Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics

Iñigo Urteaga, Tristan Bertin, Theresa M. Hardy, David J. Albers, Noémie Elhadad
Proceedings of the 4th Machine Learning for Healthcare Conference, PMLR 106:66-90, 2019.

Abstract

We present an end-to-end statistical framework for personalized, accurate, and minimally invasive modeling of female reproductive hormonal patterns. Reconstructing and forecasting the evolution of hormonal dynamics is a challenging task, but a critical one to improve general understanding of the menstrual cycle and personalized detection of potential health issues. Our goal is to infer and forecast individual hormone daily levels over time, while accommodating pragmatic and minimally invasive measurement settings. To that end, our approach combines the power of probabilistic generative models (i.e., multi-task Gaussian processes) with the flexibility of neural networks (i.e., a dilated convolutional architecture) to learn complex temporal mappings. To attain accurate hormone level reconstruction with as little data as possible, we propose a sampling mechanism for optimal reconstruction accuracy with limited sampling budget. Our results show the validity of our proposed hormonal dynamic modeling framework, as it provides accurate predictive performance across different realistic sampling budgets and outperforms baselines methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v106-urteaga19a, title = {Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics}, author = {Urteaga, I{\~{n}}igo and Bertin, Tristan and Hardy, Theresa M. and Albers, David J. and Elhadad, No{\'{e}}mie}, booktitle = {Proceedings of the 4th Machine Learning for Healthcare Conference}, pages = {66--90}, 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/urteaga19a/urteaga19a.pdf}, url = {https://proceedings.mlr.press/v106/urteaga19a.html}, abstract = {We present an end-to-end statistical framework for personalized, accurate, and minimally invasive modeling of female reproductive hormonal patterns. Reconstructing and forecasting the evolution of hormonal dynamics is a challenging task, but a critical one to improve general understanding of the menstrual cycle and personalized detection of potential health issues. Our goal is to infer and forecast individual hormone daily levels over time, while accommodating pragmatic and minimally invasive measurement settings. To that end, our approach combines the power of probabilistic generative models (i.e., multi-task Gaussian processes) with the flexibility of neural networks (i.e., a dilated convolutional architecture) to learn complex temporal mappings. To attain accurate hormone level reconstruction with as little data as possible, we propose a sampling mechanism for optimal reconstruction accuracy with limited sampling budget. Our results show the validity of our proposed hormonal dynamic modeling framework, as it provides accurate predictive performance across different realistic sampling budgets and outperforms baselines methods.} }
Endnote
%0 Conference Paper %T Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics %A Iñigo Urteaga %A Tristan Bertin %A Theresa M. Hardy %A David J. Albers %A Noémie Elhadad %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-urteaga19a %I PMLR %P 66--90 %U https://proceedings.mlr.press/v106/urteaga19a.html %V 106 %X We present an end-to-end statistical framework for personalized, accurate, and minimally invasive modeling of female reproductive hormonal patterns. Reconstructing and forecasting the evolution of hormonal dynamics is a challenging task, but a critical one to improve general understanding of the menstrual cycle and personalized detection of potential health issues. Our goal is to infer and forecast individual hormone daily levels over time, while accommodating pragmatic and minimally invasive measurement settings. To that end, our approach combines the power of probabilistic generative models (i.e., multi-task Gaussian processes) with the flexibility of neural networks (i.e., a dilated convolutional architecture) to learn complex temporal mappings. To attain accurate hormone level reconstruction with as little data as possible, we propose a sampling mechanism for optimal reconstruction accuracy with limited sampling budget. Our results show the validity of our proposed hormonal dynamic modeling framework, as it provides accurate predictive performance across different realistic sampling budgets and outperforms baselines methods.
APA
Urteaga, I., Bertin, T., Hardy, T.M., Albers, D.J. & Elhadad, N.. (2019). Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics. Proceedings of the 4th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 106:66-90 Available from https://proceedings.mlr.press/v106/urteaga19a.html.

Related Material