Unified Screening for Multiple Diseases

Yiğit Narter, Alihan Hüyük, Mihaela Van Der Schaar, Cem Tekin
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:45737-45769, 2025.

Abstract

Current screening programs that focus on improving patient health while minimizing screening costs are tailored for individual diseases. Designing unified screening programs for multiple diseases requires carefully balancing competing disease risks, which is an open problem. In this work, we address this problem by casting unified screening as a referral problem, in which we choose to activate a subset of screening policies for individual diseases by accounting for competing risks that influence patient outcomes. We introduce a novel optimization framework that incorporates disease risks, budget constraints, and diagnostic error limits and characterize the structural properties of the optimal referral policy. For the unified screening of two diseases, we show that the optimal activation threshold for the screening of one disease depends on the risk of the other, resulting in decision boundaries with distinct risk-dependent profiles. We compare our unified model with independent screening programs that apply isolated activation thresholds for screening of each disease. Our approach optimizes screening decisions collectively, improving overall survival outcomes, particularly for patients with high disease risks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-narter25a, title = {Unified Screening for Multiple Diseases}, author = {Narter, Yi\u{g}it and H\"{u}y\"{u}k, Alihan and Van Der Schaar, Mihaela and Tekin, Cem}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {45737--45769}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/narter25a/narter25a.pdf}, url = {https://proceedings.mlr.press/v267/narter25a.html}, abstract = {Current screening programs that focus on improving patient health while minimizing screening costs are tailored for individual diseases. Designing unified screening programs for multiple diseases requires carefully balancing competing disease risks, which is an open problem. In this work, we address this problem by casting unified screening as a referral problem, in which we choose to activate a subset of screening policies for individual diseases by accounting for competing risks that influence patient outcomes. We introduce a novel optimization framework that incorporates disease risks, budget constraints, and diagnostic error limits and characterize the structural properties of the optimal referral policy. For the unified screening of two diseases, we show that the optimal activation threshold for the screening of one disease depends on the risk of the other, resulting in decision boundaries with distinct risk-dependent profiles. We compare our unified model with independent screening programs that apply isolated activation thresholds for screening of each disease. Our approach optimizes screening decisions collectively, improving overall survival outcomes, particularly for patients with high disease risks.} }
Endnote
%0 Conference Paper %T Unified Screening for Multiple Diseases %A Yiğit Narter %A Alihan Hüyük %A Mihaela Van Der Schaar %A Cem Tekin %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-narter25a %I PMLR %P 45737--45769 %U https://proceedings.mlr.press/v267/narter25a.html %V 267 %X Current screening programs that focus on improving patient health while minimizing screening costs are tailored for individual diseases. Designing unified screening programs for multiple diseases requires carefully balancing competing disease risks, which is an open problem. In this work, we address this problem by casting unified screening as a referral problem, in which we choose to activate a subset of screening policies for individual diseases by accounting for competing risks that influence patient outcomes. We introduce a novel optimization framework that incorporates disease risks, budget constraints, and diagnostic error limits and characterize the structural properties of the optimal referral policy. For the unified screening of two diseases, we show that the optimal activation threshold for the screening of one disease depends on the risk of the other, resulting in decision boundaries with distinct risk-dependent profiles. We compare our unified model with independent screening programs that apply isolated activation thresholds for screening of each disease. Our approach optimizes screening decisions collectively, improving overall survival outcomes, particularly for patients with high disease risks.
APA
Narter, Y., Hüyük, A., Van Der Schaar, M. & Tekin, C.. (2025). Unified Screening for Multiple Diseases. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:45737-45769 Available from https://proceedings.mlr.press/v267/narter25a.html.

Related Material