Improving Individualized Treatment Decisions: A Bayesian Multivariate Hierarchical Model for Developing a Treatment Benefit Index using Mixed Types of Outcomes.
Bayesian multivariate hierarchical model
COVID-19
Individualized treatment decision rule
Precision medicine
Treatment benefit index model
Journal
medRxiv : the preprint server for health sciences
Titre abrégé: medRxiv
Pays: United States
ID NLM: 101767986
Informations de publication
Date de publication:
18 Nov 2023
18 Nov 2023
Historique:
pubmed:
28
11
2023
medline:
28
11
2023
entrez:
28
11
2023
Statut:
epublish
Résumé
Precision medicine has led to the development of targeted treatment strategies tailored to individual patients based on their characteristics and disease manifestations. Although precision medicine often focuses on a single health outcome for individualized treatment decision rules (ITRs), relying only on a single outcome rather than all available outcomes information leads to suboptimal data usage when developing optimal ITRs. To address this limitation, we propose a Bayesian multivariate hierarchical model that leverages the wealth of correlated health outcomes collected in clinical trials. The approach jointly models mixed types of correlated outcomes, facilitating the "borrowing of information" across the multivariate outcomes, and results in a more accurate estimation of heterogeneous treatment effects compared to using single regression models for each outcome. We develop a treatment benefit index, which quantifies the relative treatment benefit of the experimental treatment over the control treatment, based on the proposed multivariate outcome model. We demonstrate the strengths of the proposed approach through extensive simulations and an application to an international Coronavirus Disease 2019 (COVID-19) treatment trial. Simulation results indicate that the proposed method reduces the occurrence of erroneous treatment decisions compared to a single regression model for a single health outcome. Additionally, the sensitivity analysis demonstrates the robustness of the model across various study scenarios. Application of the method to the COVID-19 trial exhibits improvements in estimating the individual-level treatment efficacy (indicated by narrower credible intervals for odds ratios) and optimal ITRs. The study jointly models mixed types of outcomes in the context of developing ITRs. By considering multiple health outcomes, the proposed approach can advance the development of more effective and reliable personalized treatment.
Sections du résumé
Background
UNASSIGNED
Precision medicine has led to the development of targeted treatment strategies tailored to individual patients based on their characteristics and disease manifestations. Although precision medicine often focuses on a single health outcome for individualized treatment decision rules (ITRs), relying only on a single outcome rather than all available outcomes information leads to suboptimal data usage when developing optimal ITRs.
Methods
UNASSIGNED
To address this limitation, we propose a Bayesian multivariate hierarchical model that leverages the wealth of correlated health outcomes collected in clinical trials. The approach jointly models mixed types of correlated outcomes, facilitating the "borrowing of information" across the multivariate outcomes, and results in a more accurate estimation of heterogeneous treatment effects compared to using single regression models for each outcome. We develop a treatment benefit index, which quantifies the relative treatment benefit of the experimental treatment over the control treatment, based on the proposed multivariate outcome model.
Results
UNASSIGNED
We demonstrate the strengths of the proposed approach through extensive simulations and an application to an international Coronavirus Disease 2019 (COVID-19) treatment trial. Simulation results indicate that the proposed method reduces the occurrence of erroneous treatment decisions compared to a single regression model for a single health outcome. Additionally, the sensitivity analysis demonstrates the robustness of the model across various study scenarios. Application of the method to the COVID-19 trial exhibits improvements in estimating the individual-level treatment efficacy (indicated by narrower credible intervals for odds ratios) and optimal ITRs.
Conclusion
UNASSIGNED
The study jointly models mixed types of outcomes in the context of developing ITRs. By considering multiple health outcomes, the proposed approach can advance the development of more effective and reliable personalized treatment.
Identifiants
pubmed: 38014277
doi: 10.1101/2023.11.17.23298711
pmc: PMC10680905
pii:
doi:
Types de publication
Preprint
Langues
eng
Subventions
Organisme : NCATS NIH HHS
ID : UL1 TR001445
Pays : United States
Déclaration de conflit d'intérêts
Competing interests The authors declare that they have no competing interests.
Références
J Am Stat Assoc. 2015;110(510):583-598
pubmed: 26236062
Electron J Stat. 2018;12(1):2074-2089
pubmed: 30416643
JAMA Netw Open. 2022 Jan 4;5(1):e2147375
pubmed: 35076698
J Biopharm Stat. 2020 May 3;30(3):462-480
pubmed: 31691633
Int J Biostat. 2020 Aug 13;17(1):7-21
pubmed: 32784265
Biometrics. 2018 Mar;74(1):18-26
pubmed: 28742260
J Mach Learn Res. 2021 Jan;22:
pubmed: 34733120
Stat Med. 2022 Jul 10;41(15):2695-2710
pubmed: 35699385
J Comput Graph Stat. 2010 Fall;19(4):947-962
pubmed: 24963268
J Biopharm Stat. 2002 May;12(2):121-35
pubmed: 12413235
J Am Stat Assoc. 2018;113(521):1-13
pubmed: 30034060
Biometrika. 2015;102(3):501-514
pubmed: 26893526
Electron J Stat. 2016;10:2894-2921
pubmed: 28781717
BMC Med Res Methodol. 2023 Jan 25;23(1):25
pubmed: 36698073
J Am Stat Assoc. 2012 Sep 1;107(449):1106-1118
pubmed: 23630406
Neuroimage. 2022 Apr 1;249:118854
pubmed: 34971767
J Mach Learn Res. 2012 Nov;13(Nov):3253-3295
pubmed: 23741197
J Am Stat Assoc. 2017;113(523):1219-1227
pubmed: 30416232
J Mach Learn Res. 2016;17:
pubmed: 28018133
BMC Bioinformatics. 2011 Mar 17;12:77
pubmed: 21414208
Stat Methods Med Res. 2013 Oct;22(5):493-504
pubmed: 22116341
Ann Stat. 2011 Apr 1;39(2):1180-1210
pubmed: 21666835
Lancet Infect Dis. 2020 Aug;20(8):e192-e197
pubmed: 32539990
Stat Med. 2022 Dec 27;:
pubmed: 36574753
Biostatistics. 2017 Jan;18(1):105-118
pubmed: 27465235
J Am Stat Assoc. 2014 Oct;109(508):1517-1532
pubmed: 25729117
JAMA Netw Open. 2022 Jan 4;5(1):e2147331
pubmed: 35076699
Stat Med. 2018 Apr 30;37(9):1407-1418
pubmed: 29468702
J Mach Learn Res. 2019;20:
pubmed: 31440118
Stat. 2015;4(1):59-68
pubmed: 25883393
J R Stat Soc Ser C Appl Stat. 2021 Aug;70(4):886-908
pubmed: 35001978
Biometrics. 2014 Mar;70(1):53-61
pubmed: 24400912
J Am Stat Assoc. 2021;116(533):269-282
pubmed: 34776561
Stat Med. 2021 Oct 30;40(24):5131-5151
pubmed: 34164838