Machine Learning with Scarce Data: Ejection Fraction Prediction Using PLAX View

Zhiyuan Gao, Dominic Yurk, Yaser S. Abu-Mostafa
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:447-457, 2026.

Abstract

We developed a machine learning model to predict left ventricular ejection fraction (LVEF/EF) from parasternal long-axis (PLAX) echocardiographic videos. Because public datasets with labeled PLAX videos are virtually non-existent, our work focuses on an innovative data generation strategy to overcome this scarcity. By leveraging a time-based correlation between clinical notes and echocardiographic videos, combined with fine-tuning view classifiers and proxy labeling, we effectively created a large labeled PLAX dataset and achieved a mean absolute error (MAE) of 6.86%. Given that Apical four-chamber methods, the clinical standard, report MAE values of 6%-7%, our results demonstrate that EF estimation from PLAX views is both feasible and clinically relevant. This surpasses the performance of existing methods and provides a clinically useful solution for situations where apical views may not be feasible. The EF labels for PLAX videos, derived from publicly available datasets, are accessible at https://github.com/Jeffrey4899/PLAX_EF_Labels_202501.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-gao26a, title = {Machine Learning with Scarce Data: Ejection Fraction Prediction Using PLAX View}, author = {Gao, Zhiyuan and Yurk, Dominic and Abu-Mostafa, Yaser S.}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {447--457}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/gao26a/gao26a.pdf}, url = {https://proceedings.mlr.press/v301/gao26a.html}, abstract = {We developed a machine learning model to predict left ventricular ejection fraction (LVEF/EF) from parasternal long-axis (PLAX) echocardiographic videos. Because public datasets with labeled PLAX videos are virtually non-existent, our work focuses on an innovative data generation strategy to overcome this scarcity. By leveraging a time-based correlation between clinical notes and echocardiographic videos, combined with fine-tuning view classifiers and proxy labeling, we effectively created a large labeled PLAX dataset and achieved a mean absolute error (MAE) of 6.86%. Given that Apical four-chamber methods, the clinical standard, report MAE values of 6%-7%, our results demonstrate that EF estimation from PLAX views is both feasible and clinically relevant. This surpasses the performance of existing methods and provides a clinically useful solution for situations where apical views may not be feasible. The EF labels for PLAX videos, derived from publicly available datasets, are accessible at https://github.com/Jeffrey4899/PLAX_EF_Labels_202501.} }
Endnote
%0 Conference Paper %T Machine Learning with Scarce Data: Ejection Fraction Prediction Using PLAX View %A Zhiyuan Gao %A Dominic Yurk %A Yaser S. Abu-Mostafa %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-gao26a %I PMLR %P 447--457 %U https://proceedings.mlr.press/v301/gao26a.html %V 301 %X We developed a machine learning model to predict left ventricular ejection fraction (LVEF/EF) from parasternal long-axis (PLAX) echocardiographic videos. Because public datasets with labeled PLAX videos are virtually non-existent, our work focuses on an innovative data generation strategy to overcome this scarcity. By leveraging a time-based correlation between clinical notes and echocardiographic videos, combined with fine-tuning view classifiers and proxy labeling, we effectively created a large labeled PLAX dataset and achieved a mean absolute error (MAE) of 6.86%. Given that Apical four-chamber methods, the clinical standard, report MAE values of 6%-7%, our results demonstrate that EF estimation from PLAX views is both feasible and clinically relevant. This surpasses the performance of existing methods and provides a clinically useful solution for situations where apical views may not be feasible. The EF labels for PLAX videos, derived from publicly available datasets, are accessible at https://github.com/Jeffrey4899/PLAX_EF_Labels_202501.
APA
Gao, Z., Yurk, D. & Abu-Mostafa, Y.S.. (2026). Machine Learning with Scarce Data: Ejection Fraction Prediction Using PLAX View. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:447-457 Available from https://proceedings.mlr.press/v301/gao26a.html.

Related Material