Investigating fair data acquisition for risk prediction in resource-constrained settings

Ioanna Thoma, Elisabeth Abhayaratna, Matthew Sperrin, Karla Diaz-Ordaz, Ricardo Silva, Brieuc Lehmann
Proceedings of Fourth European Workshop on Algorithmic Fairness, PMLR 294:288-294, 2025.

Abstract

Clinical prediction models (CPMs) play a crucial role in precision medicine, enabling the identification of high-risk patients for targeted interventions. In many settings, additional covariates may be collected to improve risk prediction, but doing so for the entire population may not be feasible due to resource constraints. A key challenge is to determine who should receive these additional resource-intensive assessments in an efficient and equitable manner. Here, we explore policies to select which patients should be selected for additional testing based on a baseline risk estimate. We investigate these policies in the context of an integrated risk tool for cardiovascular disease. This explores how the application of a more complex, and expensive, CPM on a subset of the population can improve fairness. The proposed methodological approaches have the potential to guide future application of CPMs to prioritise patient populations who would most benefit from access to additional investigations and access to more complex CPMs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v294-thoma25a, title = {Investigating fair data acquisition for risk prediction in resource-constrained settings}, author = {Thoma, Ioanna and Abhayaratna, Elisabeth and Sperrin, Matthew and Diaz-Ordaz, Karla and Silva, Ricardo and Lehmann, Brieuc}, booktitle = {Proceedings of Fourth European Workshop on Algorithmic Fairness}, pages = {288--294}, year = {2025}, editor = {Weerts, Hilde and Pechenizkiy, Mykola and Allhutter, Doris and Corrêa, Ana Maria and Grote, Thomas and Liem, Cynthia}, volume = {294}, series = {Proceedings of Machine Learning Research}, month = {30 Jun--02 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v294/main/assets/thoma25a/thoma25a.pdf}, url = {https://proceedings.mlr.press/v294/thoma25a.html}, abstract = {Clinical prediction models (CPMs) play a crucial role in precision medicine, enabling the identification of high-risk patients for targeted interventions. In many settings, additional covariates may be collected to improve risk prediction, but doing so for the entire population may not be feasible due to resource constraints. A key challenge is to determine who should receive these additional resource-intensive assessments in an efficient and equitable manner. Here, we explore policies to select which patients should be selected for additional testing based on a baseline risk estimate. We investigate these policies in the context of an integrated risk tool for cardiovascular disease. This explores how the application of a more complex, and expensive, CPM on a subset of the population can improve fairness. The proposed methodological approaches have the potential to guide future application of CPMs to prioritise patient populations who would most benefit from access to additional investigations and access to more complex CPMs.} }
Endnote
%0 Conference Paper %T Investigating fair data acquisition for risk prediction in resource-constrained settings %A Ioanna Thoma %A Elisabeth Abhayaratna %A Matthew Sperrin %A Karla Diaz-Ordaz %A Ricardo Silva %A Brieuc Lehmann %B Proceedings of Fourth European Workshop on Algorithmic Fairness %C Proceedings of Machine Learning Research %D 2025 %E Hilde Weerts %E Mykola Pechenizkiy %E Doris Allhutter %E Ana Maria Corrêa %E Thomas Grote %E Cynthia Liem %F pmlr-v294-thoma25a %I PMLR %P 288--294 %U https://proceedings.mlr.press/v294/thoma25a.html %V 294 %X Clinical prediction models (CPMs) play a crucial role in precision medicine, enabling the identification of high-risk patients for targeted interventions. In many settings, additional covariates may be collected to improve risk prediction, but doing so for the entire population may not be feasible due to resource constraints. A key challenge is to determine who should receive these additional resource-intensive assessments in an efficient and equitable manner. Here, we explore policies to select which patients should be selected for additional testing based on a baseline risk estimate. We investigate these policies in the context of an integrated risk tool for cardiovascular disease. This explores how the application of a more complex, and expensive, CPM on a subset of the population can improve fairness. The proposed methodological approaches have the potential to guide future application of CPMs to prioritise patient populations who would most benefit from access to additional investigations and access to more complex CPMs.
APA
Thoma, I., Abhayaratna, E., Sperrin, M., Diaz-Ordaz, K., Silva, R. & Lehmann, B.. (2025). Investigating fair data acquisition for risk prediction in resource-constrained settings. Proceedings of Fourth European Workshop on Algorithmic Fairness, in Proceedings of Machine Learning Research 294:288-294 Available from https://proceedings.mlr.press/v294/thoma25a.html.

Related Material