It is tedious and complex as it can take a trained expert several hours to annotate just one patient’s polysomnogram (PSG) from a single night. Although deep learning models have demonstrated state-of-the-art performance in automating sleep staging, interpretability which defines other desiderata, has largely remained unexplored. In this study, we propose Sleep staging via Prototypes from Expert Rules (SLEEPER ), which combines deep learning models with expert defined rules using a prototype learning framework to generate simple interpretable models. In particular, SLEEPER utilizes sleep scoring rules and expert defined features to derive prototypes which are embeddings of PSG data fragments via convolutional neural networks. The final models are simple interpretable models like a shallow decision tree defined over those phenotypes. We evaluated SLEEPER using two PSG datasets collected from sleep studies and demonstrated that SLEEPER could provide accurate sleep stage classification comparable to human experts and deep neural networks with about 85% ROC-AUC and .7 $\kappa$.
APA
Al-Hussaini, I., Xiao, C., Westover, M.B. & Sun, J.. (2019). SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:721-739 Available from https://proceedings.mlr.press/v106/al-hussaini19a.html.

Related Material