Utility based approach in individualized optimal dose selection using machine learning methods
dc.contributor.author | Li, Pin | |
dc.contributor.author | Taylor, Jeremy M. G. | |
dc.contributor.author | Boonstra, Philip S. | |
dc.contributor.author | Lawrence, Theodore S. | |
dc.contributor.author | Schipper, Matthew J. | |
dc.date.accessioned | 2022-07-05T21:01:48Z | |
dc.date.available | 2023-08-05 17:01:47 | en |
dc.date.available | 2022-07-05T21:01:48Z | |
dc.date.issued | 2022-07-20 | |
dc.identifier.citation | Li, Pin; Taylor, Jeremy M. G.; Boonstra, Philip S.; Lawrence, Theodore S.; Schipper, Matthew J. (2022). "Utility based approach in individualized optimal dose selection using machine learning methods." Statistics in Medicine 41(16): 2957-2977. | |
dc.identifier.issn | 0277-6715 | |
dc.identifier.issn | 1097-0258 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/172983 | |
dc.description.abstract | The goal in personalized medicine is to individualize treatment using patient characteristics and improve health outcomes. Selection of optimal dose must balance the effect of dose on both treatment efficacy and toxicity outcomes. We consider a setting with one binary efficacy and one binary toxicity outcome. The goal is to find the optimal dose for each patient using clinical features and biomarkers from available dataset. We propose to use flexible machine learning methods such as random forest and Gaussian process models to build models for efficacy and toxicity depending on dose and biomarkers. A copula is used to model the joint distribution of the two outcomes and the estimates are constrained to have non-decreasing dose-efficacy and dose-toxicity relationships. Numerical utilities are elicited from clinicians for each potential bivariate outcome. For each patient, the optimal dose is chosen to maximize the posterior mean of the utility function. We also propose alternative approaches to optimal dose selection by adding additional toxicity based constraints and an approach taking into account the uncertainty in the estimation of the utility function. The proposed methods are evaluated in a simulation study to compare expected utility outcomes under various estimated optimal dose rules. Gaussian process models tended to have better performance than random forest. Enforcing monotonicity during modeling provided small benefits. Whether and how, correlation between efficacy and toxicity, was modeled, had little effect on performance. The proposed methods are illustrated with a study of patients with liver cancer treated with stereotactic body radiation therapy. | |
dc.publisher | Wiley Periodicals, Inc. | |
dc.publisher | MIT Press | |
dc.subject.other | utility matrix | |
dc.subject.other | Gaussian process | |
dc.subject.other | random forest | |
dc.title | Utility based approach in individualized optimal dose selection using machine learning methods | |
dc.type | Article | |
dc.rights.robots | IndexNoFollow | |
dc.subject.hlbsecondlevel | Medicine (General) | |
dc.subject.hlbsecondlevel | Statistics and Numeric Data | |
dc.subject.hlbsecondlevel | Public Health | |
dc.subject.hlbtoplevel | Health Sciences | |
dc.subject.hlbtoplevel | Science | |
dc.subject.hlbtoplevel | Social Sciences | |
dc.description.peerreviewed | Peer Reviewed | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/172983/1/sim9396_am.pdf | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/172983/2/sim9396.pdf | |
dc.identifier.doi | 10.1002/sim.9396 | |
dc.identifier.source | Statistics in Medicine | |
dc.identifier.citedreference | Chipman HA, George EI, McCulloch RE, Shively TS. High-dimensional nonparametric monotone function estimation using BART arXiv preprint arXiv:1612.01619; 2016. | |
dc.identifier.citedreference | Foster JC, Taylor JMG, Ruberg SJ. Subgroup identification from randomized clinical trial data. Stat Med. 2011; 30: 2867 - 2880. | |
