Integrating Machine Learning and Optimization Methods for Imaging of Patients with Prostate Cancer

Selin Merdan, Khurshid Ghani, Brian Denton
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:119-136, 2018.

Abstract

We combine predictive modeling techniques from machine learning and optimization methods to design coordinated imaging protocols for detection of metastatic cancer. Our approach considers different combinations of imaging tests to reduce imaging while also ensuring that the average risk of missing a metastatic cancer in the population does not exceed a desirable threshold. To account for the imperfect calibration of probability estimates obtained from predictive models, we formulate the decision problem of determining the optimal assignment of patients to imaging protocols as a robust mixed-integer program. Furthermore, we propose fast, easy-to-understand and clinically motivated approximation algorithms that can mitigate the effects of statistical error in predictions. We illustrate the practical performance of the proposed approximation algorithms and optimization models based on medical data collected by a large state-wide prostate cancer collaborative. The work presented in this article will help lay the groundwork to improve medical decision making by integrating machine learning and optimization in other disease areas.

Cite this Paper

BibTeX
@InProceedings{pmlr-v85-merdan18a, title = {Integrating Machine Learning and Optimization Methods for Imaging of Patients with Prostate Cancer}, author = {Merdan, Selin and Ghani, Khurshid and Denton, Brian}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {119--136}, year = {2018}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {85}, series = {Proceedings of Machine Learning Research}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/merdan18a/merdan18a.pdf}, url = {https://proceedings.mlr.press/v85/merdan18a.html}, abstract = {We combine predictive modeling techniques from machine learning and optimization methods to design coordinated imaging protocols for detection of metastatic cancer. Our approach considers different combinations of imaging tests to reduce imaging while also ensuring that the average risk of missing a metastatic cancer in the population does not exceed a desirable threshold. To account for the imperfect calibration of probability estimates obtained from predictive models, we formulate the decision problem of determining the optimal assignment of patients to imaging protocols as a robust mixed-integer program. Furthermore, we propose fast, easy-to-understand and clinically motivated approximation algorithms that can mitigate the effects of statistical error in predictions. We illustrate the practical performance of the proposed approximation algorithms and optimization models based on medical data collected by a large state-wide prostate cancer collaborative. The work presented in this article will help lay the groundwork to improve medical decision making by integrating machine learning and optimization in other disease areas.} }
Endnote
%0 Conference Paper %T Integrating Machine Learning and Optimization Methods for Imaging of Patients with Prostate Cancer %A Selin Merdan %A Khurshid Ghani %A Brian Denton %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-merdan18a %I PMLR %P 119--136 %U https://proceedings.mlr.press/v85/merdan18a.html %V 85 %X We combine predictive modeling techniques from machine learning and optimization methods to design coordinated imaging protocols for detection of metastatic cancer. Our approach considers different combinations of imaging tests to reduce imaging while also ensuring that the average risk of missing a metastatic cancer in the population does not exceed a desirable threshold. To account for the imperfect calibration of probability estimates obtained from predictive models, we formulate the decision problem of determining the optimal assignment of patients to imaging protocols as a robust mixed-integer program. Furthermore, we propose fast, easy-to-understand and clinically motivated approximation algorithms that can mitigate the effects of statistical error in predictions. We illustrate the practical performance of the proposed approximation algorithms and optimization models based on medical data collected by a large state-wide prostate cancer collaborative. The work presented in this article will help lay the groundwork to improve medical decision making by integrating machine learning and optimization in other disease areas.
APA
Merdan, S., Ghani, K. & Denton, B.. (2018). Integrating Machine Learning and Optimization Methods for Imaging of Patients with Prostate Cancer. Proceedings of the 3rd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 85:119-136 Available from https://proceedings.mlr.press/v85/merdan18a.html.

Related Material