Artificial Intelligence for Healthcare Interdisciplinary Partnerships for Analytics-driven Improvements in a Post-COVID World
Book contents
3 - Personalizing Medicine
Estimating Heterogeneous Treatment Effects
from Part I - Personalized Medicine
Published online by Cambridge University Press: 21 April 2022
Summary
We describe fundamental challenges to estimating heterogeneous treatment effects in the context of the statistical causal inference literature, proposed algorithms for addressing those challenges, and methods to evaluate how well heterogeneous treatment effects have been estimated. We illustrate the proposed algorithms using data from two large randomized trials of blood pressure treatments. We describe directions for future research in medical statistics and machine learning in this domain. The focus will be on how flexible machine learning methods can improve causal estimators, especially in the RCT setting.
Keywords
- Type
- Chapter
- Information
- Artificial Intelligence for HealthcareInterdisciplinary Partnerships for Analytics-driven Improvements in a Post-COVID World, pp. 37 - 59Publisher: Cambridge University PressPrint publication year: 2022
References
Alba, Ana Carolina, Agoritsas, Thomas, Walsh, Michael, Hanna, Steven, Iorio, Alfonso, Devereaux, P. J., McGinn, Thomas, and Guyatt, Gordon. 2017. Discrimination and calibration of clinical prediction models: Users’ guides to the medical literature. JAMA, 318(14), 1377–1384.CrossRefGoogle ScholarPubMed
Athey, Susan, and Imbens, Guido. 2016. Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of Sciences, 113(27), 7353–7360.CrossRefGoogle ScholarPubMed
Basu, Sanjay, Sussman, Jeremy B., Rigdon, Joseph, Steimle, Lauren, Denton, Brian T., and Hayward, Rodney A. 2017. Benefit and harm of intensive blood pressure treatment: Derivation and validation of risk models using data from the SPRINT and ACCORD trials. PLOs Medicine, 14(10), e1002410.Google Scholar
Chernozhukov, Victor, Chetverikov, Denis, Demirer, Mert, Duflo, Esther, Hansen, Christian, Newey, Whitney, and Robins, James. 2018. Double/debiased machine learning for treatment and structural parameters. The Econometrics Journal, 21(1), C1–C68.Google Scholar
Coppock, Alexander, Leeper, Thomas J., and Mullinix, Kevin J. 2018. Generalizability of heterogeneous treatment effect estimates across samples. Proceedings of the National Academy of Sciences, 115(49), 12441–12446.Google Scholar
Dahabreh, Issa J., Trikalinos, Thomas A., Kent, David M., and Schmid, Christopher H. 2017. Heterogeneity of treatment effects. Pages 227–272 of: Methods in Comparative Effectiveness Research, edited by Gatsonis, Constantine and Morton, Sally C.. New York: Chapman and Hall/CRC.Google Scholar
Davidoff, Frank. 2017. Can knowledge about heterogeneity in treatment effects help us choose wisely? Annals of Internal Medicine, 166(2), 141–142.CrossRefGoogle ScholarPubMed
Davis, Jesse, and Goadrich, Mark. 2006. The relationship between precision-recall and ROC curves. Pages 233–240 of: Proceedings of the 23rd International Conference on Machine Learning. ICML ’06, Pittsburgh, Pennsylvania, USA. New York: ACM.CrossRefGoogle Scholar
Duan, Tony, Pranav, Rajpurkar, Dillon, Laird, Ng, Andrew Y., and Sanjay, Basu. 2019. Clinical value of predicting individual treatment effects for intensive blood pressure therapy. Circulation: Cardiovascular Quality and Outcomes, 12(3), e005010.Google Scholar
Friedman, Jerome H. 2001. Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232.CrossRefGoogle Scholar
Gottesman, Omer, Johansson, Fredrik, Komorowski, Matthieu, Faisal, Aldo, Sontag, David, Doshi-Velez, Finale, and Celi, Leo Anthony. 2019. Guidelines for reinforcement learning in healthcare. Nature Medicine, 25(1), 16–18.Google Scholar
Harrell, Frank. 2001. Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis. Springer Series in Statistics. New York: Springer-Verlag.CrossRefGoogle Scholar
