Using Foundation Models to Prescribe Patients Proper Antibiotics

Simon A. Lee, Helio Halperin, Yanai Halperin, Trevor Brokowski, Jeffrey N. Chiang
Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 281:121-132, 2025.

Abstract

The rise of antibiotic-resistant bacteria presents a significant global health threat by reducing the effectiveness of essential treatments. This study evaluates the potential of clinical decision support systems powered by biomedical language foundation models to enhance antibiotic stewardship using electronic health records (EHRs). We test several state-of-the-art models, focusing on predicting whether each of eight different antibiotics will be effective for an individual patient. Additionally, we emphasize interpretability, aiming to understand how the models make decisions, where they excel, and where they fall short. Unlike previous research, which primarily benchmarks accuracy metrics, we provide insights into both the successes and limitations of these models, offering clinical and non-clinical experts a clearer understanding of their current state and reliability. These findings highlight the potential of AI systems to combat this global health threat, as well as the need for further improvements to address the limitations of existing models. We hope this work offers valuable guidance for improving AI-driven decision support systems and leveraging these advanced models for other clinical applications. Code — https://github.com/Simonlee711/antibiotics-fm- benchmark. Datasets —https://physionet.org/content/mimiciv/3.1/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v281-lee25a, title = {Using Foundation Models to Prescribe Patients Proper Antibiotics}, author = {Lee, Simon A. and Halperin, Helio and Halperin, Yanai and Brokowski, Trevor and Chiang, Jeffrey N.}, booktitle = {Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {121--132}, year = {2025}, editor = {Wu, Junde and Zhu, Jiayuan and Xu, Min and Jin, Yueming}, volume = {281}, series = {Proceedings of Machine Learning Research}, month = {25 Feb}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v281/main/assets/lee25a/lee25a.pdf}, url = {https://proceedings.mlr.press/v281/lee25a.html}, abstract = {The rise of antibiotic-resistant bacteria presents a significant global health threat by reducing the effectiveness of essential treatments. This study evaluates the potential of clinical decision support systems powered by biomedical language foundation models to enhance antibiotic stewardship using electronic health records (EHRs). We test several state-of-the-art models, focusing on predicting whether each of eight different antibiotics will be effective for an individual patient. Additionally, we emphasize interpretability, aiming to understand how the models make decisions, where they excel, and where they fall short. Unlike previous research, which primarily benchmarks accuracy metrics, we provide insights into both the successes and limitations of these models, offering clinical and non-clinical experts a clearer understanding of their current state and reliability. These findings highlight the potential of AI systems to combat this global health threat, as well as the need for further improvements to address the limitations of existing models. We hope this work offers valuable guidance for improving AI-driven decision support systems and leveraging these advanced models for other clinical applications. Code — https://github.com/Simonlee711/antibiotics-fm- benchmark. Datasets —https://physionet.org/content/mimiciv/3.1/.} }
Endnote
%0 Conference Paper %T Using Foundation Models to Prescribe Patients Proper Antibiotics %A Simon A. Lee %A Helio Halperin %A Yanai Halperin %A Trevor Brokowski %A Jeffrey N. Chiang %B Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2025 %E Junde Wu %E Jiayuan Zhu %E Min Xu %E Yueming Jin %F pmlr-v281-lee25a %I PMLR %P 121--132 %U https://proceedings.mlr.press/v281/lee25a.html %V 281 %X The rise of antibiotic-resistant bacteria presents a significant global health threat by reducing the effectiveness of essential treatments. This study evaluates the potential of clinical decision support systems powered by biomedical language foundation models to enhance antibiotic stewardship using electronic health records (EHRs). We test several state-of-the-art models, focusing on predicting whether each of eight different antibiotics will be effective for an individual patient. Additionally, we emphasize interpretability, aiming to understand how the models make decisions, where they excel, and where they fall short. Unlike previous research, which primarily benchmarks accuracy metrics, we provide insights into both the successes and limitations of these models, offering clinical and non-clinical experts a clearer understanding of their current state and reliability. These findings highlight the potential of AI systems to combat this global health threat, as well as the need for further improvements to address the limitations of existing models. We hope this work offers valuable guidance for improving AI-driven decision support systems and leveraging these advanced models for other clinical applications. Code — https://github.com/Simonlee711/antibiotics-fm- benchmark. Datasets —https://physionet.org/content/mimiciv/3.1/.
APA
Lee, S.A., Halperin, H., Halperin, Y., Brokowski, T. & Chiang, J.N.. (2025). Using Foundation Models to Prescribe Patients Proper Antibiotics. Proceedings of The First AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 281:121-132 Available from https://proceedings.mlr.press/v281/lee25a.html.

Related Material