Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning

Minghui Sun, Matthew M. Engelhard, Benjamin Goldstein
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

Risk assessment in pediatric populations often requires analysis across multiple developmental stages. For example, clinicians may evaluate risks prenatally, at birth, and during WellChild visits. While predictions at later stages typically achieve higher accuracy, it is clinically desirable to make reliable risk assessments as early as possible. Therefore, this study focuses on enhancing prediction performance in early-stage risk assessments. Our solution, **Borrowing From the Future (BFF)**, is a contrastive multi-modal framework that treats each time window as a distinct modality. In BFF, a model is trained on all available data throughout the time while conduct risk assessment using the up-to-time information. This contrastive framework allows the model to "borrow" informative signals from later stages (e.g., WellChild visits) to implicitly supervise the learning at earlier stages (e.g., prenatal/birth stages). We validate BFF on two real-world pediatric outcome prediction tasks, demonstrating consistent improvements in early risk assessment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-sun25a, title = {Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning}, author = {Sun, Minghui and Engelhard, Matthew M. and Goldstein, Benjamin}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/sun25a/sun25a.pdf}, url = {https://proceedings.mlr.press/v298/sun25a.html}, abstract = {Risk assessment in pediatric populations often requires analysis across multiple developmental stages. For example, clinicians may evaluate risks prenatally, at birth, and during WellChild visits. While predictions at later stages typically achieve higher accuracy, it is clinically desirable to make reliable risk assessments as early as possible. Therefore, this study focuses on enhancing prediction performance in early-stage risk assessments. Our solution, **Borrowing From the Future (BFF)**, is a contrastive multi-modal framework that treats each time window as a distinct modality. In BFF, a model is trained on all available data throughout the time while conduct risk assessment using the up-to-time information. This contrastive framework allows the model to "borrow" informative signals from later stages (e.g., WellChild visits) to implicitly supervise the learning at earlier stages (e.g., prenatal/birth stages). We validate BFF on two real-world pediatric outcome prediction tasks, demonstrating consistent improvements in early risk assessment.} }
Endnote
%0 Conference Paper %T Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning %A Minghui Sun %A Matthew M. Engelhard %A Benjamin Goldstein %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-sun25a %I PMLR %U https://proceedings.mlr.press/v298/sun25a.html %V 298 %X Risk assessment in pediatric populations often requires analysis across multiple developmental stages. For example, clinicians may evaluate risks prenatally, at birth, and during WellChild visits. While predictions at later stages typically achieve higher accuracy, it is clinically desirable to make reliable risk assessments as early as possible. Therefore, this study focuses on enhancing prediction performance in early-stage risk assessments. Our solution, **Borrowing From the Future (BFF)**, is a contrastive multi-modal framework that treats each time window as a distinct modality. In BFF, a model is trained on all available data throughout the time while conduct risk assessment using the up-to-time information. This contrastive framework allows the model to "borrow" informative signals from later stages (e.g., WellChild visits) to implicitly supervise the learning at earlier stages (e.g., prenatal/birth stages). We validate BFF on two real-world pediatric outcome prediction tasks, demonstrating consistent improvements in early risk assessment.
APA
Sun, M., Engelhard, M.M. & Goldstein, B.. (2025). Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/sun25a.html.

Related Material