Hastie, Trevor, Tibshirani, Robert, and Friedman, Jerome. 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. Springer Series in Statistics. New York: Springer-Verlag.Google Scholar
Hayward, Rodney A., Kent, David M., Vijan, Sandeep, and Hofer, Timothy P. 2006. Multivariable risk prediction can greatly enhance the statistical power of clinical trial subgroup analysis. BMC Medical Research Methodology, 6(1), 18.CrossRefGoogle ScholarPubMed
Imbens, Guido W., and Rubin, Donald B. 2015. Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction. New York: Cambridge University Press.CrossRefGoogle Scholar
Kent, David M., Rothwell, Peter M., Ioannidis, John P. A., Altman, Doug G., and Hayward, Rodney A. 2010. Assessing and reporting heterogeneity in treatment effects in clinical trials: A proposal. Trials, 11(August), 85.CrossRefGoogle ScholarPubMed
Kent, David M., Nelson, Jason, Dahabreh, Issa J., Rothwell, Peter M., Altman, Douglas G., and Hayward, Rodney A. 2016. Risk and treatment effect heterogeneity: Re-analysis of individual participant data from 32 large clinical trials. International Journal of Epidemiology, 45(6), 2075–2088.Google Scholar
Kent, David M., Paulus, Jessica K., van Klaveren, David, D’Agostino, Ralph, Goodman, Steve, Hayward, Rodney, Ioannidis, John P. A., Patrick-Lake, Bray, Morton, Sally, Pencina, Michael, Raman, Gowri, Ross, Joseph S., Selker, Harry P., Varadhan, Ravi, Vickers, Andrew, Wong, John B., and Steyerberg, Ewout W. 2020. The Predictive Approaches to Treatment effect Heterogeneity (PATH) statement. Annals of Internal Medicine, 172(1), 35–45.Google Scholar
Komorowski, Matthieu, Celi, Leo A., Badawi, Omar, Gordon, Anthony C., and Faisal, A. Aldo. 2018. The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care. Nature Medicine, 24(11), 1716–1720.Google Scholar
Künzel, Sören R., Sekhon, Jasjeet S., Bickel, Peter J., and Yu, Bin. 2019. Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the National Academy of Sciences, 116(10), 4156–4165.Google Scholar
Murdoch, W. James, Singh, Chandan, Kumbier, Karl, Abbasi-Asl, Reza, and Yu, Bin. 2019. Definitions, methods, and applications in interpretable machine learning. Proceedings of the National Academy of Sciences, 116(44), 22071–22080.Google Scholar
Patel, Krishna K., Arnold, Suzanne V., Chan, Paul S., Tang, Yuanyuan, Pokharel, Yashashwi, Jones, Philip G., and Spertus, John A. 2017. Personalizing the intensity of blood pressure control: Modeling the heterogeneity of risks and benefits from SPRINT (Systolic Blood Pressure Intervention Trial). Circulation: Cardiovascular Quality and Outcomes, 10(4), e003624.Google Scholar
The ACCORD Study Group. 2010. Effects of intensive blood-pressure control in type 2 diabetes mellitus. New England Journal of Medicine, 362(17), 1575–1585.Google Scholar
The SPRINT Research Group. 2015. A randomized trial of intensive versus standard blood-pressure control. New England Journal of Medicine, 373(22), 2103–2116.CrossRefGoogle Scholar
van Klaveren, David, Steyerberg, Ewout W., Serruys, Patrick W., and Kent, David M. 2018. The proposed ‘concordance-statistic for benefit’ provided a useful metric when modeling heterogeneous treatment effects. Journal of Clinical Epidemiology, 94(February), 59–68.Google Scholar
Vock, David M., Wolfson, Julian, Bandyopadhyay, Sunayan, Adomavicius, Gediminas, Johnson, Paul E., Vazquez-Benitez, Gabriela, and O’Connor, Patrick J. 2016. Adapting machine learning techniques to censored time-to-event health record data: A general-purpose approach using inverse probability of censoring weighting. Journal of Biomedical Informatics, 61(June), 119–131.CrossRefGoogle Scholar
Wager, Stefan, and Athey, Susan. 2018. Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228–1242.Google Scholar
Wallach, Joshua D., Sullivan, Patrick G., Trepanowski, John F., Sainani, Kristin L., Steyerberg, Ewout W., and Ioannidis, John P. A. 2017. Evaluation of evidence of statistical support and corroboration of subgroup claims in randomized clinical trials. JAMA Internal Medicine, 177(4), 554–560.CrossRefGoogle ScholarPubMed