Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials

Onur Atan, William R. Zame, Mihaela Schaar
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:1891-1900, 2019.

Abstract

Randomized Controlled Trials (RCTs) are the gold standard for comparing the effectiveness of a new treatment to the current one (the control). Most RCTs allocate the patients to the treatment group and the control group by uniform randomization. We show that this procedure can be highly sub-optimal (in terms of learning) if – as is often the case – patients can be recruited in cohorts (rather than all at once), the effects on each cohort can be observed before recruiting the next cohort, and the effects are heterogeneous across identifiable subgroups of patients. We formulate the patient allocation problem as a finite stage Markov Decision Process in which the objective is to minimize a given weighted combination of type-I and type-II errors. Because finding the exact solution to this Markov Decision Process is computationally intractable, we propose an algorithm Knowledge Gradient for Randomized Controlled Trials (RCT-KG) – that yields an approximate solution. Our experiment on a synthetic dataset with Bernoulli outcomes shows that for a given size of trial our method achieves significant reduction in error, and to achieve a prescribed level of confidence (in identifying whether the treatment is superior to the control), our method requires many fewer patients.

Cite this Paper


BibTeX
@InProceedings{pmlr-v89-atan19a, title = {Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials}, author = {Atan, Onur and Zame, William R. and van der Schaar, Mihaela}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {1891--1900}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/atan19a/atan19a.pdf}, url = {https://proceedings.mlr.press/v89/atan19a.html}, abstract = {Randomized Controlled Trials (RCTs) are the gold standard for comparing the effectiveness of a new treatment to the current one (the control). Most RCTs allocate the patients to the treatment group and the control group by uniform randomization. We show that this procedure can be highly sub-optimal (in terms of learning) if – as is often the case – patients can be recruited in cohorts (rather than all at once), the effects on each cohort can be observed before recruiting the next cohort, and the effects are heterogeneous across identifiable subgroups of patients. We formulate the patient allocation problem as a finite stage Markov Decision Process in which the objective is to minimize a given weighted combination of type-I and type-II errors. Because finding the exact solution to this Markov Decision Process is computationally intractable, we propose an algorithm Knowledge Gradient for Randomized Controlled Trials (RCT-KG) – that yields an approximate solution. Our experiment on a synthetic dataset with Bernoulli outcomes shows that for a given size of trial our method achieves significant reduction in error, and to achieve a prescribed level of confidence (in identifying whether the treatment is superior to the control), our method requires many fewer patients.} }
Endnote
%0 Conference Paper %T Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials %A Onur Atan %A William R. Zame %A Mihaela Schaar %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-atan19a %I PMLR %P 1891--1900 %U https://proceedings.mlr.press/v89/atan19a.html %V 89 %X Randomized Controlled Trials (RCTs) are the gold standard for comparing the effectiveness of a new treatment to the current one (the control). Most RCTs allocate the patients to the treatment group and the control group by uniform randomization. We show that this procedure can be highly sub-optimal (in terms of learning) if – as is often the case – patients can be recruited in cohorts (rather than all at once), the effects on each cohort can be observed before recruiting the next cohort, and the effects are heterogeneous across identifiable subgroups of patients. We formulate the patient allocation problem as a finite stage Markov Decision Process in which the objective is to minimize a given weighted combination of type-I and type-II errors. Because finding the exact solution to this Markov Decision Process is computationally intractable, we propose an algorithm Knowledge Gradient for Randomized Controlled Trials (RCT-KG) – that yields an approximate solution. Our experiment on a synthetic dataset with Bernoulli outcomes shows that for a given size of trial our method achieves significant reduction in error, and to achieve a prescribed level of confidence (in identifying whether the treatment is superior to the control), our method requires many fewer patients.
APA
Atan, O., Zame, W.R. & Schaar, M.. (2019). Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:1891-1900 Available from https://proceedings.mlr.press/v89/atan19a.html.

Related Material