Development of Error Passing Network for Optimizing the Prediction of VO$_2$ peak in Childhood Acute Leukemia Survivors

Nicolas Raymond, Hakima Laribi, Maxime Caru, Mehdi Mitiche, Valerie Marcil, Maja Krajinovic, Daniel Curnier, Daniel Sinnett, Martin Vallières
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:506-521, 2024.

Abstract

Approximately two-thirds of survivors of childhood acute lymphoblastic leukemia (ALL) cancer develop late adverse effects post-treatment. Prior studies explored prediction models for personalized follow-up, but none integrated the usage of neural networks to date. In this work, we propose the Error Passing Network (EPN), a graph-based method that leverages relationships between samples to propagate residuals and adjust predictions of any machine learning model. We tested our approach to estimate patients’ \vo peak, a reliable indicator of their cardiac health. We used the EPN in conjunction with several baseline models and observed up to 12.16% improvement in the mean average percentage error compared to the last established equation predicting \vo peak in childhood ALL survivors. Along with this performance improvement, our final model is more efficient considering that it relies only on clinical variables that can be self-reported by patients, therefore removing the previous need of executing a resource-consuming physical test.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-raymond24a, title = {Development of Error Passing Network for Optimizing the Prediction of VO$_2$ peak in Childhood Acute Leukemia Survivors}, author = {Raymond, Nicolas and Laribi, Hakima and Caru, Maxime and Mitiche, Mehdi and Marcil, Valerie and Krajinovic, Maja and Curnier, Daniel and Sinnett, Daniel and Valli\`eres, Martin}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {506--521}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/raymond24a/raymond24a.pdf}, url = {https://proceedings.mlr.press/v248/raymond24a.html}, abstract = {Approximately two-thirds of survivors of childhood acute lymphoblastic leukemia (ALL) cancer develop late adverse effects post-treatment. Prior studies explored prediction models for personalized follow-up, but none integrated the usage of neural networks to date. In this work, we propose the Error Passing Network (EPN), a graph-based method that leverages relationships between samples to propagate residuals and adjust predictions of any machine learning model. We tested our approach to estimate patients’ \vo peak, a reliable indicator of their cardiac health. We used the EPN in conjunction with several baseline models and observed up to 12.16% improvement in the mean average percentage error compared to the last established equation predicting \vo peak in childhood ALL survivors. Along with this performance improvement, our final model is more efficient considering that it relies only on clinical variables that can be self-reported by patients, therefore removing the previous need of executing a resource-consuming physical test. } }
Endnote
%0 Conference Paper %T Development of Error Passing Network for Optimizing the Prediction of VO$_2$ peak in Childhood Acute Leukemia Survivors %A Nicolas Raymond %A Hakima Laribi %A Maxime Caru %A Mehdi Mitiche %A Valerie Marcil %A Maja Krajinovic %A Daniel Curnier %A Daniel Sinnett %A Martin Vallières %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-raymond24a %I PMLR %P 506--521 %U https://proceedings.mlr.press/v248/raymond24a.html %V 248 %X Approximately two-thirds of survivors of childhood acute lymphoblastic leukemia (ALL) cancer develop late adverse effects post-treatment. Prior studies explored prediction models for personalized follow-up, but none integrated the usage of neural networks to date. In this work, we propose the Error Passing Network (EPN), a graph-based method that leverages relationships between samples to propagate residuals and adjust predictions of any machine learning model. We tested our approach to estimate patients’ \vo peak, a reliable indicator of their cardiac health. We used the EPN in conjunction with several baseline models and observed up to 12.16% improvement in the mean average percentage error compared to the last established equation predicting \vo peak in childhood ALL survivors. Along with this performance improvement, our final model is more efficient considering that it relies only on clinical variables that can be self-reported by patients, therefore removing the previous need of executing a resource-consuming physical test.
APA
Raymond, N., Laribi, H., Caru, M., Mitiche, M., Marcil, V., Krajinovic, M., Curnier, D., Sinnett, D. & Vallières, M.. (2024). Development of Error Passing Network for Optimizing the Prediction of VO$_2$ peak in Childhood Acute Leukemia Survivors. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:506-521 Available from https://proceedings.mlr.press/v248/raymond24a.html.

Related Material