dc.identifier.citedreference | Zhao Y, Zeng D, Rush AJ, Kosorok MR. Estimating individualized treatment rules using outcome weighted learning. J Am Stat Assoc. 2012; 107: 1106 - 1118. | |
dc.identifier.citedreference | Williams CKI, Rasmussen CE. Gaussian Processes for Machine Learning. Vol 2. Cambridge, MA: MIT Press; 2006. | |
dc.identifier.citedreference | Logan BR, Sparapani R, Mc Culloch RE, Laud PW. Decision making and uncertainty quantification for individualized treatments using Bayesian additive regression trees. Stat Methods Med Res. 2019; 28 ( 4 ): 1079 - 1093. | |
dc.identifier.citedreference | Li P, Taylor JMG, Kong S, Jolly S, Schipper MJ. A utility approach to individualized optimal dose selection using biomarkers. Biom J. 2020; 62: 386 - 397. | |
dc.identifier.citedreference | Houede N, Thall PF, Nguyen H, Paoletti X, Kramar A. Utility-based optimization of combination therapy using ordinal toxicity and efficacy in phase I/II trials. Biometrics. 2010; 66: 532 - 540. | |
dc.identifier.citedreference | Thall PF, Cook JD. Dose-finding based on efficacy–Toxicity trade-offs. Biometrics. 2004; 60: 684 - 693. | |
dc.identifier.citedreference | FDA. Considerations for the design of early-phase clinical trials of cellular and gene therapy products. Draft guidance for industry. Rockville, MD: Center for Biologics Evaluation and Research, FDA; 2013. | |
dc.identifier.citedreference | Thall PF. Bayesian utility-based designs for subgroup-specific treatment comparison and early-phase dose optimization in oncology clinical trials. JCO Precis Oncol. 2019; 3: 1 - 7. | |
dc.identifier.citedreference | Seligman M. Rborist: extensible, parallelizable implementation of the random forest algorithm R package version; Version, 1(3), 2015:1-15. | |
dc.identifier.citedreference | Barlow RE, Bartholomew DJ, Bremner JM, Brunk HD. Statistical Inference Under Order Restrictions. Hoboken, NJ: Wiley; 1972. | |
dc.identifier.citedreference | Neal RM. Bayesian Learning for Neural Networks. Vol 118. Berlin, Germany: Springer Science & Business Media; 2012. | |
dc.identifier.citedreference | Team Stan Developent. RStan: the R interface to Stan R package version; 2016:2. | |
dc.identifier.citedreference | Riihimäki J, Vehtari A. Gaussian processes with monotonicity information. Paper presented at: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics; 2010:645-652. JMLR Workshop and Conference Proceedings. | |
dc.identifier.citedreference | Brook RH, Chassin MR, Fink A, Solomon DH, Kosecoff J, Park RE. A method for the detailed assessment of the appropriateness of medical technologies. Int J Technol Assess Health Care. 1986; 2: 53 - 63. | |
dc.identifier.citedreference | Chipman HA, George EI, McCulloch RE. BART: Bayesian additive regression trees. Ann Appl Stat. 2010; 4: 266 - 298. | |
dc.identifier.citedreference | Chen T, Guestrin C. Xgboost: a scalable tree boosting system Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016:785-794; ACM, New York, NY. | |
dc.identifier.citedreference | Linero AR. A review of tree-based Bayesian methods. Commun Stat Appl Methods. 2017; 24 ( 6 ): 543 - 559. | |
dc.identifier.citedreference | Carvalho CM, Polson NG, Scott JG. Handling sparsity via the horseshoe. Artificial Intelligence and Statistics. PMLR; 2009: 73 - 80. | |
dc.identifier.citedreference | Glasziou PP, Simes RJ, Gelber RD. Quality adjusted survival analysis. Stat Med. 1990; 9: 1259 - 1276. | |
dc.identifier.citedreference | Diniz MA, Tighiouart M, Rogatko A. Comparison between continuous and discrete doses for model based designs in cancer dose finding. PLoS One. 2019; 14: e0210139. | |
dc.identifier.citedreference | Song Peter X-K, Li M, Yuan Y. Joint regression analysis of correlated data using Gaussian copulas. Biometrics. 2009; 65 ( 1 ): 60 - 68. | |
dc.identifier.citedreference | Joe H, Xu JJ. The estimation method of inference functions for margins for multivariate models; 1996. | |
dc.working.doi | NO | en |
dc.owningcollname | Interdisciplinary and Peer-Reviewed |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.